Cross-border e-commerce item selection method and system based on dynamic time planning algorithm

Abstract

The invention is suitable for the technical field of e-commerce, and provides a cross-border e-commerce item selection method and system based on a dynamic time planning algorithm, and the method comprises the steps: firstly obtaining excellent commodity data set information and to-be-analyzed commodity data set information, and then obtaining a first category ranking information according to a time interval and a plurality of first category ranking information; the method comprises the steps of generating ideal ranking curve information according to a first category of ranking information, generating to-be-analyzed ranking curve information according to a time interval and the second category of ranking information, quickly generating similarity comparison result set information according to the ideal ranking curve information and the to-be-analyzed ranking curve information, and finally determining the ranking curve according to the similarity comparison result set information and comparison result threshold set information. And the target commodity name information is accurately determined. According to the method and the device, the seller can be efficiently and conveniently helped to find out potential commodities in the market, the user experience is remarkably improved, the market opportunity is furthest grasped, and the seller can obtain remarkable advantages in commodity selection and operation strategies.

Description

Technical Field

[0001] The present application relates to the technical field of e-commerce, and more specifically, to a cross-border e-commerce product selection method and system based on a dynamic time planning algorithm. Background Art

[0002] With the rapid development of computer and network technology and the advancement of global economic integration, cross-border e-commerce (abbreviated as "cross-border e-commerce") has rapidly emerged as a new international trade model around the world. Cross-border e-commerce has broken the time and space limitations of traditional trade, used Internet technology to build a trading platform, and promoted the transformation and development of international trade.

[0003] At present, e-commerce product selection mainly relies on the selector's industry experience and some simple data analysis methods, which often leads to less than ideal product selection results and cannot meet actual market demand. There is a problem of poor user experience and further improvement is needed. Summary of the invention

[0004] Based on this, the embodiment of the present application provides a cross-border e-commerce product selection method and system based on a dynamic time planning algorithm to solve the problem of poor user experience in the prior art.

[0005] In a first aspect, an embodiment of the present application provides a cross-border e-commerce product selection method based on a dynamic time planning algorithm, the method comprising:

[0006] Acquire excellent product data set information and product data set information to be analyzed, wherein the excellent product data set information includes excellent product name information and a plurality of first category ranking information corresponding to the excellent product name information, and the product data set information to be analyzed includes a plurality of product data information to be analyzed and a plurality of second category ranking information corresponding to each of the product data information to be analyzed, and the category to which the product data information to be analyzed belongs is the same as the category to which the excellent product name information belongs;

[0007] For the excellent product name information: according to the preset time interval and the plurality of first category ranking information, generate the ideal ranking curve information; and for each of the product data information to be analyzed: according to the time interval and the plurality of second category ranking information, generate the ranking curve information to be analyzed;

[0008] Generate similarity comparison result set information according to the ideal ranking curve information and the ranking curve information to be analyzed;

[0009] The target product name information is determined based on the similarity comparison result set information and the preset comparison result threshold set information.

[0010] Compared with the prior art, the beneficial effect is as follows: the cross-border e-commerce product selection method based on the dynamic time planning algorithm provided by the embodiment of the present application, the terminal device can first obtain the excellent product data set information and the product data set information to be analyzed, and then perform the processing on the excellent product name information: generate the ideal ranking curve information according to the preset time interval and multiple first category ranking information, and perform the processing on each product data information to be analyzed at the same time: generate the ranking curve information to be analyzed according to the time interval and multiple second category ranking information, and then quickly generate the similarity comparison result set information according to the ideal ranking curve information and the ranking curve information to be analyzed, and finally accurately determine the target product name information according to the similarity comparison result set information and the preset comparison result threshold set information, so as to accurately, quickly and conveniently identify potential products on the market for sellers, effectively improve the user experience, and to a certain extent solve the current problem of poor user experience.

[0011] In a second aspect, an embodiment of the present application provides a cross-border e-commerce product selection system based on a dynamic time planning algorithm, the system comprising:

[0012] A commodity data set information acquisition module: used to acquire excellent commodity data set information and commodity data set information to be analyzed, wherein the excellent commodity data set information includes excellent commodity name information and a plurality of first category ranking information corresponding to the excellent commodity name information, and the commodity data set information to be analyzed includes a plurality of commodity data information to be analyzed and a plurality of second category ranking information corresponding to each of the commodity data information to be analyzed, and the category to which the commodity data information to be analyzed belongs is the same as the category to which the excellent commodity name information belongs;

[0013] A ranking curve information generating module: used for generating ideal ranking curve information for the excellent product name information according to a preset time interval and a plurality of the first category ranking information, and for each of the product data information to be analyzed according to the time interval and a plurality of the second category ranking information, generating ranking curve information to be analyzed;

[0014] Similarity comparison result set information generation module: used to generate similarity comparison result set information according to the ideal ranking curve information and the ranking curve information to be analyzed;

[0015] Target product name information determination module: used to determine the target product name information based on the similarity comparison result set information and the preset comparison result threshold set information.

[0016] In a third aspect, an embodiment of the present application provides a terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method of the first aspect described above when executing the computer program.

[0017] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method of the first aspect described above are implemented.

[0018] It can be understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art.

[0020] Figure 1 It is a flowchart of a cross-border e-commerce product selection method provided by an embodiment of the present application;

[0021] Figure 2 It is a flowchart of step S200 in the cross-border e-commerce product selection method provided in one embodiment of the present application;

[0022] Figure 3 is a schematic diagram of ideal ranking curve information provided by an embodiment of the present application;

[0023] Figure 4 This is a flow chart of the process after step S200 in the cross-border e-commerce product selection method provided in one embodiment of the present application;

[0024] Figure 5 This is a flow chart of the process after step S2092 in the cross-border e-commerce product selection method provided in one embodiment of the present application;

[0025] Figure 6 It is a flowchart of step S300 in the cross-border e-commerce product selection method provided in one embodiment of the present application;

[0026] Figure 7 It is a flowchart of step S700 in the cross-border e-commerce product selection method provided in one embodiment of the present application;

[0027] Figure 8 This is a module block diagram of a cross-border e-commerce product selection system provided by an embodiment of the present application;

[0028] Fig. 9 It is a schematic diagram of a terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0030] In the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and should not be understood as indicating or implying relative importance.

[0031] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0032] In order to illustrate the technical solution described in this application, a specific embodiment is provided below for illustration.

[0033] See also Figure 1 , Figure 1 It is a flow chart of the cross-border e-commerce product selection method based on the dynamic time planning algorithm provided in the embodiment of the present application. In the present embodiment, the executor of the cross-border e-commerce product selection method is a terminal device. It is understandable that the types of terminal devices include but are not limited to mobile phones, tablet computers, laptop computers, ultra-mobile personal computers (Ultra-Mobile Personal Computer, UMPC), netbooks, personal digital assistants (Personal Digital Assistant, PDA), etc., and the embodiment of the present application does not impose any restrictions on the specific types of terminal devices.

[0034] See also Figure 1 The cross-border e-commerce product selection method provided in the embodiment of the present application includes but is not limited to the following steps:

[0035] In S100, excellent commodity data set information and to-be-analyzed commodity data set information are obtained.

[0036] Specifically, the terminal device can first obtain the excellent product data set information and the product data set information to be analyzed; wherein, the excellent product data set information includes excellent product name information and multiple first category ranking information corresponding to the excellent product name information. For example, the terminal device can determine the current popular product that the public likes most as the excellent product name information through the Amazon cross-border e-commerce platform, or determine a certain popular product that the public likes as the excellent product name information; the first category ranking information is used to describe the weekly ranking information of the excellent product name information in the category to which it belongs, and the category to which it belongs is used to describe the major category to which the excellent product name information belongs, such as games, food or clothing; the multiple first category ranking information can be the weekly ranking of the first week of January, the weekly ranking of the second week of January, the weekly ranking of the third week of January, the weekly ranking of the fourth week of January, the weekly ranking of the first week of January, the weekly ranking of the second week of January, the weekly ranking of the third week of January and the weekly ranking of the fourth week of January.

[0037] Without loss of generality, the commodity data set information to be analyzed includes multiple commodity data information to be analyzed and multiple second category ranking information corresponding to each commodity data information to be analyzed. The commodity data information to be analyzed is used to describe whether the commodity to be analyzed is an excellent commodity. The commodity data information to be analyzed may be an innovative commodity, and the category to which the commodity data information to be analyzed belongs is the same as the category to which the excellent commodity name information belongs; the second category ranking information is used to describe the weekly ranking information of the commodity data information to be analyzed in its category.

[0038] In S200, for excellent product name information: ideal ranking curve information is generated according to a preset time interval and multiple first category ranking information, and for each product data information to be analyzed: ranking curve information to be analyzed is generated according to the time interval and multiple second category ranking information.

[0039] Specifically, after the terminal device obtains the excellent product data set information and the product data set information to be analyzed, the terminal device can perform this processing on the excellent product name information: generate ideal ranking curve information based on a preset time interval and multiple first category ranking information, and at the same time perform this processing on each product data information to be analyzed: generate ranking curve information to be analyzed based on the time interval and multiple second category ranking information.

[0040] In some possible implementations, in order to generate effective ideal ranking curve information and ranking curve information to be analyzed, please refer to Figure 2 Step S200 includes but is not limited to the following steps:

[0041] In S210 , for excellent product name information: ideal ranking curve information is generated according to a preset time interval and a plurality of first category ranking information.

[0042] Specifically, the terminal device can perform this processing on the excellent product name information: generate ideal ranking curve information according to the preset time interval and multiple first-category ranking information, wherein, in cross-border e-commerce business, the ranking growth curves corresponding to excellent products in different categories will be different. For example, in a specific category such as games, products with high market acceptance generally show a slow increase in ranking after they are put on the shelves, and then they can continue to maintain a high ranking level. Therefore, the ranking changes of sampled products within half a year of being put on the shelves will be more meaningful, which not only reflects the market's acceptance of new products, but also because the product has been on the shelves for a short time, other merchants have more opportunities to optimize the design of the product and launch upgraded products. Therefore, the time interval can be one week, and the total time length of multiple first-category ranking information can be from the launch of the product to the 24th week. For example, please refer to Figure 3 The ideal ranking curve information is used to describe a curve with the horizontal axis as the time interval and the vertical axis as the first category ranking information.

[0043] In S220, for each commodity data information to be analyzed: generating ranking curve information to be analyzed according to the time interval and the plurality of second category ranking information.

[0044] Specifically, after the terminal device generates the ideal ranking curve information, the terminal device can perform this processing for each commodity data information to be analyzed: generate the ranking curve information to be analyzed based on the time interval and multiple second category ranking information, wherein the ranking curve information to be analyzed is used to describe a curve with the horizontal axis as the time interval and the vertical axis as the second category ranking information.

[0045] In S300 , similarity comparison result set information is generated according to the ideal ranking curve information and the ranking curve information to be analyzed.

[0046] Specifically, after the terminal device generates the ideal ranking curve information and the ranking curve information to be analyzed, the terminal device can accurately generate the similarity comparison result set information according to the ideal ranking curve information and the ranking curve information to be analyzed.

[0047] In some possible implementations, to improve the effectiveness of the ranking curve, see Figure 4 After step S200, the method further includes but is not limited to the following steps:

[0048] In S201 , first ranking mean information is generated according to an average value of a plurality of first category ranking information, and second ranking mean information is generated according to an average value of a plurality of second category ranking information.

[0049] Specifically, after the terminal device generates ideal ranking curve information and ranking curve information to be analyzed, the terminal device can quickly generate first ranking mean information based on the average value of multiple first category ranking information, and quickly generate second ranking mean information based on the average value of multiple second category ranking information.

[0050] In S202, for each first category ranking information: first deviation information is generated according to the difference between the first category ranking information and the first ranking mean information, and for each second category ranking information: second deviation information is generated according to the difference between the second category ranking information and the second ranking mean information.

[0051] Specifically, after the terminal device generates the first ranking mean information and the second ranking mean information, the terminal device can perform this processing for each first category ranking information: effectively generate first deviation information based on the difference between the first category ranking information and the first ranking mean information, and at the same time perform this processing for each second category ranking information: effectively generate second deviation information based on the difference between the second category ranking information and the second ranking mean information.

[0052] In S203, first square value information is generated according to the square value of the first deviation information, and second square value information is generated according to the square value of the second deviation information.

[0053] Specifically, after the terminal device generates the first deviation information and the second deviation information, the terminal device may generate the first square value information according to the square value of the first deviation information, and generate the second square value information according to the square value of the second deviation information.

[0054] In S204, first variance information is generated according to the sum of the first square value information divided by the number of first category ranking information, and second variance information is generated according to the sum of the plurality of second square value information divided by the number of second category ranking information.

[0055] Specifically, after the terminal device generates the first square value information and the second square value information, the terminal device can generate the first variance information according to the sum of the first square value information divided by the number of first category ranking information, and at the same time generate the second variance information according to the sum of multiple second square value information divided by the number of second category ranking information.

[0056] In S205 , the first variance information is compared with preset normal interval information.

[0057] Specifically, after the terminal device generates the first variance information and the second variance information, the terminal device may compare the first variance information with preset normal interval information, wherein the minimum value of the normal interval information is -1.5 and the maximum value of the normal interval information is 1.5.

[0058] In S206 , if the first variance information is outside the normal interval information, the first category ranking information is determined to be the first abnormal value information.

[0059] Without loss of generality, the ranking curve of a product is not a completely smooth curve. After a product is put on the shelf, its ranking will rise rapidly due to advertising promotion, and will also fall rapidly due to short-term shortages, causing a certain local value to deviate seriously from the normal value.

[0060] Specifically, if the first variance information is outside the normal interval information, that is, the first variance information is less than the minimum value of the normal interval information, or the first variance information is greater than the maximum value of the normal interval information, then the terminal device can determine that the first category ranking information is the first outlier information, thereby repairing the outliers in the ranking curve and reducing the adverse effects of outliers on the curve calculation.

[0061] In S207, manual correction value information is obtained.

[0062] Specifically, after the terminal device determines the first abnormal value information, the terminal device may obtain manual correction value information, wherein the manual correction value information is used to describe the manually corrected value.

[0063] In S208, the first abnormal value information is replaced with the manual correction value information to generate the first optimization curve information.

[0064] Specifically, after the terminal device obtains the artificial correction value information, the terminal device may replace the first abnormal value information with the artificial correction value information to generate first optimization curve information, thereby realizing data repair using a quadratic interpolation method.

[0065] In S209 , the second variance information and the normal interval information are compared.

[0066] Specifically, after the terminal device generates the first optimization curve information, the terminal device may compare the second variance information with the normal interval information.

[0067] In S2091, if the second variance information is outside the normal interval information, the second category ranking information is determined to be second abnormal value information.

[0068] Specifically, if the second variance information is outside the normal interval information, that is, the second variance information is less than the minimum value of the normal interval information, or the second variance information is greater than the maximum value of the normal interval information, the terminal device can determine that the second category ranking information is second abnormal value information.

[0069] In S2092, the second abnormal value information is replaced with the manual correction value information to generate the second optimization curve information.

[0070] Specifically, after the terminal device determines the second abnormal value information, the terminal device may replace the second abnormal value information with the manual correction value information to generate the second optimization curve information.

[0071] Accordingly, the above step S300 includes but is not limited to the following steps:

[0072] In S301, similarity comparison result set information is generated according to the first optimization curve information and the second optimization curve information.

[0073] Specifically, after the terminal device generates the second optimization curve information, the terminal device can effectively generate the similarity comparison result set information according to the first optimization curve information and the second optimization curve information.

[0074] In some possible implementations, the product ranking curve after outlier processing using the quadratic interpolation method may still not be smooth enough and may have many jagged fluctuations. Therefore, in order to effectively improve the smoothness of the ranking curve, please refer to Figure 5 If the first optimization curve information and the second optimization curve information are generated, then after step S2092, the method further includes but is not limited to the following steps:

[0075] In S20921, wavelet transform processing is performed on the first optimization curve information to generate third optimization curve information.

[0076] Specifically, the terminal device can perform wavelet transform processing on the first optimization curve information to generate third optimization curve information. For example, the terminal device can first perform discrete wavelet transform processing on the first optimization curve information to decompose the time series data into different frequency components, namely low-frequency approximation coefficients and high-frequency detail coefficients, and then remove certain manually selected detail coefficients, and finally perform wavelet reconstruction based on the remaining approximation coefficients and detail coefficients to obtain a smoother ranking curve.

[0077] In S20922, wavelet transform processing is performed on the second optimization curve information to generate fourth optimization curve information.

[0078] Specifically, after the terminal device generates the third optimization curve information, the terminal device can perform wavelet transform processing on the second optimization curve information to generate fourth optimization curve information, wherein other wavelet transform processing can refer to the relevant description in the above step S20921, so it is not repeated.

[0079] Accordingly, the above step S300 includes but is not limited to the following steps:

[0080] In S302, similarity comparison result set information is generated according to the third optimization curve information and the fourth optimization curve information.

[0081] Specifically, after the terminal device generates the fourth optimization curve information, the terminal device may generate similarity comparison result set information according to the third optimization curve information and the fourth optimization curve information.

[0082] In some possible implementations, in order to facilitate finding the product ranking curve that is most similar to the ideal curve and determining the products that are most likely to become excellent products, please refer to Figure 6 Step S300 includes but is not limited to the following steps:

[0083] In S310 , based on a preset cosine distance calculation formula, cosine similarity information is generated according to the first part of the ideal ranking curve information and the first part of the ranking curve information to be analyzed.

[0084] Without loss of generality, the similarity comparison result set information includes cosine similarity information and DTW distance information.

[0085] Specifically, since the cosine distance can well calculate the similarity between time series of equal length, the terminal device can use the preset cosine distance calculation formula to calculate the cosine distance value between the first part of the ideal ranking curve information and the first part of the ranking curve information to be analyzed, and then determine the cosine similarity information according to the complement of the cosine distance value, wherein the first part of the ideal ranking curve information is used to describe the part from the head end to the specified position in the ideal ranking curve information, and the specified position is used to describe the time position corresponding to the specified first category ranking information. Exemplarily, the specified position can be the eighth week after the product is launched; the first part of the ranking curve information to be analyzed is used to describe the part from the head end to the specified position in the ranking curve information to be analyzed.

[0086] In S320 , based on a preset dynamic time warping algorithm, DTW distance information is generated according to the second part of the ideal ranking curve information and the second part of the ranking curve information to be analyzed.

[0087] Specifically, after the terminal device generates cosine similarity information, the terminal device can generate DTW distance information based on a preset dynamic time warping (DTW) algorithm according to the second part of the ideal ranking curve information and the second part of the ranking curve information to be analyzed, wherein the second part of the ideal ranking curve information is used to describe the remaining part of the ideal ranking curve information except the first part, and the second part of the ranking curve information to be analyzed is used to describe the remaining part of the ranking curve information to be analyzed except the first part.

[0088] Exemplarily, the terminal device may first define a cost matrix, that is, define a cost matrix for the second part of the ideal ranking curve information and the second part of the ranking curve information to be analyzed, respectively, wherein each element represents the distance or cost between corresponding points in the two sequences, and then initialize the matrix, that is, initialize the first row and the first column of the cost matrix to the cumulative cost, representing the cost from the beginning of the sequence to the current point, and then fill the matrix, that is, start from the element in the upper left corner and fill the rest of the cost matrix one by one, and then constrain the conditions, that is, use the Sakoe-Chiba band or Itakura band to limit the range of points that can be accessed when filling the matrix, and then find the best path, that is, start from the upper right corner of the matrix (that is, the end of the two sequences), trace back to the upper left corner (that is, the beginning of the two sequences), and find the path with the minimum cost, which represents the best match between the two sequences, and finally calculate the DTW distance information that can represent the similarity, that is, the lower right corner element of the cost matrix (that is, the minimum cost from the beginning of the sequence to the end of the sequence) is determined as the DTW distance information.

[0089] In S400, target product name information is determined according to similarity comparison result set information and preset comparison result threshold set information.

[0090] Specifically, after the terminal device generates similarity comparison result set information, the terminal device can accurately determine the target product name information based on the similarity comparison result set information and preset comparison result threshold set information, wherein the comparison result threshold set information includes cosine similarity threshold and distance threshold information.

[0091] In some possible implementations, in order to determine the target product name information, please refer to Figure 7 Step S400 includes but is not limited to the following steps:

[0092] In S410 , the cosine similarity information is compared with the cosine similarity threshold, and the DTW distance information is compared with the distance threshold information.

[0093] Specifically, after the terminal device generates similarity comparison result set information, the terminal device may compare the cosine similarity information with the cosine similarity threshold, and simultaneously compare the DTW distance information with the distance threshold information.

[0094] In S420 , if the cosine similarity information is greater than the cosine similarity threshold, and the DTW distance information is less than the distance threshold information, it is determined that the product data information to be analyzed is the target product name information.

[0095] Specifically, if the cosine similarity information is greater than the cosine similarity threshold and the DTW distance information is less than the distance threshold information, the terminal device can determine that the product data information to be analyzed is the target product name information, thereby making it easier for sellers to identify products with potential on the market, facilitate the adoption of corresponding follow-up strategies in product development, and improve the user experience.

[0096] The implementation principle of the cross-border e-commerce product selection method based on the dynamic time planning algorithm in the embodiment of the present application is: the terminal device can first obtain the excellent product data set information and the product data set information to be analyzed, and then perform the processing on the excellent product name information: generate ideal ranking curve information according to the preset time interval and multiple first category ranking information, and perform the processing on each product data information to be analyzed at the same time: generate the ranking curve information to be analyzed according to the time interval and multiple second category ranking information, and then quickly generate similarity comparison result set information according to the ideal ranking curve information and the ranking curve information to be analyzed, and finally accurately determine the target product name information according to the similarity comparison result set information and the preset comparison result threshold set information, so as to quickly and conveniently identify potential products on the market for sellers and effectively improve the user experience.

[0097] It should be noted that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0098] The embodiment of the present application also provides a cross-border e-commerce product selection system based on a dynamic time planning algorithm. For ease of description, only the parts related to the present application are shown, such as Figure 8 As shown, the system 80 includes:

[0099] The commodity data set information acquisition module 81 is used to acquire excellent commodity data set information and to-be-analyzed commodity data set information, wherein the excellent commodity data set information includes excellent commodity name information and a plurality of first category ranking information corresponding to the excellent commodity name information, and the to-be-analyzed commodity data set information includes a plurality of to-be-analyzed commodity data information and a plurality of second category ranking information corresponding to each to-be-analyzed commodity data information, and the category to which the to-be-analyzed commodity data information belongs is the same as the category to which the excellent commodity name information belongs;

[0100] The ranking curve information generating module 82 is used to generate ideal ranking curve information for excellent commodity name information according to a preset time interval and a plurality of first category ranking information, and to generate ranking curve information to be analyzed according to a time interval and a plurality of second category ranking information for each commodity data information to be analyzed;

[0101] Similarity comparison result set information generation module 83: used to generate similarity comparison result set information according to the ideal ranking curve information and the ranking curve information to be analyzed;

[0102] The target product name information determination module 84 is used to determine the target product name information according to the similarity comparison result set information and the preset comparison result threshold set information.

[0103] Optionally, the first category ranking information is used to describe the weekly ranking information of the excellent product name information in the category to which it belongs, and the second category ranking information is used to describe the weekly ranking information of the product data information to be analyzed in the category to which it belongs; the ranking curve information generating module 82 includes:

[0104] The ideal ranking curve information generating submodule is used to generate the ideal ranking curve information for the excellent product name information according to the preset time interval and a plurality of first category ranking information, wherein the ideal ranking curve information is used to describe the curve with the horizontal axis being the time interval and the vertical axis being the first category ranking information;

[0105] The ranking curve information to be analyzed generation submodule is used for generating the ranking curve information to be analyzed for each commodity data information to be analyzed according to the time interval and multiple second category ranking information, wherein the ranking curve information to be analyzed is used to describe a curve with the horizontal axis as the time interval and the vertical axis as the second category ranking information.

[0106] Optionally, the system 80 further includes:

[0107] A ranking mean information generating module: used to generate first ranking mean information according to the average value of a plurality of first category ranking information, and to generate second ranking mean information according to the average value of a plurality of second category ranking information;

[0108] Deviation information generating module: used for generating first deviation information according to the difference between the first category ranking information and the first ranking mean information for each first category ranking information, and generating second deviation information according to the difference between the second category ranking information and the second ranking mean information for each second category ranking information;

[0109] A square value information generating module: used to generate first square value information according to the square value of the first deviation information, and to generate second square value information according to the square value of the second deviation information;

[0110] A variance information generating module: used to generate first variance information according to the sum of the first square value information divided by the number of first category ranking information, and to generate second variance information according to the sum of the plurality of second square value information divided by the number of second category ranking information;

[0111] A first variance information comparison module: used to compare the first variance information with preset normal interval information, wherein the minimum value of the normal interval information is -1.5 and the maximum value of the normal interval information is 1.5;

[0112] A first outlier information determination module: used to determine that the first category ranking information is the first outlier information if the first variance information is outside the normal interval information;

[0113] Manual correction value information acquisition module: used to obtain manual correction value information;

[0114] A first optimization curve information generating module: used to replace the first abnormal value information with the manual correction value information to generate the first optimization curve information;

[0115] Second variance information comparison module: used for comparing the second variance information with the normal interval information;

[0116] A second outlier information determination module: configured to determine that the second category ranking information is the second outlier information if the second variance information is outside the normal interval information;

[0117] A second optimization curve information generating module: used to replace the second abnormal value information with the manual correction value information to generate the second optimization curve information;

[0118] Accordingly, the similarity comparison result set information generating module 83 includes:

[0119] The similarity comparison result set information first generation submodule is used to generate similarity comparison result set information according to the first optimization curve information and the second optimization curve information.

[0120] Optionally, if the first optimization curve information and the second optimization curve information are generated, the system 80 further includes:

[0121] The third optimization curve information generating module is used to perform wavelet transform processing on the first optimization curve information to generate the third optimization curve information;

[0122] The fourth optimization curve information generating module is used to perform wavelet transform processing on the second optimization curve information to generate fourth optimization curve information;

[0123] Accordingly, the similarity comparison result set information generating module 83 includes:

[0124] The second similarity comparison result set information generation submodule is used to generate similarity comparison result set information according to the third optimization curve information and the fourth optimization curve information.

[0125] Optionally, the similarity comparison result set information includes cosine similarity information and DTW distance information; the similarity comparison result set information generating module 83 includes:

[0126] A cosine similarity information generating submodule: used to generate cosine similarity information based on a preset cosine distance calculation formula according to the first part of the ideal ranking curve information and the first part of the ranking curve information to be analyzed, wherein the first part of the ideal ranking curve information is used to describe the part from the head end to the specified position in the ideal ranking curve information, and the first part of the ranking curve information to be analyzed is used to describe the part from the head end to the specified position in the ranking curve information to be analyzed;

[0127] DTW distance information generation submodule: used to generate DTW distance information based on a preset dynamic time warping algorithm, according to the second part of the ideal ranking curve information and the second part of the ranking curve information to be analyzed, wherein the second part of the ideal ranking curve information is used to describe the remaining part of the ideal ranking curve information except the first part, and the second part of the ranking curve information to be analyzed is used to describe the remaining part of the ranking curve information to be analyzed except the first part.

[0128] Optionally, the comparison result threshold set information includes cosine similarity threshold and distance threshold information; the target product name information determination module 84 includes:

[0129] Cosine similarity information comparison submodule: used to compare cosine similarity information and cosine similarity threshold, and to compare DTW distance information and distance threshold information;

[0130] Target product name information determination submodule: used to determine that the product data information to be analyzed is the target product name information if the cosine similarity information is greater than the cosine similarity threshold and the DTW distance information is less than the distance threshold information.

[0131] It should be noted that the information interaction, execution process and other contents between the above-mentioned modules are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0132] The present application also provides a terminal device, such as Fig. 9 As shown, the terminal device 90 of this embodiment includes: a processor 91, a memory 92, and a computer program 93 stored in the memory 92 and executable on the processor 91. When the processor 91 executes the computer program 93, the steps in the above cross-border e-commerce product selection method embodiment are implemented, such as Figure 1 Steps S100 to S400 shown; or, when the processor 91 executes the computer program 93, the functions of each module in the above device are realized, for example Figure 8The functions of modules 81 to 84 are shown.

[0133] The terminal device 90 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server, and the terminal device 90 includes but is not limited to a processor 91 and a memory 92. Those skilled in the art will appreciate that Fig. 9 It is only an example of the terminal device 90 and does not constitute a limitation of the terminal device 90. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal device 90 may also include input and output devices, network access devices, buses, etc.

[0134] Among them, the processor 91 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.; the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0135] The memory 92 may be an internal storage unit of the terminal device 90, such as a hard disk or memory of the terminal device 90, or the memory 92 may be an external storage device of the terminal device 90, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the terminal device 90; further, the memory 92 may also include both an internal storage unit and an external storage device of the terminal device 90, and the memory 92 may also store a computer program 93 and other programs and data required by the terminal device 90, and the memory 92 may also be used to temporarily store data that has been output or is to be output.

[0136] One embodiment of the present application also provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the steps of each of the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc.; the computer-readable medium may include: any entity or device that can carry computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0137] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, all equivalent changes made according to the methods, principles, and structures of the present application should be included in the protection scope of the present application.

Claims

1. A cross-border e-commerce product selection method based on a dynamic time planning algorithm, characterized in that: The method comprises: Acquire excellent product data set information and product data set information to be analyzed, wherein the excellent product data set information includes excellent product name information and a plurality of first category ranking information corresponding to the excellent product name information, and the product data set information to be analyzed includes a plurality of product data information to be analyzed and a plurality of second category ranking information corresponding to each of the product data information to be analyzed, and the category to which the product data information to be analyzed belongs is the same as the category to which the excellent product name information belongs; For the excellent product name information: according to the preset time interval and the plurality of first category ranking information, generate the ideal ranking curve information; and for each of the product data information to be analyzed: according to the time interval and the plurality of second category ranking information, generate the ranking curve information to be analyzed; Generate similarity comparison result set information according to the ideal ranking curve information and the ranking curve information to be analyzed; The target product name information is determined based on the similarity comparison result set information and the preset comparison result threshold set information.

2. The method according to claim 1, characterized in that The first category ranking information is used to describe the weekly ranking information of the excellent product name information in the category to which it belongs, and the second category ranking information is used to describe the weekly ranking information of the product data information to be analyzed in the category to which it belongs; for the excellent product name information: according to a preset time interval and a plurality of the first category ranking information, generating ideal ranking curve information, and for each of the product data information to be analyzed: according to the time interval and a plurality of the second category ranking information, generating the ranking curve information to be analyzed, including: For the excellent product name information: according to a preset time interval and a plurality of the first category ranking information, generate ideal ranking curve information, wherein the ideal ranking curve information is used to describe a curve whose horizontal axis is the time interval and whose vertical axis is the first category ranking information; For each of the commodity data information to be analyzed: generate ranking curve information to be analyzed according to the time interval and multiple second category ranking information, wherein the ranking curve information to be analyzed is used to describe a curve with the horizontal axis being the time interval and the vertical axis being the second category ranking information.

3. The method according to claim 2, characterized in that After generating the ideal ranking curve information according to the preset time interval and the plurality of first category ranking information for the excellent product name information, and generating the ranking curve information to be analyzed according to the time interval and the plurality of second category ranking information for each of the product data information to be analyzed, the method further includes: Generate first ranking mean information according to an average value of a plurality of first category ranking information, and generate second ranking mean information according to an average value of a plurality of second category ranking information; For each piece of the first category ranking information: generate first deviation information according to the difference between the first category ranking information and the first ranking mean information, and for each piece of the second category ranking information: generate second deviation information according to the difference between the second category ranking information and the second ranking mean information; generating first square value information according to the square value of the first deviation information, and generating second square value information according to the square value of the second deviation information; Generating first variance information according to the sum of the first square value information divided by the number of the first category ranking information, and generating second variance information according to the sum of the plurality of second square value information divided by the number of the second category ranking information; Comparing the first variance information with preset normal interval information, wherein a minimum value of the normal interval information is -1.5, and a maximum value of the normal interval information is 1.5; If the first variance information is outside the normal interval information, determining that the first category ranking information is first abnormal value information; Obtaining manual correction value information; Replacing the first abnormal value information with the manual correction value information to generate first optimization curve information; comparing the second variance information with the normal interval information; If the second variance information is outside the normal interval information, determining that the second category ranking information is second abnormal value information; Replacing the second abnormal value information with the manual correction value information to generate second optimization curve information; Accordingly, generating similarity comparison result set information according to the ideal ranking curve information and the ranking curve information to be analyzed includes: Generate similarity comparison result set information based on the first optimization curve information and the second optimization curve information.

4. The method according to claim 3, characterized in that If the first optimization curve information and the second optimization curve information are generated, then after replacing the second abnormal value information with the manual correction value information to generate the second optimization curve information, the method further includes: Performing wavelet transform processing on the first optimization curve information to generate third optimization curve information; Performing wavelet transform processing on the second optimization curve information to generate fourth optimization curve information; Accordingly, generating similarity comparison result set information according to the ideal ranking curve information and the ranking curve information to be analyzed includes: Generate similarity comparison result set information based on the third optimization curve information and the fourth optimization curve information.

5. The method according to claim 3, characterized in that: The similarity comparison result set information includes cosine similarity information and DTW distance information; the similarity comparison result set information is generated according to the ideal ranking curve information and the ranking curve information to be analyzed, including: Based on a preset cosine distance calculation formula, the cosine similarity information is generated according to the first part of the ideal ranking curve information and the first part of the ranking curve information to be analyzed, wherein the first part of the ideal ranking curve information is used to describe the part from the head end to the specified position in the ideal ranking curve information, and the first part of the ranking curve information to be analyzed is used to describe the part from the head end to the specified position in the ranking curve information to be analyzed; Based on a preset dynamic time warping algorithm, the DTW distance information is generated according to the second part of the ideal ranking curve information and the second part of the ranking curve information to be analyzed, wherein the second part of the ideal ranking curve information is used to describe the remaining part of the ideal ranking curve information except the first part, and the second part of the ranking curve information to be analyzed is used to describe the remaining part of the ranking curve information to be analyzed except the first part.

6. The method according to claim 5, characterized in that The comparison result threshold set information includes cosine similarity threshold and distance threshold information; Determining the target product name information according to the similarity comparison result set information and the preset comparison result threshold set information includes: Comparing the cosine similarity information with the cosine similarity threshold, and comparing the DTW distance information with the distance threshold information; If the cosine similarity information is greater than the cosine similarity threshold, and the DTW distance information is less than the distance threshold information, it is determined that the commodity data information to be analyzed is target commodity name information.

7. A cross-border e-commerce product selection system based on a dynamic time planning algorithm, characterized in that: The system comprises: A commodity data set information acquisition module: used to acquire excellent commodity data set information and commodity data set information to be analyzed, wherein the excellent commodity data set information includes excellent commodity name information and a plurality of first category ranking information corresponding to the excellent commodity name information, and the commodity data set information to be analyzed includes a plurality of commodity data information to be analyzed and a plurality of second category ranking information corresponding to each of the commodity data information to be analyzed, and the category to which the commodity data information to be analyzed belongs is the same as the category to which the excellent commodity name information belongs; A ranking curve information generating module: used for generating ideal ranking curve information for the excellent product name information according to a preset time interval and a plurality of the first category ranking information, and for each of the product data information to be analyzed according to the time interval and a plurality of the second category ranking information, generating ranking curve information to be analyzed; Similarity comparison result set information generation module: used to generate similarity comparison result set information according to the ideal ranking curve information and the ranking curve information to be analyzed; Target product name information determination module: used to determine the target product name information based on the similarity comparison result set information and the preset comparison result threshold set information.

8. The system according to claim 7, characterized in that The first category ranking information is used to describe the weekly ranking information of the excellent product name information in the category to which it belongs, and the second category ranking information is used to describe the weekly ranking information of the product data information to be analyzed in the category to which it belongs; The ranking curve information generating module comprises: An ideal ranking curve information generating submodule is used to generate ideal ranking curve information for the excellent product name information according to a preset time interval and a plurality of first category ranking information, wherein the ideal ranking curve information is used to describe a curve whose horizontal axis is the time interval and whose vertical axis is the first category ranking information; A submodule for generating ranking curve information to be analyzed: for each of the commodity data information to be analyzed: generating ranking curve information to be analyzed according to the time interval and multiple second category ranking information, wherein the ranking curve information to be analyzed is used to describe a curve with the horizontal axis being the time interval and the vertical axis being the second category ranking information.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images