International trade business information analysis method and system

Abstract

The invention is suitable for the technical field of international trade, and particularly relates to an international trade business information analysis method and system, and the method comprises the steps: obtaining business data from a database; determining a first commodity feature set and a first market feature set based on the business data; determining a target commodity and a target market of the target enterprise based on the first commodity feature set and the first market feature set; determining target business data based on the target commodity and the target market; determining evaluation dimensions and feature data corresponding to each evaluation dimension based on the target business data; and obtaining an evaluation dimension score and a comprehensive competitiveness index of the target enterprise according to the evaluation dimension and the feature data. According to the international trade business information analysis method provided by the embodiment of the invention, the problems that the future trade trend of an enterprise is difficult to predict and the competitiveness of the enterprise is difficult to reflect in time can be solved.

Description

Technical Field

[0001] The present application belongs to the field of international trade technology, and in particular, to an international trade business information analysis method and system. Background Art

[0002] International trade refers to the transaction of goods and services across national borders, generally consisting of import trade and export trade. It can regulate the utilization rate of domestic production factors, improve international supply and demand relations, adjust economic structure, increase fiscal revenue, etc.

[0003] In the existing technology, the analysis of international trade is limited to analyzing the current market and commodity data, and lacks the ability to predict the future trade trends of enterprises. Most of the competitiveness assessments in the existing technology are based on historical data, which makes it difficult to reflect the latest competitive situation of enterprises in a timely manner. Therefore, the existing technology has obvious deficiencies in predicting the future trade trends of enterprises and evaluating their competitiveness. Summary of the invention

[0004] The embodiments of the present application provide a method and system for analyzing international trade business information, which can solve the problem that it is difficult to predict the future trade trend of an enterprise and difficult to reflect the competitiveness of an enterprise in a timely manner.

[0005] In a first aspect, an embodiment of the present application provides an international trade business information analysis method, comprising: Acquire business data from a database; wherein the database includes commodity data tables, customer data tables, sales data tables, and market data tables corresponding to a plurality of enterprises engaging in international trade, and the business data is data in the commodity data tables, customer data tables, sales data tables, and market data tables of the database; Determine a first commodity feature set and a first market feature set based on the business data; wherein the first commodity feature set includes commodity features of multiple commodities of the target enterprise, and the first market feature set includes multiple market features corresponding to the commodity features of the first commodity feature set, the commodity features include performance parameters and customer types of the commodities, and the market features are market shares of the commodities corresponding to the commodity features; Determining the target commodity and target market of the target enterprise based on the first commodity feature set and the first market feature set; wherein the target commodity is the commodity that the target enterprise is most likely to import or export in the future, and the target market is the market demand for the target commodity; Determining target business data based on the target commodity and the target market; wherein the target business data is sales data, market data and customer data of the target commodity in future international trade; Determine an evaluation dimension and characteristic data corresponding to each evaluation dimension based on the target business data; wherein the evaluation dimension is a key indicator for classifying, measuring or evaluating the target business data, and the characteristic data is used to reflect the characteristics of the corresponding evaluation dimension; The evaluation dimension score and the comprehensive competitiveness index of the target enterprise are obtained according to the evaluation dimension and the characteristic data.

[0006] The above technical solutions in the embodiments of the present application have at least the following technical effects: The international trade business information analysis method provided in the embodiment of the present application can comprehensively and accurately depict the international trade business profile of the target enterprise by acquiring business data, determining the first commodity feature set and the first market feature set; determining the target commodity and target market of the target enterprise based on the first commodity feature set and the first market feature set, thereby focusing on various commodities and their market demands that the target enterprise may import and export in the future; determining the target business data based on the target commodity and the target market, quantifying the key business information of the target commodity in future international trade, and providing data support for subsequent evaluation; determining the evaluation dimension and the feature data under each evaluation dimension based on the target business data; obtaining the evaluation dimension score and the comprehensive competitiveness index of the target enterprise according to the evaluation dimension and the feature data. Therefore, the international trade business information analysis method provided in the embodiment of the present application realizes the accurate prediction of future trade trends and the timely reflection of the competitiveness of the target enterprise, and provides powerful decision-making support for the target enterprise.

[0007] In a second aspect, an embodiment of the present application provides an international trade business information analysis system, including: An acquisition module, used to acquire business data from a database; wherein the database includes commodity data tables, customer data tables, sales data tables, and market data tables corresponding to a plurality of enterprises engaged in international trade, and the business data is data in the commodity data tables, customer data tables, sales data tables, and market data tables of the database; a feature module, configured to determine a first commodity feature set and a first market feature set based on the business data; wherein the first commodity feature set includes commodity features of a plurality of commodities of a target enterprise, and the first market feature set includes a plurality of market features corresponding to the commodity features of the first commodity feature set, the commodity features include performance parameters and customer types of the commodities, and the market features are market shares of the commodities corresponding to the commodity features; A first target module, used to determine the target commodity and target market of the target enterprise based on the first commodity feature set and the first market feature set; wherein the target commodity is the commodity that the target enterprise is most likely to import or export in the future, and the target market is the market demand for the target commodity; A second target module, used to determine target business data based on the target commodity and the target market; wherein the target business data is sales data, market data and customer data of the target commodity in future international trade; An evaluation module, used to determine evaluation dimensions and characteristic data corresponding to each evaluation dimension based on the target business data; wherein the evaluation dimension is a key indicator for classifying, measuring or evaluating the target business data, and the characteristic data is used to reflect the characteristics of the corresponding evaluation dimension; The target enterprise module is used to obtain the evaluation dimension score and comprehensive competitiveness index of the target enterprise according to the evaluation dimension and the characteristic data.

[0008] In a third aspect, an embodiment of the present application provides an international trade business information analysis device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements a method as described in any one of the above-mentioned first aspects when executing the computer program.

[0009] 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 method described in any one of the first aspects above is implemented.

[0010] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product runs on an international trade business information analysis device, the international trade business information analysis device executes the international trade business information analysis method described in any one of the first aspects above.

[0011] It can be understood that the beneficial effects of the second to fifth 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

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0013] Figure 1 It is a flowchart of an international trade business information analysis method provided by an embodiment of the present application; Figure 2 It is a schematic diagram of the implementation process of the international trade business information analysis method provided in one embodiment of the present application; Figure 3It is a schematic diagram of the implementation process of step S300 in the international trade business information analysis method provided in one embodiment of the present application; Figure 4 It is a schematic diagram of the implementation process of step S320 in the international trade business information analysis method provided in one embodiment of the present application; Figure 5 It is a schematic diagram of the implementation process of step S500 in the international trade business information analysis method provided in one embodiment of the present application; Figure 6 It is a schematic diagram of the implementation process of step S600 in the international trade business information analysis method provided in one embodiment of the present application; Figure 7 It is a schematic diagram of the implementation process of step S640 in the international trade business information analysis method provided in one embodiment of the present application; Figure 8 It is a structural diagram of the international trade business information analysis system provided by the embodiment of the present application; Fig. 9 It is a structural schematic diagram of the international trade business information analysis device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0014] 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.

[0015] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0016] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0017] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0018] In addition, 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 cannot be understood as indicating or implying relative importance.

[0019] 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.

[0020] In the related technologies, the analysis of international trade is limited to analyzing the current market and commodity data, and lacks the ability to predict the future trade trends of enterprises. Most of the competitiveness assessments in the existing technologies are based on historical data, which makes it difficult to reflect the latest competitive situation of enterprises in a timely manner. Therefore, the existing technologies have obvious deficiencies in predicting the future trade trends of enterprises and evaluating their competitiveness.

[0021] To solve the above problems, the embodiment of the present application provides an international trade business information analysis method and system. In this method, by obtaining business data, determining the first commodity feature set and the first market feature set, the international trade business profile of the target enterprise can be comprehensively and accurately depicted; based on the first commodity feature set and the first market feature set, the target commodity and target market of the target enterprise are determined, so as to focus on the various commodities and their market demands that the target enterprise may import and export in the future; based on the target commodity and the target market, the target business data is determined, and the key business information of the target commodity in future international trade is quantified, providing data support for subsequent evaluation; based on the target business data, the evaluation dimension and the feature data under each evaluation dimension are determined; according to the evaluation dimension and the feature data, the evaluation dimension score and the comprehensive competitiveness index of the target enterprise are obtained. Therefore, the international trade business information analysis method provided by the embodiment of the present application realizes the accurate prediction of future trade trends and the timely reflection of the competitiveness of the target enterprise, and provides strong decision-making support for the target enterprise.

[0022] The international trade business information analysis method provided in the embodiment of the present application can be applied to an international trade business information analysis device. In this case, the international trade business information analysis device is the executor of the international trade business information analysis method provided in the embodiment of the present application. The embodiment of the present application does not impose any restrictions on the specific type of the international trade business information analysis device.

[0023] For example, the international trade business information analysis device can be a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a mobile phone, a tablet computer, a wearable device, a vehicle-mounted device, an augmented reality (AR) / virtual reality (VR) device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), a desktop computer, a smart screen, a smart TV, a handheld device with wireless communication function, a computing device or other processing device connected to a wireless modem, a vehicle-mounted device, a vehicle networking terminal, a computer, a laptop computer, a handheld communication device, a handheld computing device, a satellite wireless device, etc., but not limited to these.

[0024] In order to better understand the international trade business information analysis method provided in the embodiment of the present application, the specific implementation process of the international trade business information analysis method provided in the embodiment of the present application is exemplarily introduced below.

[0025] Figure 1A schematic flow chart of an international trade business information analysis method provided in an embodiment of the present application is shown. The international trade business information analysis method includes: S100, obtaining business data from a database, wherein the database includes commodity data tables, customer data tables, sales data tables, and market data tables corresponding to multiple enterprises engaged in international trade, and the business data is data in the commodity data tables, customer data tables, sales data tables, and market data tables of the database.

[0026] Exemplarily, data in commodity data tables, customer data tables, sales data tables, and market data tables corresponding to multiple enterprises engaged in international trade can be exported from the database. For example, the commodity data table includes commodity number, commodity name, price, inventory, commodity category, material, size, function, and enterprise number, etc.; the customer data table includes customer number, customer name, commodity number, transaction date (transaction includes purchase and return), transaction quantity, transaction amount, age, gender, and region, etc.; the sales data table includes sales number, sales date, customer number, commodity number, enterprise number, sales quantity, sales unit price, sales cost, and average annual profit, etc.; the market data table includes market number, commodity category, market size (i.e., the average annual sales amount of each category of commodities) and market capacity (i.e., the annual sales amount of each category of commodities), etc.

[0027] S200, determining a first product feature set and a first market feature set based on the business data, wherein the first product feature set includes product features of multiple products of the target enterprise, the first market feature set includes multiple market features corresponding to the product features of the first product feature set, the product features include product performance parameters and customer types, and the market features are market shares of the products corresponding to the product features.

[0028] For example, the product data of the target enterprise may be screened out, and then key product features, i.e., performance parameters (e.g., material, size, function, etc.) and customer types (e.g., age composition, gender ratio, region, etc.) may be extracted therefrom. The corresponding market features, i.e., market share, are obtained based on the product features of the target enterprise's multiple products and the corresponding market features. The first product feature set and the first market feature set are determined based on the product features of the target enterprise's multiple products and the corresponding market features. For example, the first product feature set is shown in Table 1, and the first market feature set is shown in Table 2.

[0029] Table 1 Table 2 In one possible implementation, see Figure 2 S200, determining a first commodity feature set and a first market feature set based on the business data, including: S210, determining a target enterprise in the business data.

[0030] It can be understood that determining the target enterprise in the business data is to select a target enterprise from multiple enterprises engaged in international trade as an analysis object.

[0031] For example, screening can be performed based on conditions such as company name, industry classification, market position, etc. to determine the target company.

[0032] S220, extracting commodity data of the target enterprise from the business data, wherein the commodity data includes commodity information, sales information and customer information of at least one commodity of the target enterprise.

[0033] It can be understood that extracting the target enterprise's product data from the business data includes: Extracting product information of each product of the target enterprise from the product data table corresponding to the target enterprise, for example, the product information includes the product number, material, size, function and enterprise number of each product of the target enterprise; Extracting sales information of each commodity of the target enterprise from the sales data table corresponding to the target enterprise, for example, the sales information includes the average annual profit of each commodity of the target enterprise, etc.; The customer information of each product of the target enterprise is extracted from the customer data table corresponding to the target enterprise. For example, the customer information includes the age, gender and region of the customers of each product of the target enterprise.

[0034] S230, extracting market data of the target enterprise from the business data, wherein the market data includes the market size of at least one commodity of the target enterprise.

[0035] Exemplarily, the market size of each commodity of the target enterprise may be extracted from the market data table according to the commodity category of each commodity of the target enterprise in the business data.

[0036] S240: Determine a first product feature set based on the product data.

[0037] It can be understood that determining the first commodity feature set based on commodity data is to extract commodity features of each commodity of the target enterprise based on the commodity data, thereby determining the first commodity feature set.

[0038] Exemplarily, the product features of each product of the target enterprise may be extracted from the product data to form a first product feature set.

[0039] S250: Determine a first market feature set based on the market data and the product data.

[0040] For example, the market share of each commodity of the target enterprise may be determined based on the market data and commodity data to form the first market feature set. For example, the market data includes the market size of at least one commodity of the target enterprise, and the sales information in the commodity data includes the average annual profit of each commodity of the target enterprise. Then, the market share of each commodity of the target enterprise = the average annual profit of each commodity / the average annual sales of all commodities in the same category as the commodity (i.e., the market size).

[0041] Through the above steps S210 to S250, the target enterprise is first determined, and the commodity data and market data of the target enterprise are extracted from the business data. Then, the first commodity feature set is determined based on the commodity data, and the first market feature set is determined in combination with the market data and the commodity data. The commodity data and market data are integrated to conduct a comprehensive and systematic analysis of the commodity characteristics and market characteristics of the target enterprise. The key commodity characteristics and market characteristics are extracted, providing strong data support for the international trade information analysis of the target enterprise.

[0042] S300, determining the target commodity and target market of the target enterprise based on the first commodity feature set and the first market feature set, wherein the target commodity is the commodity that the target enterprise is most likely to import or export in the future, and the target market is the market demand for the target commodity.

[0043] Exemplarily, the similarity between the target enterprise's products and the products of enterprises other than the target enterprise can be determined based on the first product feature set and the first market feature set, and each product of the enterprise other than the target enterprise corresponding to the maximum similarity is used as a candidate target product. The product with the highest profit potential among the candidate target products is selected as the target product, and the target market is determined based on the market characteristics of the target product.

[0044] In one possible implementation, see Figure 3 S300, determining a target product and a target market of a target enterprise based on a first product feature set and a first market feature set, including: S310, extracting features from the business data to obtain a second product feature set and a second market feature set, wherein the second product feature set includes product features of multiple products of multiple different enterprises, and the second market feature set includes multiple market features corresponding to the product features of the second product feature set, and the different enterprises are enterprises different from the target enterprise.

[0045] It can be understood that feature extraction is performed on business data to obtain the second product feature set and the second market feature set, which is to extract product features and corresponding market features of multiple products of multiple different enterprises in the business data. For example, the second product feature set is shown in Table 3, and the second market feature set is shown in Table 4.

[0046] Table 3 Table 4 S320: Obtain, according to the second product feature set, a similarity between each product feature in the first product feature set and each product feature in the second product feature set.

[0047] Exemplarily, a similarity calculation method such as cosine similarity and Euclidean distance may be used to calculate the similarity between each product feature in the first product feature set and each product feature in the second product feature set.

[0048] Optionally, see Figure 4 S320, obtaining the similarity between each product feature of the first product feature set and each product feature of the second product feature set according to the second product feature set, including: S321, vectorize each product feature in the first product feature set to obtain a corresponding first feature vector.

[0049] It can be understood that vectorization processing is to convert product features into a vector form that can perform mathematical operations.

[0050] Exemplarily, word embedding technology (such as Word2Vec, BERT, etc.) or feature engineering methods (such as one-hot encoding, TF-IDF, etc.) can be used to convert the product features into the corresponding first feature vector. For example, the first product feature set is shown in Table 5, then the first feature vector of product 001 is: [1, 10, 5, 20, 1, 25, 40, 0.55, 1] ​​(metal = 1, size = 10, 5, 20, cutting = 1, age composition = 25, 40, gender ratio = 0.55, region: China = 1), and the first feature vector of product 002 is: [2, 15, 15, 20, 2, 18, 30, 0.48, 0] (plastic = 2, size = 15, 15, 20, storage = 2, age composition = 18, 30, gender ratio = 0.48, region: global = 0).

[0051] Table 5 S322, vectorize each product feature in the second product feature set to obtain a corresponding second feature vector.

[0052] Exemplarily, a word embedding technology (such as Word2Vec, BERT, etc.) or a feature engineering method (such as one-hot encoding, TF-IDF, etc.) can be used to convert the product features into the corresponding second feature vector. For example, the second product feature set is shown in Table 6, then the second feature vector of product P001 is: [2, 10, 5, 20, 2, 20, 30, 0.55, 1] ​​(plastic = 2, size = 10, 5, 20, storage = 2, age composition = 20, 30, gender ratio = 0.55, region: China = 1), the second feature vector of product P002 is: [1, 10, 5, 20, 2, 30, 40, 0.48, 2] (metal = 1, size = 10, 5, 20, storage = 2, age composition = 30, 40, gender ratio = 0.48, region: United States = 2), and the second feature vector of product P003 is: [3, 80, 60, 0, 3, 40, 50, 0.45, 3] (wood = 3, size = 80, 60, 0, decoration = 3, age composition = 40, 50, gender ratio = 0.45, region: United Kingdom = 3).

[0053] Table 6 S323, calculating a similarity value between each first eigenvector and each second eigenvector.

[0054] Exemplarily, the similarity value between each first eigenvector and each second eigenvector in all second eigenvectors can be calculated based on the cosine similarity to obtain multiple similarity values. , where A is the first eigenvector, ‖A‖ is the magnitude of the first eigenvector, B is the second eigenvector, and ‖B‖ is the magnitude of the second eigenvector.

[0055] S324: Determine the similarity value as the similarity between each product feature in the first product feature set and each product feature in the second product feature set.

[0056] It can be understood that the similarity value between each feature vector of the first feature vector set and each feature vector of the second feature vector set is the similarity between each product feature of the first product feature set and each product feature of the second product feature set.

[0057] Through the above steps S321 to S324, the product features are converted from the original non-numerical form to the feature vector in numerical form, which is conducive to the comparison and calculation of product features in different formats on the same dimension. By calculating the similarity value between each feature vector in the first feature vector set and each feature vector in the second feature vector set, a quantitative evaluation of the similarity between the product features is achieved. The determination of similarity is conducive to identifying products with similar features or attributes.

[0058] S330: Determine the maximum similarity between each product feature in the first product feature set and each product feature in the second product feature set according to each similarity.

[0059] Exemplarily, after obtaining the similarity value between each first feature vector and each second feature vector based on the cosine similarity calculation, the similarity values ​​of the first feature vector corresponding to each product feature of the first product feature set and the second feature vectors corresponding to all product features of the second product feature set are compared, and it is determined that each product feature of the first product feature set has a product feature of the second product feature set that is most similar (i.e., has the largest similarity value), and multiple maximum similarities (i.e., the largest similarity values) are obtained.

[0060] S340: taking the products of different companies corresponding to the maximum similarities as candidate target products.

[0061] It can be understood that the products of different enterprises corresponding to the respective maximum similarities are taken as candidates for the target product.

[0062] S350, evaluating the revenue of the candidate target commodities, and selecting the commodity with the highest revenue potential as the target commodity.

[0063] Exemplarily, the average annual profit, market size (i.e., the average annual sales of all commodities in the category to which the candidate target commodity belongs) and market capacity (i.e., the total annual sales of all commodities in the category to which the candidate target commodity belongs) of the candidate target commodity in the business data can be extracted, and the market share of each candidate target commodity can be obtained based on the average annual profit and market size (market share = average annual profit / corresponding market size). The revenue of the candidate target commodity is evaluated in combination with the market share and market capacity, and the candidate target commodity with a low market share but a clear growth trend in market capacity is selected as the commodity with the highest revenue potential, i.e., the target commodity. For example, a threshold value (such as 5%) is set. If the market share of the candidate target commodity does not exceed the corresponding threshold value, it is determined that the market share of the candidate target commodity is low; a trend line is obtained by fitting the change of the market capacity of the region corresponding to the market share of the candidate target commodity less than the threshold value over time using methods such as linear regression, polynomial regression or exponential regression, and the candidate target commodity with the highest trend line slope among the candidate target commodities with an upward trend is selected as the target commodity.

[0064] S360, determining a target market based on product characteristics and market characteristics of the target product.

[0065] It can be understood that the target market includes the regions and market shares where the target enterprise will sell the target products in the future.

[0066] For example, the similarity between the customer types of target products of different enterprises and the customer types of target enterprises may be determined based on the product features of the target product in the second product feature set and the market features of the target product in the second market feature set (for example, the customer types of target products of different enterprises and the customer types of target enterprises are vectorized to obtain corresponding feature vectors, , where A is the feature vector of different enterprises, ‖A‖ is the modulus of the feature vector of different enterprises, B is the feature vector of the target enterprise, and ‖B‖ is the modulus of the feature vector of the target enterprise), determine a different enterprise corresponding to the maximum similarity between the customer type of the target goods of different enterprises and the customer type of the target enterprise, and determine the target market based on the customer type and market share of the different enterprise (for example, the target market is the region and 30% of the market share of the customer type of the different enterprise).

[0067] Through the above steps S310 to S360, by extracting features, calculating similarities, screening candidate target products, and evaluating products with the highest profit potential, the target products and target markets are determined, and in-depth mining and analysis of business data are achieved, which is conducive to providing decision support for target enterprises and improving the market competitiveness of target enterprises.

[0068] S400, determining target business data based on the target commodity and the target market, wherein the target business data is sales data, market data and customer data of the target commodity in future international trade.

[0069] It can be understood that sales data includes sales quantity, inventory, unit sales price and average annual profit, etc.; market data includes market size (i.e. the average annual sales of all commodities in the category to which the target commodity belongs) and market capacity (i.e. the annual sales of all commodities in the category to which the target commodity belongs), etc.; customer data includes transaction date (transactions include purchases and returns), transaction quantity and transaction amount, etc.

[0070] Exemplarily, a prediction model may be constructed using a machine learning algorithm (eg, linear regression, random forest, etc.), and target business data may be obtained based on target commodities and target markets.

[0071] In one possible implementation, see Figure 2 S400, determining target business data based on target goods and target markets, including: S410, determining competing enterprises based on the target product and the target market.

[0072] For example, it may be possible to determine, based on the target commodity, that different enterprises whose products are the same as the target commodity are competing enterprises, or to obtain product features based on the target commodity and, based on the product features of the target commodity and the target market, determine that there are different enterprises whose functions are consistent with those of the target commodity and whose regions of sale are the same as those of sale of the target commodity are competing enterprises.

[0073] S420, determining competitor enterprise data based on the competitor enterprise and the business data, wherein the competitor enterprise data is data in the customer data table, sales data table, and market data table of the target product of the competitor enterprise in the database.

[0074] For example, data of the competitor's target product in the customer data table, sales data table, and market data table may be extracted from the business data according to the competitor.

[0075] S430, constructing a prediction model based on the business data.

[0076] Exemplarily, it can be to clean business data (identify and delete duplicate data, process missing values, correct outliers, and unify data formats); select features (products, the market and competing enterprise data corresponding to the product) according to the prediction target (future sales data, market data, and customer data); divide the processed business data into training sets and test sets (for example, 70% training set, 30% test set), and ensure that the training set and the test set are continuous in time; use machine learning algorithms (such as linear regression, random forest, etc.) to build a model, using the selected features as input and future sales data, market data, and customer data as output; use the training set to train the model, and iteratively optimize the algorithm parameters to minimize the model's prediction error; use the test set to verify the trained model and evaluate the model's performance (for example, K-fold cross validation), and based on the verification results, adjust the model parameters or try different model structures to improve the model performance and obtain a prediction model.

[0077] S440, inputting the target product, target market and competing enterprise data into the prediction model to obtain target business data.

[0078] For example, the target product, target market and competitor data may be input into a prediction model to obtain future sales data, market data and customer data of the target product.

[0079] Through the above steps S410 to S440, by identifying competing enterprises, obtaining competing enterprise data, building a prediction model and outputting prediction results, a more comprehensive and in-depth market insight is provided to the target enterprise, which helps the target enterprise to better grasp market opportunities and respond to market challenges.

[0080] S500, determining evaluation dimensions and feature data corresponding to each evaluation dimension based on target business data, wherein the evaluation dimension is a key indicator for classifying, measuring or evaluating the target business data, and the feature data is used to reflect the characteristics of the corresponding evaluation dimension.

[0081] Exemplarily, the evaluation dimensions and the characteristic data of each evaluation enterprise corresponding to each evaluation dimension may be determined based on the target business data. For example, the evaluation dimensions and the characteristic data are shown in Table 7, and the characteristic data is the data under the evaluation dimensions in Table 7.

[0082] Table 7 In a possible implementation, refer to 4, S500, determining the evaluation dimension and the feature data corresponding to each evaluation dimension based on the target business data, including: S510: Determine the correlation coefficients between multiple variables in the target business data based on the target business data, wherein the variables refer to data items of different aspects or attributes in the target business data.

[0083] Exemplarily, a selected correlation coefficient calculation method (such as Pearson correlation coefficient, Spearman correlation coefficient, etc.) can be used to calculate the correlation coefficients between multiple variables in the target business data. For example, the Pearson correlation coefficient is: , substituting the two sets of data, sales (RMB 10,000 / year): 1500, 1650, 1800 and cost (RMB 10,000 / year): 600, 650, 700, into the formula, we get a correlation coefficient of about 0.99 (almost completely positive correlation), where n is the sample size, x is i is the profit, y i is the cost, and represent the sample means of profit and cost respectively.

[0084] S520, determining multiple target sets based on correlation coefficients between variables, wherein the target set includes multiple highly correlated variables.

[0085] For example, a correlation coefficient threshold can be set to determine which variables are highly correlated. For example, the correlation coefficient threshold is 0.7. The variables in the variable pairs whose correlation coefficients are greater than or equal to the correlation coefficient threshold are highly correlated, and each variable and all variables highly correlated with the variable are grouped together, and each group is a target set.

[0086] S530: Determine evaluation dimensions based on each target set.

[0087] For example, regression analysis, correlation analysis, or principal components analysis can be used to determine whether the target sets are suitable for merging into one evaluation dimension to determine the final evaluation dimension. For example, one of the target sets (including product return rate) is used as the dependent variable, one target set (including inventory turnover rate) and another target set (including sales and cost) are used as independent variables, and regression analysis is performed to check the fit of the regression model, including the R² value (coefficient of determination) and the significance level of the regression coefficient. If the R² values ​​are low and the regression coefficients are not significant, it indicates that the linear relationship between the target sets is weak and is not suitable for merging. The evaluation dimension can be determined separately according to each target set (for example, the evaluation dimensions are named market performance, product quality, and operational efficiency respectively through natural language processing (NLP) technology).

[0088] S540, extracting characteristic data of each evaluated enterprise corresponding to each evaluation dimension from the target business data, wherein the evaluated enterprises include the target enterprise and the competing enterprises.

[0089] Exemplarily, SQL query or Python's pandas library may be used to extract feature data from target business data, and the feature data of each evaluated enterprise directly related to each evaluation dimension may be determined based on natural language processing (NLP) technology.

[0090] Through the above steps S510 to S540, by analyzing the correlation coefficients between multiple variables in the target business data, multiple highly correlated variable sets (i.e., target sets) are determined, and the dimension of each target set is reduced or screened, and the evaluation dimensions corresponding to each target set are determined, which further simplifies the data structure and improves the analysis efficiency. The characteristic data of each evaluated enterprise (including the target enterprise and the competing enterprise) corresponding to each evaluation dimension is extracted from the target business data, which provides important data support for the subsequent analysis of the evaluation dimension scores and the comprehensive competitiveness index of the target enterprise.

[0091] S600, obtain the evaluation dimension score and comprehensive competitiveness index of the target enterprise based on the evaluation dimension and characteristic data.

[0092] Exemplarily, the weights corresponding to the evaluation dimensions and the feature data may be determined based on the evaluation dimensions and the feature data to obtain the evaluation dimension scores and the comprehensive competitiveness index of the target enterprise.

[0093] In one possible implementation, see Figure 6 , S600, obtains the evaluation dimension score and comprehensive competitiveness index of the target enterprise based on the evaluation dimension and characteristic data, including: S610, calculating the correlation coefficient of each feature data pair to obtain a first correlation coefficient matrix, wherein the feature data pair is each two feature data in each feature data of different evaluation dimensions corresponding to each evaluated enterprise.

[0094] For example, a selected correlation coefficient calculation method (such as Pearson correlation coefficient, Spearman correlation coefficient, etc.) can be used to calculate the correlation coefficient of each pair of characteristic data of different evaluation dimensions corresponding to each evaluated enterprise. For example, the characteristic data of an evaluated enterprise is shown in Table 8, and the correlation coefficient (r 12 ), the correlation coefficient between profit and inventory turnover rate (r 13 ) and the correlation coefficient between product return rate and inventory turnover rate (r 23 ), then the first correlation coefficient matrix is: .

[0095] Table 8 S620: If each correlation coefficient in the first correlation coefficient matrix is ​​less than a preset threshold, it is determined that each characteristic data of each evaluated enterprise maintains relative independence, and the characteristic data is determined as independent characteristic data.

[0096] It can be understood that the preset threshold is that each correlation coefficient in the first correlation coefficient matrix does not exceed a preset specified value. The preset specified value can be set by ordinary technicians in this field according to actual needs and is not limited here.

[0097] For example, a reasonable preset threshold can be determined based on historical data and industry standards. For example, the preset threshold is 0.5. If there is no feature data pair with an absolute value of a correlation coefficient greater than 0.5, it is determined that each feature data of each evaluated enterprise is relatively independent. The feature data is determined as independent feature data.

[0098] S630, calculating the standard deviation and mean of each independent feature data.

[0099] Exemplarily, the standard deviation and mean of each independent feature data are calculated. For example, the evaluation dimensions and independent feature data are shown in Table 9, and the standard deviation and mean of each independent feature data are shown in Table 10.

[0100] Table 9 Table 10 Optionally, see Figure 6 , S630, before calculating the standard deviation and mean of the independent feature data corresponding to each evaluation dimension, the method further includes: S6301, if there is at least one correlation coefficient in the first correlation coefficient matrix that is not less than a preset threshold, the feature data pairs corresponding to the correlation coefficients that are not less than the preset threshold are merged to form new feature data, and it is determined that each new feature data of each enterprise maintains relative independence.

[0101] It can be understood that each new feature data includes feature data formed by merging feature data pairs corresponding to correlation coefficients not less than a preset threshold and unmerged feature data.

[0102] For example, a reasonable preset threshold (for example, the preset threshold is 0.5) can be determined based on historical data and industry standards. If there are feature data pairs with a correlation coefficient greater than 0.5, the covariance matrix of the standardized feature data can be calculated (for example, the covariance matrix of the feature data pair: , , where X and Y are feature data pairs with a correlation coefficient greater than 0.5, Var(X) and Var(Y) are the variances corresponding to X and Y, and n is the number of feature data); use mathematical methods (such as characteristic equation method, power iteration method, QR algorithm, etc.) to perform eigenvalue decomposition on the covariance matrix to obtain eigenvectors and eigenvalues; select the eigenvector with the largest eigenvalue; multiply the standardized data by the eigenvector with the largest eigenvalue to obtain the projection value of each feature data in the direction of the principal component; determine the projection value as the merged new feature data.

[0103] S6302: Determine each new feature data as independent feature data.

[0104] It can be understood that each new feature data is independent feature data.

[0105] Through the above steps S6301 to S6302, by analyzing the correlation coefficients in the first correlation coefficient matrix, those highly correlated (i.e., the correlation coefficient is not less than a preset threshold) feature data pairs are identified, and these highly correlated feature data pairs are merged to form new feature data, which is conducive to eliminating redundancy between data, achieving accurate optimization of feature data in business data, and improving data availability and accuracy.

[0106] S640, determining the feature data weight corresponding to each independent feature data based on the standard deviation and the second correlation coefficient matrix, wherein the second correlation coefficient matrix is ​​a matrix of correlation coefficients between independent feature data of each evaluated enterprise under each evaluation dimension.

[0107] For example, the CRITIC method (weight determination method based on standard deviation and correlation coefficient) can be used to calculate the characteristic data weight corresponding to the independent characteristic data of each evaluated enterprise under each evaluation dimension. The indicator conflict of the independent characteristic data of each evaluated enterprise under each evaluation dimension is: , the CRITIC value of the independent characteristic data of each evaluated enterprise under each evaluation dimension is: , the corresponding feature data weights of the independent feature data of each evaluated enterprise under each evaluation dimension are: , where C j is the CRITIC value of the jth independent feature data, S j The standard deviation of the jth independent characteristic data, p is the number of evaluated companies, r ij is the correlation coefficient between the ith independent feature data and the jth independent feature data (i.e., r ij is the value of the i-th row and j-th column in the second correlation coefficient matrix), R j Indicates the index conflict of each independent feature data, W j is the weight of the jth independent feature data. For example, the standard deviation is shown in Table 11, and the second correlation coefficient matrix is: .

[0108] Table 11 Optionally, see Figure 7 , S640, determining the feature data weight corresponding to each independent feature data based on the standard deviation and the second correlation coefficient matrix, including: S641, determining the CRITIC value of each independent feature data based on the standard deviation and the second correlation coefficient matrix.

[0109] Exemplarily, the CRITIC value of each independent feature data may be determined based on the standard deviation and the second correlation coefficient matrix: , Among them, C j is the CRITIC value of the jth independent feature data, S j The standard deviation of the jth independent characteristic data, p is the number of evaluated companies, r ij is the correlation coefficient between the ith independent feature data and the jth independent feature data (i.e., r ij is the value of the i-th row and j-th column in the second correlation coefficient matrix), R j Indicates the index conflict of each independent feature data.

[0110] S642, determining the feature data weight based on the CRITIC value of each independent feature data.

[0111] Exemplarily, the CRITIC values ​​of each independent feature data may be normalized, and the normalized CRITIC values ​​corresponding to each independent feature data may be determined as the feature data weights of each independent feature data. , where W jis the weight of the jth independent feature data, C j is the CRITIC value of the jth independent characteristic data, and p is the number of evaluated enterprises.

[0112] Through the above steps S641 to S642, by calculating the standard deviation of each independent feature data and their correlation coefficients in the second correlation coefficient matrix, the CRITIC value of each feature data is comprehensively obtained. According to the CRITIC value of each independent feature data, the weight of the feature data is determined. The weight determination method based on the CRITIC value not only takes into account the volatility of the feature data, but also takes into account the correlation between the feature data, thereby improving the accuracy and reliability of data analysis.

[0113] S650, obtaining an evaluation dimension score of the target enterprise according to the target characteristic data and the corresponding characteristic data weight, wherein the target characteristic data is the data of the target enterprise in the characteristic data.

[0114] For example, the target feature data can be multiplied by the corresponding weight to obtain the score of the target enterprise in each evaluation dimension, and each score can be standardized (for example, Z-score standardization and Min-Max standardization, etc.) to obtain the evaluation dimension score. For example, the target feature data of the target enterprise in market performance is shown in Table 12, and the score of the target enterprise in market performance is: 900×W1+1000×W2+1000×W3, where W1 is the weight of the target enterprise's first year profit, that is, the weight of the first independent feature data, W2 is the weight of the target enterprise's second year profit, that is, the weight of the second independent feature data, and W3 is the weight of the target enterprise's third year profit, that is, the weight of the third independent feature data.

[0115] Table 12 S660, determining the coefficient of variation of each evaluation dimension based on the mean.

[0116] For example, the coefficient of variation of each evaluation dimension can be calculated based on the mean of each feature data (coefficient of variation = standard deviation / mean). For example, the evaluation dimensions and independent feature data are shown in Table 13, market performance: mean = 1000 (10,000 yuan), standard deviation ≈ 115.47; product quality: mean = 2%, standard deviation ≈ 0.58; operational efficiency: mean = 4.3 (times / year), standard deviation ≈ 0.47, then the coefficients of variation of each evaluation dimension are market performance: 0.11547, product quality: 0.29, operational efficiency: 0.1088.

[0117] Table 13 S670, determining the evaluation dimension weight corresponding to each evaluation dimension based on the coefficient of variation.

[0118] For example, the coefficient of variation can be normalized, and the normalized coefficient of variation corresponding to each evaluation dimension is the evaluation dimension weight corresponding to the evaluation dimension. For example, the coefficients of variation of each evaluation dimension are market performance: 0.11547, product quality: 0.29, operational efficiency: 0.1088, and the sum of the coefficients of variation: 0.11547+0.29+0.1088=0.51427. The weights of each evaluation dimension obtained by normalizing the coefficient of variation are market performance weight: 0.11547 / 0.51427≈22.28%, product quality weight: 0.29 / 0.51427≈56.39%, and operational efficiency weight: 0.1088 / 0.51427≈21.33%.

[0119] S680, obtaining a comprehensive competitiveness index of the target enterprise according to the evaluation dimension scores of the target enterprise and the corresponding evaluation dimension weights.

[0120] For example, the score of the target enterprise in each evaluation dimension may be multiplied by the corresponding weight and the summed up to obtain the comprehensive competitiveness index of the target enterprise.

[0121] Through the above steps S610 to S680, by calculating the correlation coefficient of each pair of feature data, the correlation between the feature data is identified, which provides a basis for subsequent data processing and analysis. When the correlation between the feature data is low, confirming that the feature data of each evaluated enterprise remain relatively independent helps to retain the effective information of the data and avoid information redundancy and interference. According to the target feature data and the corresponding feature data weights, the evaluation dimension score of the target enterprise is calculated, which reflects the performance of the target enterprise in each evaluation dimension. Further, the coefficient of variation of each evaluation dimension is determined based on the standard deviation and the mean, and the evaluation dimension weight corresponding to each evaluation dimension is determined accordingly, which fully considers the differences between the evaluation dimensions, which is conducive to a more objective and fair evaluation result. The comprehensive competitiveness index of the target enterprise is calculated by combining the evaluation dimension score of the target enterprise and the corresponding evaluation dimension weight, which is conducive to a comprehensive reflection of the comprehensive competitive strength and future market position of the target enterprise.

[0122] It should be understood 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.

[0123] Corresponding to the international trade business information analysis method described in the above embodiment, the embodiment of the present application further provides an international trade business information analysis system, and each module of the system can implement each step of the international trade business information analysis method. Figure 8 A structural block diagram of an international trade business information analysis system provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0124] Reference Figure 8 The system comprises: An acquisition module, used to acquire business data from a database; wherein the database includes commodity data tables, customer data tables, sales data tables, and market data tables corresponding to a plurality of enterprises engaged in international trade, and the business data is data in the commodity data tables, customer data tables, sales data tables, and market data tables of the database; a feature module, configured to determine a first commodity feature set and a first market feature set based on the business data; wherein the first commodity feature set includes commodity features of a plurality of commodities of a target enterprise, and the first market feature set includes a plurality of market features corresponding to the commodity features of the first commodity feature set, the commodity features include performance parameters and customer types of the commodities, and the market features are market shares of the commodities corresponding to the commodity features; A first target module, used to determine the target commodity and target market of the target enterprise based on the first commodity feature set and the first market feature set; wherein the target commodity is the commodity that the target enterprise is most likely to import or export in the future, and the target market is the market demand for the target commodity; A second target module, used to determine target business data based on the target commodity and the target market; wherein the target business data is sales data, market data and customer data of the target commodity in future international trade; An evaluation module, used to determine evaluation dimensions and characteristic data corresponding to each evaluation dimension based on the target business data; wherein the evaluation dimension is a key indicator for classifying, measuring or evaluating the target business data, and the characteristic data is used to reflect the characteristics of the corresponding evaluation dimension; The target enterprise module is used to obtain the evaluation dimension score and comprehensive competitiveness index of the target enterprise according to the evaluation dimension and the characteristic data.

[0125] 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.

[0126] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0127] The present application also provides an international trade business information analysis device, Fig. 9 This is a schematic diagram of the structure of an international trade business information analysis device provided in one embodiment of the present application. Fig. 9 As shown, the international trade business information analysis device 6 of this embodiment includes: at least one processor 60 ( Fig. 9 Only one is shown), at least one memory 61 ( Fig. 9 Only one is shown in the figure) and a computer program 62 stored in the at least one memory 61 and executable on the at least one processor 60. When the processor 60 executes the computer program 62, the international trade business information analysis device 6 implements the steps in any of the above-mentioned international trade business information analysis method embodiments, or implements the functions of each module / unit in the above-mentioned system embodiments.

[0128] Exemplarily, the computer program 62 may be divided into one or more modules / units, which are stored in the memory 61 and executed by the processor 60 to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program 62 in the international trade business information analysis device 6.

[0129] The international trade business information analysis device 6 can be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The international trade business information analysis device can include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art can understand that Fig. 9It is only an example of the international trade business information analysis device 6 and does not constitute a limitation of the international trade business information analysis device 6. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, buses, etc.

[0130] The processor 60 may 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. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0131] In some embodiments, the memory 61 may be an internal storage unit of the international trade business information analysis device 6, such as a hard disk or memory of the international trade business information analysis device 6. In other embodiments, the memory 61 may also be an external storage device of the international trade business information analysis device 6, 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 international trade business information analysis device 6. Further, the memory 61 may also include both the internal storage unit of the international trade business information analysis device 6 and an external storage device. The memory 61 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory 61 may also be used to temporarily store data that has been output or is to be output.

[0132] An embodiment of the present application further 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 in any of the above method embodiments are implemented.

[0133] An embodiment of the present application provides a computer program product. When the computer program product runs on an international trade business information analysis device, the international trade business information analysis device implements the steps in any of the above method embodiments.

[0134] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned 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. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the international trade business information analysis device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0135] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0136] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0137] In the embodiments provided in the present application, it should be understood that the disclosed international trade business information analysis device / international trade business information analysis equipment and method can be implemented in other ways. For example, the international trade business information analysis device / international trade business information analysis equipment embodiment described above is only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0138] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0139] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for analyzing international trade business information, characterized in that: include: Acquire business data from a database; wherein the database includes commodity data tables, customer data tables, sales data tables, and market data tables corresponding to a plurality of enterprises engaging in international trade, and the business data is data in the commodity data tables, customer data tables, sales data tables, and market data tables of the database; Determine a first commodity feature set and a first market feature set based on the business data; wherein the first commodity feature set includes commodity features of multiple commodities of the target enterprise, and the first market feature set includes multiple market features corresponding to the commodity features of the first commodity feature set, the commodity features include performance parameters and customer types of the commodities, and the market features are market shares of the commodities corresponding to the commodity features; Determining the target commodity and target market of the target enterprise based on the first commodity feature set and the first market feature set; wherein the target commodity is the commodity that the target enterprise is most likely to import or export in the future, and the target market is the market demand for the target commodity; Determining target business data based on the target commodity and the target market; wherein the target business data is sales data, market data and customer data of the target commodity in future international trade; Determine an evaluation dimension and characteristic data corresponding to each evaluation dimension based on the target business data; wherein the evaluation dimension is a key indicator for classifying, measuring or evaluating the target business data, and the characteristic data is used to reflect the characteristics of the corresponding evaluation dimension; The evaluation dimension score and the comprehensive competitiveness index of the target enterprise are obtained according to the evaluation dimension and the characteristic data.

2. The international trade business information analysis method according to claim 1, characterized in that: The determining the first commodity feature set and the first market feature set based on the business data includes: Determining the target enterprise in the business data; Extracting commodity data of the target enterprise from the business data; wherein the commodity data includes commodity information, sales information and customer information of at least one commodity of the target enterprise; Extracting market data of the target enterprise from the business data; wherein the market data includes the market size of at least one commodity of the target enterprise; Determine the first commodity feature set based on the commodity data; The first set of market characteristics is determined based on the market data and the product data.

3. The international trade business information analysis method according to claim 1, characterized in that: The determining the target product and target market of the target enterprise based on the first product feature set and the first market feature set includes: Extracting features from the business data to obtain a second product feature set and a second market feature set; wherein the second product feature set includes product features of multiple products of multiple different enterprises, and the second market feature set includes multiple market features corresponding to the product features of the second product feature set, and the different enterprises are enterprises different from the target enterprise; Obtaining, according to the second product feature set, a similarity between each product feature in the first product feature set and each product feature in the second product feature set; Determine the maximum similarity between each product feature in the first product feature set and each product feature in the second product feature set according to each of the similarities; The products of different enterprises corresponding to the respective maximum similarities are taken as candidate target products; Performing a revenue evaluation on the candidate target products, and selecting a product with the highest revenue potential as the target product; The target market is determined based on the product characteristics and market characteristics of the target product.

4. The international trade business information analysis method according to claim 3, characterized in that: The obtaining, according to the second product feature set, the similarity between each product feature in the first product feature set and each product feature in the second product feature set includes: Vectorize each product feature of the first product feature set to obtain a corresponding first feature vector; Vectorize each product feature of the second product feature set to obtain a corresponding second feature vector; calculating a similarity value between each of the first eigenvectors and each of the second eigenvectors; The similarity value is determined as the similarity between each product feature of the first product feature set and each product feature of the second product feature set.

5. The international trade business information analysis method according to claim 1, characterized in that: The determining of target business data based on the target commodity and the target market includes: Determine competing enterprises based on the target product and the target market; Determine competitor enterprise data based on the competitor enterprise and the business data; wherein the competitor enterprise data is data in the customer data table, sales data table and market data table of the target commodity in the database of the competitor enterprise; Building a prediction model based on the business data; The target commodity, the target market and the competing enterprise data are input into the prediction model to obtain the target business data.

6. The international trade business information analysis method according to claim 5, characterized in that: The determining of the evaluation dimension and the characteristic data corresponding to each evaluation dimension based on the target business data includes: Determining correlation coefficients between a plurality of variables in the target business data based on the target business data; wherein the variables refer to data items of different aspects or attributes in the target business data; Determining a plurality of target sets based on correlation coefficients between the variables; wherein the target sets include a plurality of highly correlated variables; Determining the evaluation dimensions based on each of the target sets; Extracting characteristic data of each evaluation enterprise corresponding to each evaluation dimension from the target business data; wherein the evaluation enterprises include the target enterprise and the competing enterprises.

7. The international trade business information analysis method according to claim 6, characterized in that: The step of obtaining the evaluation dimension score and the comprehensive competitiveness index of the target enterprise according to the evaluation dimension and the characteristic data includes: Calculate the correlation coefficient of each characteristic data pair to obtain a first correlation coefficient matrix; wherein the characteristic data pair is every two characteristic data in each characteristic data corresponding to each evaluated enterprise; If each correlation coefficient in the first correlation coefficient matrix is ​​less than a preset threshold, it is determined that each characteristic data of each evaluated enterprise maintains relative independence; and the characteristic data is determined as independent characteristic data; Calculate the standard deviation and mean of each of the independent feature data; Determine the feature data weight corresponding to each of the independent feature data based on the standard deviation and the second correlation coefficient matrix; wherein the second correlation coefficient matrix is ​​a matrix of correlation coefficients between the independent feature data of each of the evaluated enterprises corresponding to each of the evaluation dimensions; Obtaining the evaluation dimension score of the target enterprise according to the target feature data and the corresponding feature data weight; wherein the target feature data is the data of the target enterprise in the feature data; Determine the coefficient of variation of each of the evaluation dimensions based on the mean; Determine the evaluation dimension weight corresponding to each of the evaluation dimensions based on the coefficient of variation; The comprehensive competitiveness index of the target enterprise is obtained according to the evaluation dimension scores of the target enterprise and the corresponding evaluation dimension weights.

8. The international trade business information analysis method according to claim 7, characterized in that: Before calculating the standard deviation and mean of the independent feature data corresponding to each evaluation dimension, the method further includes: If there is at least one correlation coefficient in the first correlation coefficient matrix that is not less than a preset threshold, then the feature data pairs corresponding to the correlation coefficients that are not less than the preset threshold are merged to form new feature data, and it is determined that each new feature data of each evaluated enterprise is relatively independent; Each new feature data is determined as the independent feature data.

9. The international trade business information analysis method according to claim 7, characterized in that: The determining the feature data weight corresponding to each of the independent feature data based on the standard deviation and the second correlation coefficient matrix includes: Determine the CRITIC value of each of the independent feature data based on the standard deviation and the second correlation coefficient matrix; The feature data weight is determined based on the CRITIC value of each of the independent feature data.

10. An international trade business information analysis system, characterized in that: include: An acquisition module, used to acquire business data from a database; wherein the database includes commodity data tables, customer data tables, sales data tables, and market data tables corresponding to a plurality of enterprises engaged in international trade, and the business data is data in the commodity data tables, customer data tables, sales data tables, and market data tables of the database; a feature module, configured to determine a first commodity feature set and a first market feature set based on the business data; wherein the first commodity feature set includes commodity features of a plurality of commodities of a target enterprise, and the first market feature set includes a plurality of market features corresponding to the commodity features of the first commodity feature set, the commodity features include performance parameters and customer types of the commodities, and the market features are market shares of the commodities corresponding to the commodity features; A first target module, used to determine the target commodity and target market of the target enterprise based on the first commodity feature set and the first market feature set; wherein the target commodity is the commodity that the target enterprise is most likely to import or export in the future, and the target market is the market demand for the target commodity; A second target module, used to determine target business data based on the target commodity and the target market; wherein the target business data is sales data, market data and customer data of the target commodity in future international trade; An evaluation module, used to determine evaluation dimensions and characteristic data corresponding to each evaluation dimension based on the target business data; wherein the evaluation dimension is a key indicator for classifying, measuring or evaluating the target business data, and the characteristic data is used to reflect the characteristics of the corresponding evaluation dimension; The target enterprise module is used to obtain the evaluation dimension score and comprehensive competitiveness index of the target enterprise according to the evaluation dimension and the characteristic data.

Images