Business risk identification method and system based on container shipping document

Abstract

The embodiment of the invention discloses a business risk identification method and system based on container sea transportation documents, and relates to the technical field of artificial intelligence and logistics transportation. The method comprises the steps of obtaining to-be-checked document information related to a target container; performing feature extraction processing on the state information and / or content information of each sub-item in the to-be-checked document information to obtain an initial feature vector; multiple different levels of depth feature mining is carried out on the initial feature vector, multiple depth feature vectors corresponding to the to-be-checked document information are obtained, and each depth feature vector is used for representing the depth feature of the to-be-checked document information in the corresponding level; performing feature fusion on the plurality of depth feature vectors corresponding to the to-be-checked document information to obtain a fused feature vector; and carrying out risk identification in multiple aspects based on the fusion feature vector to obtain a corresponding business risk identification result.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence and logistics and transportation technology, and specifically, to a business risk identification method and system based on container shipping documents. Background Art

[0002] In the field of shipping, container shipping documents (such as booking list, bill of lading, packing list, cargo list, annotation list, customs declaration, commercial invoice, etc.) carry various information in the process of cargo transportation. These documents are not only important vouchers for cargo transportation, but also an important basis for business risk identification.

[0003] Shipping documents may contain various risk information, such as false information, illegal trade, compliance issues, unclear cargo transportation routes, etc. With the increase and complexity of global trade, the review and risk identification of documents have become increasingly important. However, the traditional manual review method is inefficient and prone to errors (such as missed identification). Therefore, an automated system is urgently needed to implement container shipping document review to identify potential business risks. Summary of the invention

[0004] In view of this, one aspect of an embodiment of this specification provides a method for identifying business risks based on container shipping documents, the method comprising: Acquire document information to be checked related to the target container, wherein the document information to be checked is obtained by identifying at least one document related to the target container and arranging the documents in a preset order; Performing feature extraction processing on the status information and / or content information of each sub-item in the document information to be verified to obtain an initial feature vector; Performing deep feature mining at multiple different levels on the initial feature vector to obtain multiple deep feature vectors corresponding to the document information to be verified, wherein each of the deep feature vectors is used to represent the deep features of the document information to be verified at a corresponding level; Performing feature fusion on multiple deep feature vectors corresponding to the document information to be verified to obtain a fused feature vector; Based on the fused feature vector, multiple aspects of risk identification are performed to obtain corresponding business risk identification results.

[0005] In some embodiments, obtaining the document information to be checked related to the target container includes: For each target document related to the target container, extract the document type information of the target document and the status information and / or content information of at least one sub-item contained in the target document by using OCR recognition technology to obtain the partial information to be verified corresponding to the target document; The status information and / or content information of at least one sub-item contained in each of the target documents is arranged according to a first preset order, and when there are multiple documents, the local information to be verified corresponding to the multiple documents are arranged according to a second preset order to obtain the document information to be verified related to the target container.

[0006] In some embodiments, the step of arranging the partial information to be checked corresponding to the plurality of documents in accordance with a second preset order to obtain the document information to be checked related to the target container includes: Sorting the documents according to their importance to determine the second preset order; According to the document type information of at least one document related to the target container, the corresponding local information to be verified is written into the corresponding position in the second preset order, and the missing data is filled with preset values ​​to obtain the document information to be verified related to the target container.

[0007] In some embodiments, the feature extraction process is performed on the status information and / or content information of each sub-item in the document information to be verified to obtain an initial feature vector, including: The status information and / or content information of each sub-item in the document information to be verified is semantically encoded through natural language processing to obtain at least one semantic vector corresponding to the document information to be verified, and the initial feature vector is obtained based on the at least one semantic vector.

[0008] In some embodiments, the performing of deep feature mining at multiple different levels on the initial feature vector to obtain multiple deep feature vectors corresponding to the document information to be verified includes: Inputting the initial feature vector into a deep feature extraction network, wherein the deep feature extraction network includes a plurality of hidden layers, each hidden layer corresponds to an activation function, and each of the hidden layers and the activation function is used to perform a level of deep feature mining on the initial feature vector; Based on the outputs of the multiple hidden layers, multiple deep feature vectors corresponding to the document information to be verified are obtained.

[0009] In some embodiments, the performing feature fusion on multiple deep feature vectors corresponding to the document information to be verified to obtain the fused feature vector includes: concatenating the multiple deep feature vectors to obtain the fused feature vector.

[0010] In some embodiments, the risk identification in multiple aspects is performed based on the fused feature vector to obtain corresponding business risk identification results, including: The fused feature vectors are respectively input into a plurality of pre-trained classifiers for classification processing, and the business risk identification result is obtained based on the outputs of the plurality of classifiers; wherein each of the classifiers corresponds to one aspect of risk identification.

[0011] In some embodiments, the multiple classifiers are trained based on the following method: Acquire a sample fusion feature vector obtained by processing at least one sample document related to the sample case, and a plurality of risk labels corresponding to the sample fusion feature vector, wherein each of the plurality of risk labels is used as an expected output of a classifier; Inputting the sample fusion feature vector into the multiple classifiers respectively to obtain the prediction output corresponding to each classifier; Determine a loss value for each classifier based on a difference between a predicted output and an expected output corresponding to each of the classifiers; The multiple classifiers are iteratively optimized based on the loss values ​​until the multiple trained classifiers are obtained when preset training conditions are met.

[0012] In some embodiments, before inputting the sample fusion feature vector into the multiple classifiers respectively to obtain the prediction output corresponding to each classifier, the method further includes: For each of the classifiers, the sample fusion feature vector is attention-encoded by an attention mechanism to obtain an attention fusion vector corresponding to each classifier; The attention fusion vector is input as the input data of the classifier into the corresponding classifier for processing to obtain the corresponding prediction output of each classifier.

[0013] Another aspect of the embodiments of this specification further provides a business risk identification system based on container shipping documents, the system comprising: An acquisition module, used for acquiring document information to be checked related to a target container, wherein the document information to be checked is obtained by identifying at least one document related to the target container and arranging the documents in a preset order; An initial feature vector determination module is used to perform feature extraction processing on the status information and / or content information of each sub-item in the document information to be verified to obtain an initial feature vector; A deep feature vector determination module is used to perform deep feature mining at multiple different levels on the initial feature vector to obtain multiple deep feature vectors corresponding to the document information to be verified, wherein each of the deep feature vectors is used to represent the deep features of the document information to be verified at a corresponding level; A fusion feature vector determination module is used to perform feature fusion on multiple deep feature vectors corresponding to the document information to be verified to obtain a fusion feature vector; The business risk identification module is used to perform risk identification in multiple aspects based on the fused feature vector to obtain corresponding business risk identification results.

[0014] The beneficial effects that the business risk identification method and system based on container shipping documents provided in the embodiments of this specification may bring include at least: obtaining an initial feature vector by extracting and processing the features of the document information to be verified, and then performing deep feature mining at multiple different levels on the initial feature vector to obtain multiple deep feature vectors, which can more comprehensively reflect the complex features in the document information to be verified, thereby improving the accuracy and reliability of the business risk identification results obtained based on the multiple deep feature vectors in the subsequent process.

[0015] Additional features will be described in part in the following description. For those skilled in the art, it will become apparent by reviewing the following and accompanying drawings, or it may be understood by the production or operation of the examples. The features of this specification may be implemented and obtained by practicing or using various aspects of the methods, tools, and combinations described in the following detailed examples. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein: Figure 1 is an exemplary flow chart of a business risk identification method based on container shipping documents according to some embodiments of this specification; Figure 2 is a schematic diagram of a feature vector processing flow according to some embodiments of this specification; Figure 3 It is a schematic diagram of the business risk identification principle shown in some embodiments of this specification; Figure 4 It is a schematic diagram of the business risk identification principle shown in other embodiments of this specification; Figure 5 It is an exemplary module diagram of a business risk identification system based on container shipping documents according to some embodiments of this specification. DETAILED DESCRIPTION

[0017] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0018] It should be understood that the "system", "device", "unit" and / or "module" used in this specification is a method for distinguishing different components, elements, parts, parts or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0019] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0020] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0021] The following is a detailed description of the business risk identification method and system based on container shipping documents provided in the embodiments of this specification in conjunction with the accompanying drawings.

[0022] Figure 1 is an exemplary flow chart of a business risk identification method based on container shipping documents according to some embodiments of this specification. In some embodiments, the business risk identification method based on container shipping documents can be executed by processing logic, which can include hardware (e.g., circuits, dedicated logic, programmable logic, microcode, etc.), software (instructions running on a processing device to perform hardware simulation), etc. or any combination thereof. In some embodiments, Figure 1 One or more operations in the flowchart of the method for identifying business risks based on container shipping documents can be implemented by a processing device and / or a terminal device. For example, the method for identifying business risks based on container shipping documents can be stored in a storage device in the form of a computer program and / or instruction, and called and / or executed by a processing device and / or a terminal device. Figure 1 In some embodiments, the business risk identification method based on container shipping documents may include: Step S110, obtaining document information to be checked related to the target container, wherein the document information to be checked is obtained by identifying at least one document related to the target container and arranging them in a preset order. In some embodiments, step S110 may be executed by the acquisition module 210 mentioned below.

[0023] A container is a large cargo container with standardized size and solid structure. It is the core tool for international cargo transportation. It can be used to transport various types of cargo, thereby ensuring the safety and efficiency of cargo transportation. In the actual shipping process, a container (each container has an irreplaceable container number) can correspond to one or more booking numbers, or a booking number can correspond to one or more containers, where the booking number can be understood as a business number.

[0024] In an embodiment of the present application, the document information to be checked related to the target container can be obtained. The target container can be understood as a specific container, and its unique identifier is the container number. By obtaining all the document information related to the target container, the system can fully grasp the various business data of the container during the sea transportation process. These document information include but are not limited to one or more of the booking list, packing list, bill of lading, cargo list, annotation list, commercial invoice, insurance policy, customs declaration, certificate of origin, export license, transportation contract, etc., covering the whole process from cargo packing to transportation to the destination. By identifying these document information and extracting key information, a solid data foundation can be provided for subsequent risk identification and analysis.

[0025] Specifically, a booking order refers to a consignment document prepared by a shipping company or its agent based on the shipper's booking requirements. A packing list lists in detail the type, quantity, and packaging of the goods loaded into the container. A bill of lading is a document issued by a carrier or its agent that proves that the goods have been received and that it promises to transport them to a designated location in accordance with the terms of the contract. The cargo list, annotated list, commercial invoice, insurance policy, etc. record the detailed information, transaction status, insurance status, etc. of the goods from different perspectives. The customs declaration and certificate of origin are important bases for customs clearance and tax incentives. The export license ensures the legitimacy of the exported goods. The transport contract clarifies the rights and obligations between the carrier and the shipper, providing legal protection for both parties. These documents usually contain interrelated information, which together constitute the overall picture of the container shipping business. For example, the cargo information in the booking order should be consistent with the cargo information in the packing list to ensure that there is no omission or error in the packing process; the cargo information, quantity, destination, etc. in the bill of lading should match the information in the booking order and the packing list to ensure that the carrier can deliver the goods to the designated location according to the correct transportation requirements; the cargo price, quantity, etc. in the commercial invoice are closely related to the cargo value, quantity, etc. in the customs declaration, which directly affects the customs clearance and tax calculation. Therefore, comprehensive and accurate identification and correlation analysis of these document information is the key to identifying the risks of container shipping business. Through comprehensive acquisition and in-depth analysis of this information, potential business risks can be discovered in a timely manner, such as inconsistent document information, loss of goods, mixing of counterfeit and shoddy products, tax evasion, illegal transportation, etc. These risks may not only lead to economic losses, but also have a negative impact on the reputation and long-term development of the company. Therefore, in the embodiment of the present application, it is hoped that anomalies and contradictions in the document information can be identified through intelligent algorithms, so as to accurately judge the existence or non-existence of business risks.

[0026] Specifically, in some embodiments of the present application, data can be collected for each document by scanning and then stored in a storage device. Further, the acquisition module 210 can acquire at least one document related to the target container from the storage device, then identify the at least one document and arrange them in a preset order, thereby obtaining the document information to be checked related to the target container.

[0027] Specifically, in some embodiments, for each target document related to the target container (the target document may be any one of one or more documents related to the target container), the document type information of the target document and the status information and / or content information of at least one sub-item contained in the target document may be extracted through OCR (Optical Character Recognition) recognition technology to obtain the local information to be verified corresponding to the target document. The sub-item may be understood as a specific field or item in the target document, such as cargo description, weight, volume, port of departure, port of destination, voyage, consignor, carrier, consignee, notify party, freight payment method, etc. The local information to be verified may be understood as local data in the document information to be verified related to the target container. In the embodiment of the present application, the local information to be verified may refer to the information set of all sub-items contained in a target document.

[0028] In an embodiment of the present application, some sub-items in the target document can be used to indicate the business status, such as the "characteristic relationship confirmation", "price impact relationship confirmation" and "goods-related royalty payment confirmation" that may be involved in the customs declaration form, etc. These business statuses can be reflected in the form of text (such as yes or no) or status codes (such as 1 or 0), and these texts or status codes can intuitively reflect the current status of the sub-item in the business process.

[0029] It should be noted that in some embodiments of the present application, the various sub-items in the documents can be divided by the tables in each document, or the aggregation, logic and continuity between the texts. For example, different sub-items can be defined based on the column headings or row contents in the document table, such as "cargo description" may correspond to a column in the table, while "weight" and "volume" may correspond to adjacent columns respectively. At the same time, by analyzing the keywords or phrases in the text description, such as "port of departure", "port of destination", etc., they can also be accurately identified as independent sub-items. In addition, the sub-items in the documents can be further subdivided and classified based on the correlation between business logic and documents to improve the accuracy and efficiency of information identification.

[0030] In some embodiments of the present application, a dedicated OCR recognition model for information identification and extraction of various types of documents can be trained by machine learning. For example, in some embodiments, the initial OCR recognition model is trained with a large number of document samples to improve its accuracy and robustness in recognizing characters and formats in container shipping documents. During the training process, the model will learn and understand the layout, text features, and possible logical relationships of different sub-items in the document, so that it can more accurately identify and extract key information in practical applications. The specially trained OCR recognition model can greatly improve the accuracy and reliability of document information identification and feature extraction, and provide a reliable data basis for subsequent business risk assessment and decision-making. More training details about the OCR recognition model can be regarded as prior art and will not be discussed in detail in this specification.

[0031] Furthermore, in some embodiments of the present application, the status information and / or content information of at least one sub-item contained in each of the target documents can be arranged according to a first preset order, and when the number of the documents is multiple, the local information to be verified corresponding to the multiple documents can be arranged according to a second preset order to obtain the document information to be verified related to the target container.

[0032] Exemplarily, in some embodiments of the present application, the aforementioned first preset order may refer to sorting the sub-items in each target document in a left-to-right and top-to-bottom order based on the document typesetting or layout of the data in each area.

[0033] In some embodiments of the present application, the aforementioned second preset order can be obtained by sorting according to the importance of each document. As an example only, in some embodiments, the main documents related to container shipping may include booking orders, bills of lading, packing lists, cargo lists, annotated lists, commercial invoices, insurance policies, customs declarations, certificates of origin, export licenses, etc., and the second preset order can be expressed as: bill of lading> packing list> cargo list> annotated list> commercial invoice> insurance policy> customs declaration> export license> certificate of origin> booking order. Through this sorting method, it can be ensured that in the process of business risk identification, priority is given to documents that have a greater impact on the business process, thereby improving the efficiency and accuracy of risk identification. In addition, this orderly arrangement also helps relevant staff to quickly locate key information during manual verification and reduce the time cost of finding required data in a large number of documents. It should be noted that in actual applications, the sorting rules of documents can also be flexibly adjusted according to specific business scenarios and needs to adapt to different business processes and risk management strategies.

[0034] In an embodiment of the present application, after determining the above-mentioned second preset order, the corresponding local information to be verified can be written into the corresponding position in the second preset order according to the document type information of at least one document related to the target container, and the missing data can be filled in with the preset value to obtain the document information to be verified related to the target container.

[0035] For example, in some embodiments, the documents related to the target container in the actual business processing process include bills of lading, packing lists, customs declarations and commercial invoices, then the document information to be verified related to the target container can be expressed as: "data1-1, data1-2,..., data1-m; data2-1, data2-2,..., data2-n; null; null; data5-1, data5-2,..., data5-i; null; data7-1, data7-2,..., data7-j; null; null; null". Among them, "data1-1, data1-2, ..., data1-m" represents the partial information to be verified obtained by sorting the various sub-items in the bill of lading according to the aforementioned first preset order, and m is the total number of sub-items included in the bill of lading; "data2-1, data2-2, ..., data2-n" represents the partial information to be verified obtained by sorting the various sub-items in the packing list according to the aforementioned first preset order, and n is the total number of sub-items included in the packing list; "data5-1, data5-2, ..., data5-i" represents the partial information to be verified obtained by sorting the various sub-items in the commercial invoice according to the aforementioned first preset order, and i is the total number of sub-items included in the commercial invoice; "data7-1, data7-2, ..., data7-j" represents the partial information to be verified obtained by sorting the various sub-items in the customs declaration according to the aforementioned first preset order, and j is the total number of sub-items included in the customs declaration; null represents the result obtained by filling the missing data with the preset value, in other words, it means that the document information at the corresponding position is missing.

[0036] It should be noted that in the embodiments of the present application, the documents required for different business scenarios (such as different ports of destination, different types of goods, etc.) may be different. Some business scenarios may require documents other than the document types listed above. In this case, the corresponding partial information to be verified can be placed at the end of the second preset order mentioned above, and the corresponding document information to be verified can be obtained by arranging in a similar manner. In some embodiments, at least one document corresponding to the target container may include documents with different business numbers. In this case, documents of the same type can be listed side by side in the second preset order, and based on this, the document information to be verified related to the target container can be obtained. In addition, it should be noted that for some business scenarios, only some of the document types listed above may be required. In this case, the absence of other document information may not mean that there is a business risk.

[0037] Step S120, extracting features from the status information and / or content information of each sub-item in the document information to be checked to obtain an initial feature vector. In some embodiments, step S120 may be performed by the initial feature vector determination module 220 mentioned below.

[0038] In an embodiment of the present application, the status information and / or content information of each sub-item in the document information to be verified obtained by the above process can be semantically encoded through natural language processing to obtain at least one semantic vector corresponding to the document information to be verified, and the initial feature vector can be obtained based on the at least one semantic vector.

[0039] Specifically, in the embodiment of the present application, the text content in the document information to be verified can be converted into a numerical form that can be understood by the machine through natural language processing (NLP). For example, the text information describing the status of the goods can be converted into a numerical indicator indicating the status of the goods; the text information describing the type of goods can be converted into a numerical vector indicating the characteristics of the category of the goods.

[0040] In some embodiments of the present application, each sub-item in the above-mentioned document information to be verified can be converted into a corresponding semantic vector. In other embodiments of the present application, multiple sub-items can also be converted into a semantic vector. Specifically, in some embodiments, the text information in each sub-item can be mapped to a high-dimensional vector space by word embeddings to obtain its corresponding semantic vector. Exemplary word embedding methods may include Word2Vec, GloVe, BERT, etc. These word embedding methods can learn the semantic relationship between words from a large amount of text data, thereby mapping similar words to similar positions in the vector space. In this way, the text content contained in each sub-item in the document information to be verified can be converted into a numerical form that can be understood by a machine, thereby providing data support for subsequent business risk identification.

[0041] In the embodiment of the present application, the semantic vectors corresponding to each sub-item can be arranged according to the first preset order and the second preset order to obtain the above-mentioned initial feature vector. In the embodiment of the present application, the initial feature vector can be understood as a vector represented in numerical form that contains the status information and / or content information of each sub-item in the document information to be verified. This initial feature vector will serve as important input data in the subsequent business risk identification step, and business risk prediction and evaluation will be performed based on it.

[0042] Step S130, performing deep feature mining at multiple different levels on the initial feature vector to obtain multiple deep feature vectors corresponding to the document information to be verified, wherein each of the deep feature vectors is used to represent the deep features of the document information to be verified at the corresponding level. In some embodiments, step S130 can be performed by the deep feature vector determination module 230 mentioned later.

[0043] It should be noted that the same or related content in different documents should correspond to an identical or similar semantic vector, and therefore, will be represented in the same or similar numerical form in the initial feature vector. However, by only identifying the same or related information in the initial feature vector, it is still impossible to confirm under what circumstances the initial feature vector has business risks and under what circumstances there are no business risks. Based on this, in some embodiments of the present application, multiple deep feature vectors corresponding to the document information to be verified can be obtained by performing deep feature mining at multiple different levels on the initial feature vector, wherein each of the deep feature vectors is used to represent the deep features of the document information to be verified at the corresponding level.

[0044] It can be understood that by performing multiple different levels of deep feature mining on the initial feature vector, more abstract and higher-level feature representations can be gradually extracted, thereby capturing more complex feature patterns and semantic information. Specifically, in some embodiments of the present application, the initial feature vector can be input into a deep feature extraction network, wherein the deep feature extraction network includes multiple hidden layers, each hidden layer corresponds to an activation function, and each of the hidden layers and the activation function is used to perform one level of deep feature mining on the initial feature vector; further, based on the outputs of the multiple hidden layers, multiple deep feature vectors corresponding to the document information to be verified can be obtained.

[0045] Figure 2 is a schematic diagram of a feature vector processing flow according to some embodiments of this specification. Figure 2 In the embodiment of the present application, each hidden layer of the deep feature extraction network (e.g. Figure 2 H1, H2, H3, ..., Hx) shown may include multiple neurons (the neuron can be understood as a computing unit, and multiple neurons can constitute a convolution kernel. In the embodiment of the present application, different hidden layers can have the same or different numbers of neurons). Each neuron can receive the output from the neurons in the previous layer, and calculate based on the weights and biases to output a result. These results can be passed to the next layer of neurons after nonlinear transformation by the activation function (such as ReLU), so as to perform higher-level deep feature extraction. In this way, the deep feature extraction network can gradually extract the complex features in the document information to be verified, which helps to dig out deep data information, thereby realizing accurate identification of business risks.

[0046] Specifically, in the embodiment of the present application, the first hidden layer H1 can accept the initial feature vector and process the initial feature vector through the multiple neurons it contains to obtain the output of each neuron. Furthermore, the output of each neuron in the first hidden layer H1 can be used as the input of the second hidden layer H2, and each neuron in the second hidden layer H2 processes these inputs, and so on, until the last hidden layer Hx (x is the number of hidden layers). In each hidden layer, by continuously adjusting the weights and biases of the neurons, the deep feature extraction network can learn more abstract and complex feature representations.

[0047] In some embodiments of the present application, for each hidden layer, the outputs of the multiple neurons contained therein can be integrated to obtain the output corresponding to the hidden layer. For example, by weighted averaging or summing the outputs of the neurons in the first hidden layer H1, the depth feature vector O1 corresponding to the first hidden layer H1 can be obtained. Similarly, for the subsequent hidden layers H2, H3...Hx, the same method can be used to integrate the outputs of the multiple neurons contained therein to obtain the corresponding depth feature vectors O2, O3...Ox. It can be understood that these deep feature vectors can more comprehensively reflect the complex features in the document information to be verified, thereby providing strong support for the accurate identification of subsequent business risks.

[0048] Step S140, performing feature fusion on the multiple deep feature vectors corresponding to the document information to be verified to obtain a fused feature vector. In some embodiments, step S140 may be performed by the fused feature vector determination module 240 mentioned below.

[0049] Continue to refer to Figure 2 After obtaining the above-mentioned depth feature vectors O1, O2, O3...Ox, the multiple depth feature vectors can be subjected to feature fusion by a feature fusion unit to obtain a fused feature vector.

[0050] Specifically, in some embodiments of the present application, the fused feature vector may be obtained by concatenating the above-mentioned multiple depth feature vectors O1, O2, O3...Ox.

[0051] It can be understood that in the embodiment of the present application, the fused feature vector contains the deep features obtained by extracting features at different levels of the document information to be verified, and therefore, it can more comprehensively express the complex features in the document information to be verified. Based on this, in the subsequent business risk identification process, a more accurate and comprehensive analysis can be performed based on the fused feature vector, thereby improving the accuracy and reliability of business risk identification. In some embodiments of the present application, the feature fusion unit can be implemented by a dedicated hardware circuit or software module to achieve efficient fusion of multiple deep feature vectors.

[0052] Step S150 is used to perform risk identification in multiple aspects based on the fused feature vector to obtain corresponding business risk identification results. In some embodiments, step S150 may be performed by the business risk identification module 250 mentioned below.

[0053] In the embodiment of the present application, the fused feature vectors obtained in the above process can be respectively input into a plurality of pre-trained classifiers for classification processing, and the business risk identification result can be obtained based on the outputs of the plurality of classifiers, wherein each of the classifiers corresponds to one aspect of risk identification.

[0054] Specifically, the risks reflected by container shipping documents may include multiple aspects, such as compliance risks (whether they comply with relevant laws and regulations on international and domestic trade and transportation), financial risks (financial verification issues involving invoices, payments, etc.), transportation risks (possible delays, damage or loss of goods in the transportation, unloading, customs clearance and other links), contractual risks (the terms of shipment and delivery of goods are inconsistent with the contract, or there are problems with the transporter's performance of the contract), and information accuracy risks (for example, whether the information in the document is accurate, such as whether the product name, quantity, mode of transportation, etc. are consistent with the actual situation).

[0055] In the embodiment of the present application, in order to ensure the accuracy and reliability of risk identification, multiple classifiers can be used to process the fused feature vector respectively. Among them, each classifier is specially trained (for example, the document data of the relevant case is specially trained), so that each classifier can identify a specific type of risk. It should be noted that in the embodiment of the present application, by using relevant cases to train each classifier differently, each classifier can have different focuses during the data processing process. For example, after training, the classifier of compliance risk may focus on whether the document complies with the relevant laws and regulations of international trade and transportation; after training, the classifier of financial risk may pay more attention to the verification of financial information such as invoices and payments; the classifier of transportation risk will evaluate the problems that may exist in the links of cargo transportation, unloading, customs clearance, etc.; the classifier of contract risk may focus on analyzing whether the terms of cargo shipment and delivery are consistent with the contract, as well as the performance of the transporter; and the classifier of information accuracy risk may focus on whether the information in the document, such as the name, quantity, mode of transportation, etc., is consistent with the actual situation.

[0056] It should be noted that in the embodiment of the present application, through the collaborative work of multiple classifiers, comprehensive and accurate identification of the various risks involved in container shipping documents can be achieved. This multi-classifier design not only improves the efficiency of risk identification, but also ensures the accuracy of identification. In addition, since each classifier has been specially trained and has different focuses, it can better adapt to different types of risk identification needs, making the entire risk identification system more flexible and efficient.

[0057] Figure 3 This is a schematic diagram of the business risk identification principle shown in some embodiments of this specification. Figure 3In some embodiments of the present application, the fused feature vector can be input into classifier 1, classifier 2, ..., classifier y for processing, and the classification result F1 output by classifier 1, the classification result F2 output by classifier 2, ..., and the classification result Fy output by classifier y are obtained. In some embodiments of the present application, classifier 1, classifier 2, ..., classifier y can be binary classifiers, and their output results are 0 or 1, where 0 indicates that the document does not involve the risk identified by the corresponding classifier, and 1 indicates that the document involves the risk identified by the corresponding classifier. In some embodiments of the present application, classifier 1, classifier 2, ..., classifier y can also be linear classifiers (such as softmax classifiers), and their output results can be expressed in the form of probability. For example, the output result of each classifier can be in the range of [0, 1], where 0 indicates that the document information to be verified does not involve the risk identified by the corresponding classifier, 0.1 indicates that the probability that the document information to be verified involves the risk identified by the corresponding classifier is small, and 0.9 indicates that the probability that the document information to be verified involves the risk identified by the corresponding classifier is large.

[0058] The following is a brief introduction to the training methods of each classifier involved in the embodiments of the present application: In an embodiment of the present application, a sample fusion feature vector obtained by processing at least one sample document related to a sample case and a plurality of risk labels corresponding to the sample fusion feature vector can be obtained, wherein each of the plurality of risk labels is used as the expected output of a classifier (the risk label can be obtained through manual evaluation); then, the sample fusion feature vector can be respectively input into the plurality of classifiers to obtain the predicted output corresponding to each classifier; further, the loss value of each classifier can be determined based on the difference between the predicted output and the expected output corresponding to each of the classifiers; finally, the plurality of classifiers are iteratively optimized based on the loss value until the plurality of trained classifiers are obtained when the preset training conditions are met.

[0059] Exemplarily, in some embodiments, the loss value may be expressed as:

[0060] Where L represents the sum of the loss values ​​of all classifiers, represents the predicted output of the i-th classifier, represents the corresponding risk label, and y represents the total number of classifiers.

[0061] In some embodiments of the present application, in order to accelerate the convergence speed of classifier training to a certain extent, each classifier can be trained separately. For example, for the classifier for compliance risk identification, a large number of cases related to compliance risks can be obtained (including positive samples and negative samples, that is, the sample cases require both document data with risks and document data without risks), and these cases may include one or more sample documents related to the sample container. In the embodiment of the present application, one or more sample documents related to the sample container can be processed in the above manner to obtain the corresponding sample fusion feature vector and the compliance risk label corresponding to the sample fusion feature vector; then, the sample fusion feature vector can be input into the corresponding target classifier respectively to obtain the corresponding predicted output of the target classifier; further, the loss value can be determined based on the difference between the predicted output and the expected output corresponding to the target classifier; finally, the target classifier is iteratively optimized based on the loss value until the training of the target classifier is completed when the preset training conditions are met.

[0062] In an embodiment of the present application, the classifier can be iteratively optimized using a gradient descent method or other optimization algorithms. Specifically, in each iteration, the loss value is calculated based on the parameters of the current classifier, and then the gradient of the loss value to the classifier parameters is calculated by the back propagation algorithm, and then the parameters of the classifier are updated according to the gradient to reduce the loss value. By repeating this process continuously until the loss value converges to a smaller value, or reaches a preset number of iterations, the classifier can be considered to have been trained. It can be understood that after training, each classifier can obtain the corresponding generalization ability and can accurately predict the business risk of the document information to be verified related to the target container. Moreover, in this way, trained classifiers for different types of risks (such as compliance risk, financial risk, contract risk, etc.) can be obtained, and these classifiers can be used to classify the fused feature vectors obtained in the above process, so as to accurately identify the potential business risks in container shipping documents.

[0063] In some embodiments of the present application, the above-mentioned fused feature vector can be processed by a trained classifier to obtain a corresponding business risk identification result. The business risk identification result may include multiple data (for example, y data), each of which is used to reflect its risk situation in one aspect. In some embodiments of the present application, when the classification result obtained by processing the above-mentioned fused feature vector using a trained classifier reflects the existence of at least one risk, the relevant data can be backed up and recorded and sent to relevant business personnel for manual review.

[0064] Specifically, in some embodiments of the present application, the system can automatically mark documents that are at risk, and save them together with relevant business data to a designated storage medium for subsequent review and analysis. At the same time, in some embodiments, the system can also generate a risk warning notification, and send it to the corresponding business personnel in a timely manner through e-mail, text message, or system message. After receiving the warning notification, the business personnel can log in to the system to view detailed risk information and related documents for manual review. During the review process, the business personnel can further confirm and evaluate the risks identified by the system based on their own professional knowledge and experience to ensure the accuracy and reliability of risk identification. It should be noted that in this way, the efficiency and accuracy of risk identification in the container shipping document business can be effectively improved, while reducing the operating risks of the enterprise, greatly reducing the manpower costs required for document review.

[0065] Figure 4 This is a schematic diagram of the business risk identification principle shown in other embodiments of this specification. Figure 4 In some embodiments of the present application, for each of the classifiers, the sample fusion feature vector can be attention encoded through the attention mechanism to obtain the attention fusion vector corresponding to each classifier; then, the attention fusion vector is input into the corresponding classifier as the input data of the classifier for processing to obtain the prediction output corresponding to each classifier.

[0066] It can be understood that by using the attention mechanism to perform attention encoding on the sample fusion feature vector, the classifier can pay more attention to those features that have a greater impact on the risk identification results, thereby improving the accuracy and efficiency of risk identification. Specifically, the attention mechanism can assign different weights to different features according to their importance, so that important features receive more attention and consideration in the risk identification process. In this way, the risk points reflected by the deep features of different levels in the fusion feature vector corresponding to the document information to be verified can be captured more accurately, thereby improving the efficiency and accuracy of risk identification.

[0067] At the same time, since the attention mechanism can adaptively adjust the feature weights according to different situations, the flexibility and adaptability of risk identification can also be improved. More details about the attention encoding of the sample fusion feature vector by the attention mechanism can be regarded as prior art and will not be repeated in this specification.

[0068] Figure 5 is a module diagram of a business risk identification system based on container shipping documents according to some embodiments of this specification. In some embodiments, Figure 5The business risk identification system 200 based on container shipping documents shown can be implemented in software and / or hardware. For example, it can be configured in the form of software and / or hardware to a processing device and / or a terminal device for processing at least one document related to a target container and identifying potential business risks based on the at least one document.

[0069] Reference Figure 5 In some embodiments, the business risk identification system 200 based on container shipping documents may include an acquisition module 210, an initial feature vector determination module 220, a deep feature vector determination module 230, a fusion feature vector determination module 240 and a business risk identification module 250.

[0070] The acquisition module 210 may be used to acquire document information to be checked related to the target container. The document information to be checked is obtained by identifying at least one document related to the target container and arranging the documents in a preset order.

[0071] The initial feature vector determination module 220 may be used to perform feature extraction processing on the status information and / or content information of each sub-item in the document information to be verified to obtain an initial feature vector.

[0072] The deep feature vector determination module 230 can be used to perform deep feature mining at multiple different levels on the initial feature vector to obtain multiple deep feature vectors corresponding to the document information to be verified, wherein each of the deep feature vectors is used to represent the deep features of the document information to be verified at the corresponding level.

[0073] The fused feature vector determination module 240 may be used to perform feature fusion on a plurality of deep feature vectors corresponding to the document information to be verified to obtain a fused feature vector.

[0074] The business risk identification module 250 can be used to perform risk identification in multiple aspects based on the fused feature vector to obtain corresponding business risk identification results.

[0075] For more details about the above modules, please refer to other places in this manual (for example Figure 1~Figure 4 part and its related description) will not be repeated here.

[0076] It should be understood that Figure 5The business risk identification system 200 based on container shipping documents and its modules shown can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented by hardware, software, or a combination of software and hardware. Among them, the hardware part can be implemented by using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated hardware. Those skilled in the art can understand that the above methods and systems can be implemented using computer executable instructions and / or included in processor control codes, such as such codes provided on carrier media such as disks, CDs or DVD-ROMs, programmable memories such as read-only memories (firmware), or data carriers such as optical or electronic signal carriers. The system and its modules of this specification can be implemented not only by hardware circuits such as ultra-large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but also by software implemented by, for example, various types of processors, and can also be implemented by a combination of the above hardware circuits and software (for example, firmware).

[0077] It should be noted that the above description of the business risk identification system 200 based on container shipping documents is provided for illustrative purposes only and is not intended to limit the scope of this specification. It is understandable that for those skilled in the art, according to the description of this specification, without departing from this principle, the various modules can be arbitrarily combined, or a subsystem can be formed to connect with other modules. For example, Figure 5 The acquisition module 210, the initial feature vector determination module 220, the deep feature vector determination module 230, the fusion feature vector determination module 240 and the business risk identification module 250 described in the embodiment can be different modules in a system, or one module can realize the functions of two or more of the above modules. Such variations are within the protection scope of this specification.

[0078] In summary, the beneficial effects that may be brought about by the embodiments of the present specification include but are not limited to: (1) In the business risk identification method and system based on container shipping documents provided in some embodiments of the present specification, an initial feature vector is obtained by extracting and processing the features of the document information to be verified, and then multiple deep feature vectors are obtained by performing deep feature mining at multiple different levels on the initial feature vector, which can more comprehensively reflect the complex features in the document information to be verified, thereby improving the accuracy and reliability of the business risk identification results obtained based on the multiple deep feature vectors in the subsequent process; (2) In the business risk identification method and system based on container shipping documents provided in some embodiments of the present specification, multiple classifiers are used to classify the business risk based on multiple different levels. The fused feature vector obtained by fusion of the deep feature vectors of the layers is processed to realize risk identification in multiple aspects, so that each classifier can have different focus after training, so as to better adapt to different types of risk identification needs, to a certain extent improve the efficiency of risk identification and the accuracy of risk identification results, and make the entire risk identification system more flexible and efficient; (3) In the business risk identification method and system based on container shipping documents provided in some embodiments of this specification, the verification of container shipping documents is realized by artificial intelligence, which can effectively improve the efficiency and accuracy of container shipping document business risk identification, while reducing the operating risk of the enterprise, and greatly reduce the manpower cost required for document review.

[0079] It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects that may be produced may be any one or a combination of the above, or may be any other possible beneficial effects.

[0080] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0081] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0082] In addition, it will be understood by those skilled in the art that various aspects of this specification may be illustrated and described by a number of patentable categories or situations, including any new and useful process, machine, product or combination of substances, or any new and useful improvements thereto. Accordingly, various aspects of this specification may be performed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software may be referred to as "data blocks", "modules", "engines", "units", "components" or "systems". In addition, various aspects of this specification may be represented as a computer product located in one or more computer-readable media, which includes computer-readable program code.

[0083] A computer storage medium may include a propagated data signal containing computer program code, for example, in baseband or as part of a carrier wave. The propagated signal may be in a variety of forms, including electromagnetic, optical, etc., or a suitable combination. A computer storage medium may be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, device or apparatus to communicate, propagate or transmit the program for use. The program code on the computer storage medium may be transmitted via any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of the above media.

[0084] The computer program codes required for the operation of each part of this specification can be written in any one or more programming languages, including object-oriented programming languages ​​such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc., conventional procedural programming languages ​​such as C language, Visual Basic, Fortran2003, Perl, COBOL2002, PHP, ABAP, dynamic programming languages ​​such as Python, Ruby and Groovy, or other programming languages, etc. The program code can be run entirely on the user's computer, or run on the user's computer as an independent software package, or run partly on the user's computer and partly on a remote computer, or run entirely on a remote computer or processing device. In the latter case, the remote computer can be connected to the user's computer through any network form, such as a local area network (LAN) or a wide area network (WAN), or connected to an external computer (e.g., via the Internet), or in a cloud computing environment, or used as a service such as software as a service (SaaS).

[0085] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing processing device or mobile device.

[0086] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0087] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining the digits. Although the numerical domains and parameters used to confirm the breadth of the range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0088] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification is hereby incorporated by reference in its entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0089] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A business risk identification method based on container shipping documents, characterized in that: The method comprises: Acquire document information to be checked related to the target container, wherein the document information to be checked is obtained by identifying at least one document related to the target container and arranging the documents in a preset order; Performing feature extraction processing on the status information and / or content information of each sub-item in the document information to be verified to obtain an initial feature vector; Performing deep feature mining at multiple different levels on the initial feature vector to obtain multiple deep feature vectors corresponding to the document information to be verified, wherein each of the deep feature vectors is used to represent the deep features of the document information to be verified at a corresponding level; Performing feature fusion on multiple deep feature vectors corresponding to the document information to be verified to obtain a fused feature vector; Based on the fused feature vector, multiple aspects of risk identification are performed to obtain corresponding business risk identification results.

2. The business risk identification method based on container shipping documents according to claim 1 is characterized in that: The obtaining of the document information to be checked related to the target container includes: For each target document related to the target container, extract the document type information of the target document and the status information and / or content information of at least one sub-item contained in the target document by using OCR recognition technology to obtain the partial information to be verified corresponding to the target document; The status information and / or content information of at least one sub-item contained in each of the target documents is arranged according to a first preset order, and when there are multiple documents, the local information to be verified corresponding to the multiple documents are arranged according to a second preset order to obtain the document information to be verified related to the target container.

3. The business risk identification method based on container shipping documents according to claim 2 is characterized in that: The step of arranging the partial information to be checked corresponding to the plurality of documents in accordance with a second preset order to obtain the document information to be checked related to the target container includes: Sorting the documents according to their importance to determine the second preset order; According to the document type information of at least one document related to the target container, the corresponding local information to be verified is written into the corresponding position in the second preset order, and the missing data is filled with preset values ​​to obtain the document information to be verified related to the target container.

4. The business risk identification method based on container shipping documents according to claim 1 is characterized in that: The feature extraction process is performed on the status information and / or content information of each sub-item in the document information to be verified to obtain an initial feature vector, including: The status information and / or content information of each sub-item in the document information to be verified is semantically encoded through natural language processing to obtain at least one semantic vector corresponding to the document information to be verified, and the initial feature vector is obtained based on the at least one semantic vector.

5. The business risk identification method based on container shipping documents according to claim 1 is characterized in that: The performing of deep feature mining at multiple different levels on the initial feature vector to obtain multiple deep feature vectors corresponding to the document information to be verified includes: Inputting the initial feature vector into a deep feature extraction network, wherein the deep feature extraction network includes a plurality of hidden layers, each hidden layer corresponds to an activation function, and each of the hidden layers and the activation function is used to perform a level of deep feature mining on the initial feature vector; Based on the outputs of the multiple hidden layers, multiple deep feature vectors corresponding to the document information to be verified are obtained.

6. The business risk identification method based on container shipping documents according to claim 5 is characterized in that: The step of fusing the multiple deep feature vectors corresponding to the document information to be verified to obtain the fused feature vector includes: concatenating the multiple deep feature vectors to obtain the fused feature vector.

7. The method for identifying business risks based on container shipping documents according to claim 5, characterized in that: The risk identification in multiple aspects is performed based on the fused feature vector to obtain corresponding business risk identification results, including: The fused feature vectors are respectively input into a plurality of pre-trained classifiers for classification processing, and the business risk identification result is obtained based on the outputs of the plurality of classifiers; wherein each of the classifiers corresponds to one aspect of risk identification.

8. The method for identifying business risks based on container shipping documents according to claim 7, characterized in that: The multiple classifiers are trained based on the following method: Acquire a sample fusion feature vector obtained by processing at least one sample document related to the sample case, and a plurality of risk labels corresponding to the sample fusion feature vector, wherein each of the plurality of risk labels is used as an expected output of a classifier; Inputting the sample fusion feature vector into the multiple classifiers respectively to obtain the prediction output corresponding to each classifier; Determine a loss value for each classifier based on a difference between a predicted output and an expected output corresponding to each of the classifiers; The multiple classifiers are iteratively optimized based on the loss values ​​until the multiple trained classifiers are obtained when preset training conditions are met.

9. The business risk identification method based on container shipping documents according to claim 8 is characterized in that: Before inputting the sample fusion feature vectors into the multiple classifiers respectively to obtain the prediction output corresponding to each classifier, the method further includes: For each of the classifiers, the sample fusion feature vector is attention-encoded by an attention mechanism to obtain an attention fusion vector corresponding to each classifier; The attention fusion vector is input as the input data of the classifier into the corresponding classifier for processing to obtain the corresponding prediction output of each classifier.

10. A business risk identification system based on container shipping documents, characterized in that: The system comprises: An acquisition module, used for acquiring document information to be checked related to a target container, wherein the document information to be checked is obtained by identifying at least one document related to the target container and arranging the documents in a preset order; An initial feature vector determination module is used to perform feature extraction processing on the status information and / or content information of each sub-item in the document information to be verified to obtain an initial feature vector; A deep feature vector determination module is used to perform deep feature mining at multiple different levels on the initial feature vector to obtain multiple deep feature vectors corresponding to the document information to be verified, wherein each of the deep feature vectors is used to represent the deep features of the document information to be verified at a corresponding level; A fusion feature vector determination module is used to perform feature fusion on multiple deep feature vectors corresponding to the document information to be verified to obtain a fusion feature vector; The business risk identification module is used to perform risk identification in multiple aspects based on the fused feature vector to obtain corresponding business risk identification results.

Images