Transaction information checking method, device, equipment, medium and program product

Abstract

The invention provides a transaction information checking method which can be applied to the field of artificial intelligence and the technical field of financial science and technology. The transaction information checking method comprises the following steps: determining transaction entrustment information, wherein the transaction entrustment information represents a transaction instruction of a user to a transaction executor based on a transaction intention; and a pre-trained transaction information extraction model is adopted to perform information extraction on the transaction entrustment information to obtain a plurality of transaction elements, and the pre-trained transaction information extraction model is determined based on the specific lexicon and the word segmentation model. And obtaining transaction flow details corresponding to the transaction indication. And matching the plurality of transaction elements with the transaction flow details so as to check the transaction information. The invention further provides a transaction information checking device and equipment, a storage medium and a program product.

Description

Technical Field

[0001] The present disclosure relates to the fields of artificial intelligence and financial technology, specifically to the automated processing of information, and more specifically to a transaction information verification method, device, equipment, medium and program product. Background Art

[0002] In order to effectively prevent and control the risk of transaction errors, risk management personnel need to regularly review the transaction confirmations submitted by customers and the actual transaction content to verify whether the transaction elements are consistent.

[0003] At present, when it comes to external cooperation, there are still many businesses or scenarios in which transaction confirmation letters are not generated by the transaction system. This requires manual entry of transaction element information in the transaction confirmation letter. Therefore, the existing technical solutions cannot achieve automated review, and the digital level of risk monitoring needs to be improved urgently. Summary of the invention

[0004] In view of the above problems, embodiments of the present disclosure provide a transaction information verification method, apparatus, device, medium and program product for improving the efficiency of transaction information verification.

[0005] According to a first aspect of the present disclosure, a transaction information verification method is provided, comprising: determining transaction entrustment information, wherein the transaction entrustment information represents a transaction instruction from a user to a transaction executor based on a transaction intention. Using a pre-trained transaction information extraction model to extract information from the transaction entrustment information to obtain multiple transaction elements, wherein the pre-trained transaction information extraction model is determined based on a specific vocabulary and a word segmentation model. Obtaining transaction flow details corresponding to the transaction instruction. Matching multiple transaction elements with the transaction flow details to achieve transaction information verification.

[0006] According to an embodiment of the present disclosure, the transaction entrustment information is text information, and a pre-trained transaction information extraction model is used to extract information from the transaction entrustment information to obtain multiple transaction elements, including: comparing the text information with a specific vocabulary to determine at least one target word, the target word represents a unified expression of each word in the text information and the corresponding word in the specific vocabulary. Use at least one target word to replace the corresponding word in the text information to obtain target text information. Use the pre-trained transaction information extraction model to extract information from the target text information to obtain multiple transaction elements.

[0007] According to an embodiment of the present disclosure, before extracting information from the target text information using a pre-trained transaction information extraction model, the method further includes: determining multiple transaction directions in the text information or the target text information, the transaction directions representing the buying and selling relationship between the user and the relevant transaction object. If the multiple transaction directions are different, unify the multiple transaction directions.

[0008] According to an embodiment of the present disclosure, before extracting information from the target text information using a pre-trained transaction information extraction model, the method further includes any one of the following: determining first user rejection information in the text information. Removing text information corresponding to the first user rejection information. Determining second user rejection information in the target text information. Removing text information corresponding to the second user rejection information.

[0009] According to an embodiment of the present disclosure, determining transaction entrustment information includes: obtaining initial transaction entrustment information, the initial transaction entrustment information including at least one of text data, image data, audio data and video data, and performing text extraction or recognition on the initial transaction entrustment information to obtain text information.

[0010] According to an embodiment of the present disclosure, the transaction flow details are structured data, and the multiple transaction elements include at least one of a transaction exchange rate, a currency pair, a transaction amount, a transaction direction, a value date, a transaction counterparty, and a settlement path.

[0011] According to an embodiment of the present disclosure, the transaction information verification method further includes: in the case where multiple transaction elements and transaction flow details do not match each other, determining inconsistent transaction elements and related words in the transaction flow details corresponding to the inconsistent transaction elements, and updating a specific word library based on the inconsistent transaction elements and related words.

[0012] According to an embodiment of the present disclosure, the transaction information verification method further includes: obtaining the user's authorization to determine the transaction entrustment information. After obtaining the user's authorization to determine the transaction entrustment information, the transaction entrustment information is determined.

[0013] The second aspect of the present disclosure provides a transaction information verification device, including: a determination module, used to determine transaction entrustment information, the transaction entrustment information represents the transaction instructions of the user to the transaction executor based on the transaction intention. An extraction module, used to extract information from the transaction entrustment information using a pre-trained transaction information extraction model to obtain multiple transaction elements, the pre-trained transaction information extraction model is determined based on a specific vocabulary and a word segmentation model. An acquisition module, used to obtain transaction flow details corresponding to the transaction instruction. A matching module, used to match multiple transaction elements and transaction flow details to realize transaction information verification.

[0014] The third aspect of the present disclosure provides an electronic device, comprising: one or more processors; a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the transaction information verification method.

[0015] The fourth aspect of the present disclosure further provides a computer-readable storage medium having a computer program or instruction stored thereon, which implements the steps of the transaction information verification method when the computer program or instruction is executed by a processor.

[0016] The fifth aspect of the present disclosure also provides a computer program product, including a computer program or instructions, which implement the steps of the transaction information verification method when executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The above contents and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0018] Figure 1 The application scenario diagram of the transaction information verification method, device, equipment, medium and program product according to the embodiment of the present disclosure is schematically shown; Figure 2 A flowchart of a transaction information verification method according to an embodiment of the present disclosure is schematically shown; Figure 3 A flowchart of a method for acquiring multiple transaction elements according to an embodiment of the present disclosure is schematically shown; Figure 4 A flowchart of a method for acquiring multiple transaction elements according to another embodiment of the present disclosure is schematically shown; Figure 5 A flowchart of a method for obtaining multiple transaction elements according to another embodiment of the present disclosure is schematically shown; Figure 6 A schematic diagram of a structure of a transaction information checking device according to an embodiment of the present disclosure is shown; and Figure 7 A block diagram of an electronic device suitable for implementing a transaction information verification method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0019] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0020] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0021] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0022] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0023] The embodiments of the present disclosure provide a transaction information verification method, device, equipment, medium and program product, which can be used in the field of financial technology or other fields. It should be noted that the transaction information verification method, device, equipment, medium and program product disclosed in the present disclosure can be used in the field of financial technology, and can also be used in any field other than the field of financial technology, and the application field of the transaction information verification method, device, equipment, medium and program product disclosed in the present disclosure is not limited.

[0024] In the technical solution of the present disclosure, the user information (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0025] In the scenario of using personal information for automated decision-making, the methods, devices, and systems provided by the embodiments of the present disclosure provide users with corresponding operation portals for users to choose to agree or reject the automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered. The expression "automated decision-making" here refers to the activity of automatically analyzing and evaluating a person's behavioral habits, interests and hobbies, or economic, health, credit status, etc. through computer programs, and making decisions. The expression "expert decision-making" here refers to the activity of making decisions by people who specialize in a certain field, have specialized experience, knowledge and skills, and have reached a certain level of professionalism.

[0026] The embodiments of the present disclosure provide a transaction information verification method, including: determining transaction entrustment information, where the transaction entrustment information represents the transaction instructions of the user to the transaction executor based on the transaction intention. Using a pre-trained transaction information extraction model to extract information from the transaction entrustment information to obtain multiple transaction elements, the pre-trained transaction information extraction model is determined based on a specific vocabulary and a word segmentation model. Obtaining transaction flow details corresponding to the transaction instructions. Matching multiple transaction elements and transaction flow details to achieve transaction information verification. The method of the present disclosure extracts transaction elements from the user's entrustment information (such as a transaction confirmation) using a transaction information extraction model optimized based on a specific vocabulary, and compares it with the actual transaction flow, thereby achieving automated and efficient verification of transaction information while ensuring accuracy.

[0027] Figure 1 The application scenario diagram of the transaction information verification method, device, equipment, medium and program product according to the embodiments of the present disclosure is schematically shown.

[0028] like Figure 1 As shown, the application scenario 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the first terminal device 101, the second terminal device 102, the third terminal device 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0029] The user can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only for example).

[0030] The first terminal device 101, the second terminal device 102, and the third terminal device 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0031] The server 105 may be a server that provides various services, such as a background management server (only as an example) that provides support for websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0032] It should be noted that the transaction information verification method provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the transaction information verification device provided in the embodiment of the present disclosure can generally be set in the server 105. The transaction information verification method provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Accordingly, the transaction information verification device provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105.

[0033] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0034] The following will be based on Figure 1 The scene described by Figure 2~Figure 5 The transaction information verification method of the disclosed embodiment is described in detail.

[0035] Figure 2 The flowchart of the transaction information verification method according to the embodiment of the present disclosure is schematically shown.

[0036] According to the embodiments of the present disclosure, Figure 2 As shown, the transaction information verification method of this embodiment includes, for example, operations S210 to S240, and the method can be executed by a computer program on corresponding computer hardware.

[0037] In operation S210 , transaction entrustment information is determined, where the transaction entrustment information represents a transaction instruction from a user to a transaction executor based on a transaction intention.

[0038] This step involves receiving and confirming the transaction instructions issued by the user to the transaction execution party (such as a bank, securities company, etc.) based on his or her transaction intention. The transaction entrustment information usually includes key information such as the user's transaction request, transaction type, transaction object, and transaction amount.

[0039] In operation S220, a pre-trained transaction information extraction model is used to extract information from the transaction entrustment information to obtain a plurality of transaction elements. The pre-trained transaction information extraction model is determined based on a specific vocabulary and a word segmentation model.

[0040] Using a transaction information extraction model that has been trained with a large amount of transaction data, the transaction entrustment information determined in the first step is deeply analyzed to extract multiple transaction elements. These transaction elements may include the names of the transaction parties, transaction time, transaction amount, transaction type, etc.

[0041] The pre-trained transaction information extraction model is determined based on a specific vocabulary and word segmentation model, and can accurately identify and extract key information in transaction entrustment information.

[0042] For example, a specific vocabulary is a collection of professional terms related to transaction information. These terms have specific meanings and usages in the transaction field. A specific vocabulary may include the following categories:

[0043] Transaction type words, such as "buy", "sell", "redemption", "subscription", etc., are used to describe the type of transaction. Financial product words, such as "stocks", "bonds", "funds", "futures", etc., are used to describe the objects of the transaction. Transaction parties words, such as "buyer", "seller", "investor", "issuer", etc., are used to describe the parties in the transaction. Transaction attribute words, such as "price", "quantity", "amount", "time", etc., are used to describe the specific attributes of the transaction.

[0044] These words are usually extracted from transaction-related text data. Through statistics and analysis, it is possible to determine which words have a higher frequency of occurrence and importance in transaction information, and thus include them in a specific vocabulary.

[0045] For example, the word segmentation model is the process of segmenting a continuous text string into independent vocabulary units. In transaction information extraction, the word segmentation model is usually used to segment transaction order information into smaller vocabulary units for subsequent information extraction and matching.

[0046] The word segmentation model can adopt a variety of methods, such as rule-based methods, statistical methods, deep learning-based methods, etc. Among them, deep learning-based methods (such as long short-term memory neural network LSTM) have achieved remarkable results in recent years and can more accurately identify word boundaries and semantic information.

[0047] In the extraction of transaction information, the word segmentation model needs to be trained and optimized for the specific vocabulary and grammatical rules in the transaction field. This usually requires the use of a large amount of transaction text data as training corpus, and through iterative training and adjustment of model parameters, the accuracy and generalization ability of the word segmentation model can be improved.

[0048] In operation S230, the transaction flow details corresponding to the transaction instruction are obtained.

[0049] Retrieve transaction details that match the transaction instructions issued by the user from the transaction execution party's system. Transaction details are the details of each transaction recorded by the transaction execution party, including the account information of both parties to the transaction, transaction time, transaction amount, etc.

[0050] In operation S240, a plurality of transaction elements and transaction flow details are matched to verify the transaction information.

[0051] The extracted transaction elements are compared with the acquired transaction flow details one by one to confirm whether the information between the two is consistent. This step is an important step in realizing transaction information verification, which aims to ensure that the transaction entrustment information is consistent with the records of the transaction executor, so as to avoid transaction errors or fraud.

[0052] The following is a more detailed example to illustrate the above transaction information verification method:

[0053] Suppose a user wants to trade stocks through a securities company. He submits a transaction order to the securities company, hoping to buy 1,000 shares of a certain stock at a price of 10 yuan per share.

[0054] The securities company receives the user's transaction entrustment information, which describes the user's transaction intention in detail, including the transaction type (buying stocks), transaction object (a certain stock), transaction price (10 yuan per share) and transaction quantity (1,000 shares).

[0055] Securities companies use pre-trained transaction information extraction models to conduct in-depth analysis of users' transaction entrustment information. Based on a specific financial vocabulary and word segmentation model, the model can accurately identify and extract key elements in transaction entrustment information, such as the transaction parties (users and securities companies), transaction time (the time when the entrustment is submitted), transaction amount (10,000 yuan, i.e. 10 yuan / share × 1,000 shares) and transaction type (purchase).

[0056] Based on the user's transaction entrustment information, the securities company retrieves the transaction flow details that match the user's transaction instructions in its trading system. The details record the execution of the user's transaction request in detail, including the account information of both parties to the transaction (the user's securities account and the securities company's capital account), transaction time (the time when the transaction was executed), transaction amount (10,000 yuan) and transaction quantity (1,000 shares).

[0057] The securities company compares the extracted transaction elements (such as the transaction parties, transaction time, transaction amount and transaction type) with the information in the transaction flow details one by one. In this example, the transaction elements are completely consistent with the information in the transaction flow details, including the information of the transaction parties, transaction amount, transaction quantity and transaction type. This shows that the user's transaction entrustment information has been correctly executed and the transaction information has been verified to be correct.

[0058] This embodiment achieves accurate verification of transaction information by determining transaction entrustment information, extracting information using a pre-trained transaction information extraction model, obtaining transaction flow details, and matching transaction elements with transaction flow details. This method can ensure the accuracy and completeness of transaction information, automatically and efficiently verify transaction information, and improve the security and reliability of transactions.

[0059] In operation S210, user information is obtained.

[0060] In an embodiment of the present disclosure, before obtaining the user's information, the user's consent or authorization may be obtained. For example, before operation S210, a request to obtain the user's information may be issued to the user. When the user agrees or authorizes that the user's information may be obtained, the operation S210 is performed.

[0061] In operation S220, the user information is used to perform subsequent action execution processing to implement terminal operations or information acquisition.

[0062] In the embodiments of the present disclosure, a corresponding operation entry may be provided for the user to choose to agree or reject the automated decision result. That is, before the user information is processed for subsequent action execution, the user's instruction to agree or reject the processing input through the corresponding operation entry may be obtained. If the user agrees to the processing, the user information is processed for subsequent action execution, that is, step S220 is executed. If the user refuses to perform the processing, the expert decision process is entered.

[0063] Figure 3 A flowchart of a method for obtaining multiple transaction elements according to an embodiment of the present disclosure is schematically shown. Figure 2 In addition to the operations S210 to S240 described above, the operations S321 to S323 are also included. For the sake of brevity, the description of operations S210 to S240 is omitted here, and the subsequent related method embodiments are similar and will not be repeated.

[0064] According to an embodiment of the present disclosure, the transaction entrustment information is text information, such as Figure 3As shown, for example, through operations S321 to S323, a pre-trained transaction information extraction model is used to extract information from the transaction entrustment information to obtain multiple transaction elements.

[0065] In operation S321 , the text information is compared with a specific vocabulary to determine at least one target word, where the target word represents a unified expression of each word in the text information and a corresponding word in the specific vocabulary.

[0066] In operation S322, at least one target word is used to replace a corresponding word in the text information to obtain target text information.

[0067] In operation S323, a pre-trained transaction information extraction model is used to extract information from the target text information to obtain a plurality of transaction elements.

[0068] In some embodiments, the text information can be compared with a specific word library to determine the target word, and the corresponding word in the text information can be replaced to obtain more accurate transaction elements.

[0069] For example, a user submits a transaction order through an online trading platform. The information is in text format and describes the user's intention to buy a company's stock. Since the text information may contain non-standardized words or expressions, it is necessary to improve the accuracy of information extraction by unifying the target words.

[0070] For example, the user's transaction entrustment information is: "I want to buy 100 shares of ABC company's stock, each share price is 20 yuan."

[0071] Specific terms include standard terms and expressions related to transactions. In this example, the specific terms may include the following terms: Transaction type, such as buy, sell, transfer, etc. Stock unit, such as share, share, share, etc. Currency type, such as currency A, currency B, currency C, etc. Company name, such as ABC Company, XYZ Group, etc. (assuming these companies are registered in the terminology).

[0072] By comparing the text information with a specific vocabulary, it can be found that "I want" in the text is a non-standardized expression and should be standardized as "trading intention"; "company" in "ABC company's stock" can be unified as "enterprise" or remain as it is (depending on the specific provisions of the vocabulary). However, in this example, the main focus is on unifying the expression of transaction types and stock units.

[0073] According to the comparison results, the following target words are determined: "purchase" corresponds to "transaction type: purchase" in the specific vocabulary, and "share" corresponds to "stock unit: share" in the specific vocabulary.

[0074] The corresponding words in the text information are replaced to obtain the target text information: "Transaction intention: Purchase 100 stock units: shares of ABC enterprise stock, with a price of 20 currency units: yuan per share."

[0075] It should be noted that in actual operation, it may not be necessary to replace all words with standard expressions in the word library, but to replace part of them according to the needs of the information extraction model. In addition, in order to maintain the fluency of the text, the above replaced text information may need to be appropriately adjusted, such as removing redundant words or adjusting the word order.

[0076] The adjusted target text information is input into the pre-trained transaction information extraction model. The model extracts multiple transaction elements based on the target word and context information, such as transaction type: purchase. Transaction quantity: 100 shares. Transaction object: ABC company stock. Transaction price: 20 yuan / share.

[0077] For example, a user might use a non-standard expression: "I want to buy 100 lots of XYZ Group stock."

[0078] The corresponding standardized expression (after the target word is replaced) can be: "Trading intention: Buy 100 lots of stock units: XYZ enterprise stock." (Here, "lot" as a stock unit may not be a standard expression, depending on the definition of the vocabulary. If there is no "lot" as a stock unit in the vocabulary, it may need to be converted into a standard unit, such as "share".)

[0079] This embodiment can improve the accuracy and generalization ability of the transaction information extraction model by unifying the target word method, so that it can more accurately identify and process transaction entrustment information in different formats and expressions.

[0080] Figure 4 A flowchart of a method for acquiring multiple transaction elements according to another embodiment of the present disclosure is schematically shown.

[0081] According to an embodiment of the present disclosure, before extracting information from target text information using a pre-trained transaction information extraction model, Figure 4 As shown, the transaction information verification method also includes, for example, operations S421 to S422.

[0082] In operation S421, multiple transaction directions in the text information or the target text information are determined, and the transaction directions represent the buying and selling relationship between the user and the relevant transaction object.

[0083] In operation S422, when the multiple transaction directions are different, the multiple transaction directions are unified.

[0084] In some embodiments, multiple transaction directions that may exist in text information are further considered, and a method for unifying transaction directions is proposed to more accurately extract transaction elements.

[0085] For example, a user submits a transaction order through a foreign exchange trading platform, which describes the user's intention to buy or sell foreign exchange and includes multiple transaction directions.

[0086] For example, the user's transaction entrustment information is: "I want to use 1000 currency A to buy currency B at an exchange rate of 6.5, or use currency B to sell currency A at an exchange rate of 1 / 6.5."

[0087] Compare the text information with a specific vocabulary, determine the target word, and replace it to obtain the target text information (this step is omitted in this example, the focus is on unifying the transaction direction).

[0088] Analyze the target text information (or original text information) to determine the multiple transaction directions therein: for example, in the buy direction, use 1000 currency A to buy currency B. In the sell direction, use currency B to sell currency A.

[0089] In this example, the transaction direction is unified as a buy expression. To do this, the sell direction needs to be converted so that it is expressed in the opposite direction of the buy. The specific method is as follows:

[0090] The buying direction remains unchanged: use 1000 currency A to buy currency B at an exchange rate of 6.5.

[0091] The selling direction is converted to the buying direction: that is, selling currency A with currency B (calculated at the reverse of the exchange rate of 6.5, i.e. 1 / 6.5) is converted to buying currency B with currency A at the exchange rate of 6.5.

[0092] The adjusted target text information (or text information containing only the buy direction) is input into the pre-trained transaction information extraction model. The model extracts multiple transaction elements based on the unified transaction direction and context information. Transaction type: buy (unified expression). Transaction object: currency A and currency B. Transaction quantity: 1000 currency A (buy direction). Transaction exchange rate: 6.5 (buy direction).

[0093] This embodiment can simplify the processing of transaction information by unifying the transaction direction, and make the extraction of transaction elements more accurate and consistent. At the same time, this also facilitates subsequent transaction analysis and risk management.

[0094] Figure 5 A flowchart of a method for acquiring multiple transaction elements according to yet another embodiment of the present disclosure is schematically shown.

[0095] According to an embodiment of the present disclosure, before extracting information from target text information using a pre-trained transaction information extraction model, Figure 5 As shown, the transaction information verification method, for example, also includes any one of operations S521 to S524.

[0096] In operation S521, first user rejection information in the text information is determined.

[0097] In operation S522, text information corresponding to the first user rejection information is removed.

[0098] In operation S523, second user rejection information in the target text information is determined.

[0099] In operation S524, text information corresponding to the second user rejection information is removed.

[0100] In some embodiments, a step of processing user rejection information is introduced to further improve the accuracy of transaction information extraction and user satisfaction.

[0101] For example, a user submits a shopping list through an e-commerce platform. The list contains multiple items and corresponding purchase information, but it also contains information about some items that the user later decides not to purchase (i.e., user rejection information).

[0102] The shopping list text information submitted by the user is, for example: "I want to buy a laptop, a mobile phone and a pair of headphones. However, I decided not to buy headphones because the budget is not enough. Therefore, the final shopping list is a laptop and a mobile phone."

[0103] Analyze the target text information to determine the user rejection information therein. In this example, the user clearly stated "I decided not to buy headphones", which is the first user rejection information.

[0104] According to the first user rejection information, the commodity information corresponding to the text information and which the user decides not to buy is removed. In this example, the commodity information of "headphones" is removed.

[0105] Then, the text information after removing the user rejection information is compared with the specific vocabulary to determine the target words (such as product name, purchase quantity, etc.), and corresponding replacement or standardization processing is performed to obtain the target text information.

[0106] It is understandable that the user may also remove the user rejection information from the target text information after obtaining the target text information.

[0107] The target text information after removing the user rejection information is input into the pre-trained transaction information extraction model. The model extracts multiple transaction elements based on the context information, such as transaction type: purchase. Transaction object: laptop, mobile phone (headphones removed). Transaction quantity: not explicitly mentioned (users can be further asked or default values ​​can be set based on actual needs). Other transaction elements: can be further extracted based on specific needs, such as product price, purchase time, etc.

[0108] This embodiment introduces a step for processing user rejection information, so as to more accurately extract information about commodities that the user actually wants to purchase, thereby improving the accuracy of transaction information extraction and user satisfaction.

[0109] According to an embodiment of the present disclosure, determining the transaction entrustment information includes, for example: obtaining initial transaction entrustment information, the initial transaction entrustment information including at least one of text data, image data, audio data and video data, and performing text extraction or recognition on the initial transaction entrustment information to obtain text information.

[0110] In some embodiments, the acquisition and recognition technologies of various data types (multimodal data such as text data, image data, audio data and video data) and efficient text extraction and parsing processes are combined to ensure the accuracy and completeness of transaction entrustment information.

[0111] For example, initial transaction entrustment information including at least one of text data, image data, audio data and video data may be obtained through various channels and methods, such as user input, document scanning, audio or video recording, etc.

[0112] The initial transaction entrustment information can also be pre-processed, including denoising, format conversion, etc., to ensure the accuracy of subsequent processing.

[0113] The initial transaction entrustment information is classified into text, picture, audio and video categories according to the data type.

[0114] For text data, text parsing and extraction are performed directly.

[0115] For image data, for example, OCR (optical character recognition) technology is used to convert the text in the image into text information.

[0116] For audio data, speech recognition technology is used to convert the speech in the audio into text information.

[0117] For video data, you can first extract video frames, and then perform OCR or speech recognition processing on each frame to obtain the text information in the video.

[0118] Parse the extracted text information to identify key information, such as transaction type, stock code, entrustment price, entrustment quantity, etc.

[0119] Verify the parsed key information to ensure its accuracy and compliance. For example, verify whether the commissioned price is within the price limit range, whether the commissioned quantity is an integer multiple, etc.

[0120] Integrate the parsed and verified transaction entrustment information into a standardized transaction entrustment data format.

[0121] Output the integrated transaction entrustment data for use by the subsequent transaction processing system.

[0122] This embodiment combines multiple data types and recognition technologies to more comprehensively acquire and parse transaction entrustment information, thereby improving the efficiency and accuracy of transaction processing.

[0123] According to an embodiment of the present disclosure, the transaction flow details are structured data, and the multiple transaction elements include at least one of a transaction exchange rate, a currency pair, a transaction amount, a transaction direction, a value date, a transaction counterparty, and a settlement path.

[0124] In some embodiments, by comparing multiple transaction elements in the transaction flow details, including transaction exchange rate, currency pair, transaction amount, transaction direction, interest value date, counterparty and settlement path, the accuracy and consistency of relevant transaction information can be ensured.

[0125] For example, obtain transaction details from a bank or trading platform to ensure that the data is complete and in a standardized format.

[0126] The transaction flow details should be structured data, including key elements such as transaction exchange rate, currency pair, transaction amount, transaction direction, value date, counterparty and settlement path.

[0127] Compare the transaction elements extracted from the transaction entrustment information with the information in the transaction flow details one by one. For example, check whether the transaction exchange rate is consistent with the user's instructions (if the user has previously instructed to trade at a specific exchange rate). Check whether the transaction currency pair is consistent with the business requirements and whether there is a mismatch. Check whether the transaction amount is accurate and whether there is any omission or over-recording. Check whether the transaction direction is correct, that is, whether the buy or sell is consistent with the actual transaction. Check whether the interest date is accurate and whether there is any delay or advance. Check whether the counterparty is legal and compliant and whether there is any false counterparty. Check whether the clearing path is clear and accurate and whether there is any abnormal clearing path, etc.

[0128] The verification results shall be output in the form of a report or table, clearly listing the transaction information that has passed the verification and the transaction information with differences.

[0129] This embodiment can comprehensively and accurately discover differences and errors in transaction information by checking multiple transaction elements in the transaction flow details one by one, thereby improving the accuracy and consistency of transaction information.

[0130] According to an embodiment of the present disclosure, the transaction information verification method further includes, for example, determining the inconsistent transaction elements and the related words in the transaction flow details corresponding to the inconsistent transaction elements when multiple transaction elements and transaction flow details are inconsistent. The specific word library is updated based on the inconsistent transaction elements and the related words.

[0131] In some embodiments, a processing mechanism is further introduced in the event of verification inconsistencies, that is, when multiple transaction elements and transaction flow details do not match each other, the inconsistent transaction elements are determined, and a specific vocabulary is updated based on these inconsistent transaction elements to improve the accuracy of future transaction information extraction.

[0132] For example, the extracted transaction elements are compared with the information in the transaction flow details to verify the accuracy and completeness of the transaction.

[0133] During the matching process, if it is found that the transaction elements are inconsistent with the information in the transaction flow details, first determine which transaction elements are inconsistent.

[0134] For inconsistent transaction elements, relevant words or phrases are extracted from the transaction flow details. These words or phrases may not completely match the words in the specific vocabulary, resulting in information extraction errors.

[0135] Based on inconsistent transaction elements and related words, specific word libraries are updated. This includes adding new words, modifying the weights or word segmentation rules of existing words, to improve the accuracy of the model in extracting future transaction information.

[0136] Then use the updated specific vocabulary and word segmentation model to re-extract the transaction entrustment information and match and check it with the transaction flow details again to ensure the accuracy and consistency of all transaction information.

[0137] By introducing a processing mechanism in the event of inconsistency, this embodiment not only improves the accuracy of transaction information verification, but also improves the adaptability and accuracy of the transaction information extraction model by continuously updating the specific word library. This method helps to reduce transaction risks caused by information extraction errors and improve the efficiency and reliability of transaction processing.

[0138] According to an embodiment of the present disclosure, the transaction information verification method further includes, for example: obtaining the user's authorization to determine the transaction entrustment information. After obtaining the user's authorization to determine the transaction entrustment information, the transaction entrustment information is determined.

[0139] In some embodiments, before extracting transaction elements, it is critical to ensure compliance and user privacy protection when obtaining user data from multiple platforms. The following is an example that combines "obtaining user authorization to obtain user data" and "obtaining user data after obtaining user authorization" to illustrate how to obtain user data legally and in compliance with regulations.

[0140] Obtaining the user's authorization to obtain user data includes, for example:

[0141] Clearly inform users of data usage:

[0142] Purpose: To ensure that users understand why their data is needed and how it will be used.

[0143] Example: In the privacy policy or user agreement of the application, clearly state that you plan to obtain user data from multiple platforms (such as social media, e-commerce platforms, etc.) in order to provide personalized services. At the same time, explain how this data will be processed, stored, and protected.

[0144] Request user authorization:

[0145] Purpose: To gain access to and obtain data from users with their explicit consent.

[0146] Example: During the registration or setup process of an application, provide an explicit authorization request. The user can choose to accept or deny. If the user chooses to accept, they will be asked to log in to the corresponding platform so that the application can access the data.

[0147] Verify user authorization:

[0148] Purpose: To ensure that the authorization request is made by the real user and that they actually agree to share their data.

[0149] Example: After receiving user authorization, the application can use relevant authentication protocols to verify the user's identity and authorization status. This ensures that only authorized user data is obtained.

[0150] After obtaining user authorization, obtaining user data includes, for example:

[0151] Securely access user data:

[0152] Purpose: To ensure that best security practices are followed when obtaining user data to protect the security and privacy of user data.

[0153] Example: Use secure API calls and encryption technologies (such as HTTPS) to obtain data from user-authorized platforms. At the same time, ensure that the server side of the application also adopts appropriate security measures (such as firewalls, data encryption, etc.).

[0154] Aggregate and store user data:

[0155] Purpose: To integrate user data obtained from different platforms into a unified database for subsequent processing.

[0156] Example: Set up a database on the application's server to store aggregated user data. This data can be indexed by user ID or other unique identifier for later retrieval and use.

[0157] Comply with data protection and privacy regulations:

[0158] Purpose: To ensure compliance with relevant data protection and privacy regulations when processing user data.

[0159] Example: Ensure that the application complies with relevant regulatory requirements. This may include limiting the storage time of data, providing users with the right to access and delete data, etc.

[0160] Through the above steps, user data can be obtained legally and compliantly, providing the necessary data basis for subsequent processing. At the same time, this also helps to maintain user trust and privacy rights.

[0161] Based on the above transaction information verification method, the present disclosure also provides a transaction information verification device. Figure 6 The transaction information checking device is described in detail.

[0162] Figure 6 The structural block diagram of the transaction information verification device according to the embodiment of the present disclosure is schematically shown.

[0163] like Figure 6 As shown, the transaction information checking device 600 of this embodiment includes, for example: a first determination module 610 , an extraction module 620 , a first acquisition module 630 and a matching module 640 .

[0164] The first determination module 610 is used to determine the transaction entrustment information, which represents the transaction instruction of the user to the transaction execution party based on the transaction intention. In one embodiment, the first determination module 610 can be used to perform the operation S210 described above, which will not be repeated here.

[0165] The extraction module 620 is used to extract information from the transaction entrustment information using a pre-trained transaction information extraction model to obtain multiple transaction elements. The pre-trained transaction information extraction model is determined based on a specific vocabulary and a word segmentation model. In one embodiment, the extraction module 620 can be used to perform the operation S220 described above, which will not be repeated here.

[0166] The first acquisition module 630 is used to acquire the transaction flow details corresponding to the transaction instruction. In one embodiment, the first acquisition module 630 can be used to perform the operation S230 described above, which will not be repeated here.

[0167] The matching module 640 is used to match multiple transaction elements and transaction flow details to verify the transaction information. In one embodiment, the matching module 640 can be used to perform the operation S240 described above, which will not be described in detail here.

[0168] According to an embodiment of the present disclosure, any multiple modules of the first determination module 610, the extraction module 620, the first acquisition module 630 and the matching module 640 can be combined into one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the first determination module 610, the extraction module 620, the first acquisition module 630 and the matching module 640 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware and firmware or in a suitable combination of any of them. Alternatively, at least one of the first determination module 610 , the extraction module 620 , the first acquisition module 630 , and the matching module 640 may be at least partially implemented as a computer program module, and when the computer program module is executed, a corresponding function may be performed.

[0169] According to an embodiment of the present disclosure, the extraction module 620 includes, for example, a comparison submodule, a replacement submodule, and a first extraction submodule.

[0170] The comparison submodule is used to compare the text information with the specific vocabulary to determine at least one target word, where the target word represents a unified expression of each word in the text information and the corresponding word in the specific vocabulary.

[0171] The replacement submodule is used to replace the corresponding word of the text information with at least one target word to obtain the target text information.

[0172] The first extraction submodule is used to extract information from the target text information using a pre-trained transaction information extraction model to obtain multiple transaction elements.

[0173] According to an embodiment of the present disclosure, the extraction module 620, for example, further includes a first determination submodule and a unification submodule.

[0174] The first determination submodule is used to determine multiple transaction directions in the text information or the target text information, and the transaction direction represents the buying and selling relationship between the user and the relevant transaction object.

[0175] The unification submodule is used to unify multiple transaction directions when the transaction directions are different.

[0176] According to an embodiment of the present disclosure, the extraction module 620, for example, further includes any two of a second determination submodule, a first removal submodule, a third determination submodule, and a second removal submodule.

[0177] The second determining submodule is used to determine the first user rejection information in the text information.

[0178] The first removal submodule is used to remove text information corresponding to the first user rejection information.

[0179] The third determination submodule is used to determine the second user rejection information in the target text information.

[0180] The second removal submodule is used to remove the text information corresponding to the second user rejection information.

[0181] According to an embodiment of the present disclosure, the determination module 610 includes an acquisition submodule and a second extraction submodule.

[0182] The acquisition submodule is used to acquire initial transaction entrustment information, and the initial transaction entrustment information includes at least one of text data, picture data, audio data and video data.

[0183] The second extraction submodule is used to perform text extraction or recognition on the initial transaction entrustment information to obtain text information.

[0184] According to an embodiment of the present disclosure, the transaction information checking device 600 further includes, for example, a second determination module and an update module.

[0185] The second determination module is used to determine the inconsistent transaction elements and related words in the transaction flow details corresponding to the inconsistent transaction elements when multiple transaction elements and transaction flow details do not match each other.

[0186] The updating module is used to update the specific word library based on inconsistent transaction elements and related words.

[0187] According to an embodiment of the present disclosure, the transaction information verification device, for example, further includes a second acquisition module and a third determination module.

[0188] The second acquisition module is used to obtain the user's authorization to determine the transaction entrustment information.

[0189] The third determination module is used to determine the transaction entrustment information after obtaining the user's authorization to determine the transaction entrustment information.

[0190] Figure 7 A block diagram of an electronic device suitable for implementing a transaction information verification method according to an embodiment of the present disclosure is schematically shown.

[0191] like Figure 7 As shown, the electronic device 700 according to an embodiment of the present disclosure includes a processor 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage part 708 to a random access memory (RAM) 703. The processor 701 may include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (for example, an application-specific integrated circuit (ASIC)), etc. The processor 701 may also include an onboard memory for caching purposes. The processor 701 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0192] In RAM 703, various programs and data required for the operation of electronic device 700 are stored. Processor 701, ROM 702 and RAM 703 are connected to each other via bus 704. Processor 701 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 702 and / or RAM 703. It should be noted that the program can also be stored in one or more memories other than ROM 702 and RAM 703. Processor 701 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.

[0193] According to an embodiment of the present disclosure, the electronic device 700 may further include an input / output (I / O) interface 705, which is also connected to the bus 704. The electronic device 700 may further include one or more of the following components connected to the input / output (I / O) interface 705: an input portion 706 including a keyboard, a mouse, etc.; an output portion 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 708 including a hard disk, etc.; and a communication portion 709 including a network interface card such as a LAN card, a modem, etc. The communication portion 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the input / output (I / O) interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed, so that a computer program read therefrom is installed into the storage portion 708 as needed.

[0194] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the transaction information verification method according to the embodiment of the present disclosure is implemented.

[0195] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, it may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device. For example, according to an embodiment of the present disclosure, the computer-readable storage medium may include the ROM 702 and / or RAM 703 described above and / or one or more memories other than ROM 702 and RAM 703.

[0196] The embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the transaction information verification method provided by the embodiment of the present disclosure.

[0197] The above functions defined in the system / device of the embodiment of the present disclosure are performed when the computer program is executed by the processor 701. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0198] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 709, and / or installed from the removable medium 711. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0199] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 709, and / or installed from the removable medium 711. When the computer program is executed by the processor 701, the above functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the system, device, means, module, unit, etc. described above can be implemented by a computer program module.

[0200] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0201] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0202] It will be appreciated by those skilled in the art that the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations or combinations are not explicitly described in the present disclosure. In particular, without departing from the spirit and teachings of the present disclosure, the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0203] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A transaction information verification method, characterized in that: The method comprises: Determining transaction entrustment information, wherein the transaction entrustment information represents a transaction instruction from a user to a transaction executor based on a transaction intention; Using a pre-trained transaction information extraction model to extract information from the transaction entrustment information to obtain a plurality of transaction elements, wherein the pre-trained transaction information extraction model is determined based on a specific vocabulary and a word segmentation model; Obtaining transaction details corresponding to the transaction instruction; The multiple transaction elements are matched with the transaction flow details to verify the transaction information.

2. The method according to claim 1, characterized in that The transaction entrustment information is text information. The transaction entrustment information is extracted by using a pre-trained transaction information extraction model to obtain multiple transaction elements, including: Comparing the text information with the specific vocabulary to determine at least one target word, the target word representing a unified expression of each word in the text information and a corresponding word in the specific vocabulary; Using the at least one target word to replace a corresponding word in the text information to obtain target text information; The pre-trained transaction information extraction model is used to extract information from the target text information to obtain the multiple transaction elements.

3. The method according to claim 2, characterized in that Before extracting information from the target text information using a pre-trained transaction information extraction model, the method further includes: Determining a plurality of transaction directions in the text information or the target text information, the transaction directions representing a buying and selling relationship between the user and a relevant transaction object; In the case that the multiple transaction directions are different, the multiple transaction directions are unified.

4. The method according to claim 2, characterized in that: Before extracting information from the target text information using a pre-trained transaction information extraction model, the method further includes any one of the following: Determining first user rejection information in the text message; Removing text information corresponding to the first user rejection information; Determining second user rejection information in the target text information; The text information corresponding to the second user rejection information is removed.

5. The method according to claim 2, characterized in that: The determined transaction entrustment information includes: Acquiring initial transaction entrustment information, wherein the initial transaction entrustment information includes at least one of text data, image data, audio data, and video data; Perform text extraction or recognition on the initial transaction entrustment information to obtain the text information.

6. The method according to claim 1, characterized in that The transaction flow details are structured data, and the multiple transaction elements include at least one of a transaction exchange rate, a currency pair, a transaction amount, a transaction direction, a value date, a transaction counterparty, and a settlement path.

7. The method according to claim 1, characterized in that The method further comprises: In the case where the plurality of transaction elements and the transaction flow details do not match each other, determining the inconsistent transaction elements and related words in the transaction flow details corresponding to the inconsistent transaction elements; The specific word library is updated based on the inconsistent transaction elements and the related words.

8. The method according to claim 1, characterized in that: The method further comprises: Obtaining the user's authorization to determine the transaction entrustment information; After obtaining the user's authorization to confirm the transaction entrustment information, the transaction entrustment information is confirmed.

9. A transaction information verification device, characterized in that: The device comprises: A determination module, used to determine transaction entrustment information, wherein the transaction entrustment information represents a transaction instruction from a user to a transaction executor based on a transaction intention; An extraction module, configured to extract information from the transaction entrustment information using a pre-trained transaction information extraction model to obtain a plurality of transaction elements, wherein the pre-trained transaction information extraction model is determined based on a specific vocabulary and a word segmentation model; An acquisition module, used to acquire transaction flow details corresponding to the transaction instruction; A matching module is used to match the multiple transaction elements with the transaction flow details to verify the transaction information.

10. An electronic device comprising: one or more processors; a memory for storing one or more computer programs, It is characterized in that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

12. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images