Delaration element compliance detection method and device, storage medium and electronic equipment

Abstract

The invention relates to a declaration factor compliance detection method and device, a storage medium and electronic equipment, and relates to the technical field of customs declaration, and the method comprises the steps: obtaining at least one piece of to-be-detected declaration factor data; key features are extracted from each piece of declaration element data through a preset large language model; based on each key feature corresponding to the same piece of declaration element data, matching a corresponding compliance judgment rule, and detecting whether each piece of basic element information in the corresponding declaration element data is compliant or not according to the compliance judgment rule to obtain a corresponding detection result; if the basic element information which is not compliant exists in the detection result, determining the basic element information which is not compliant as target element information, adding a corresponding target non-compliant reason, and obtaining feedback information of the terminal of the user on the target non-compliant reason; and if the feedback information is judged to be wrong, optimizing the rule matching model based on the feedback information. The method and the device have the effect of improving the efficiency of declaration element data detection.

Description

Technical Field

[0001] The present application relates to the technical field of customs declaration, and specifically to a declaration element compliance detection method, device, storage medium and electronic device. Background Art

[0002] Compliance testing of declaration elements refers to the process by which customs reviews and verifies the information of various elements provided when declaring imported and exported goods, in order to ensure the accuracy and completeness of the information and meet the requirements of customs classification, valuation, trade control, supervision, etc. In the process of international trade and customs clearance, accurately filling in and verifying the declaration elements is a key step to ensure smooth customs clearance. Through a detailed introduction and understanding of the declaration elements, enterprises can effectively improve their compliance and efficiency in customs affairs. According to customs statistics, among all the data declared and verified by customs each year, the proportion of errors in the "declaration elements" column remains high. These errors not only lead to an increase in the declaration costs of enterprises, but also increase the verification burden of customs and affect the efficiency of customs clearance. Therefore, there is an urgent need for an effective way to detect the compliance of declaration elements.

[0003] At present, the compliance check of declaration elements is usually carried out in the following way: auditors review the declaration element data one by one based on the audit rules, and finally complete the compliance check of declaration elements. However, once there are a lot of declaration element data that need to be reviewed, the manual review method is time-consuming and labor-intensive, resulting in low efficiency of compliance check of declaration elements. Summary of the invention

[0004] In order to improve the efficiency of declaration factor data detection, the present application provides a declaration factor compliance detection method, device, storage medium and electronic device.

[0005] In a first aspect of the present application, a method for compliance detection of declaration elements is provided, which specifically includes: Acquire at least one piece of declaration element data to be tested, wherein the declaration element data includes multiple basic element information; Perform semantic analysis on each basic element information in each of the declared element data through a preset large language model and extract key features; Based on the key features corresponding to the same piece of the declaration element data, the corresponding compliance determination rules are matched from the preset compliance determination rule library through the preset rule matching model, and the basic element information in the corresponding declaration element data is detected according to the compliance determination rules to obtain the corresponding detection results; If there is non-compliance of basic element information in the detection result, the non-compliant basic element information is determined as target element information and a corresponding target non-compliance reason is added, and feedback information of the user's terminal on the target non-compliance reason is obtained; If the feedback information is a judgment error, the rule matching model is optimized based on the feedback information.

[0006] By adopting the above technical solution, the basic element information in each declaration element data is semantically analyzed through a large language model, so as to extract the key features that can accurately characterize the corresponding basic element information. Further, the key features corresponding to the same declaration element data are input into the rule matching model, and the rule matching model automatically matches the corresponding compliance determination rules for the declaration element data, avoiding manual matching of compliance determination rules. Then, the compliance of the corresponding declaration element data is detected through the compliance determination rules to obtain the corresponding detection results. If the detection results show that the basic element information is non-compliant, the corresponding target non-compliance reasons are added. If the feedback information sent by the terminal is a judgment error, there may be inaccurate matching of the compliance determination rules. Based on this feedback information, the rule matching model is optimized so that the rule matching model can learn autonomously, improve the accuracy of the compliance determination rule matching, avoid multiple re-matching rules, and affect the detection progress of the declaration element data, thereby improving the efficiency of the declaration element data detection.

[0007] Optionally, if the feedback information is a judgment error, optimizing the rule matching model based on the target element information specifically includes: If the feedback information is a judgment error, the declared element data where the target element information is located is determined as the target declared element data, and the associated element information of the target element information is determined from the target declared element data; Counting a first number of non-compliant association factor information in each of the association factor information, and if the first number exceeds a preset first number threshold, obtaining a rule selection instruction sent by the terminal; According to the rule selection instruction, the corresponding optimal judgment rule is selected from the compliance judgment rule library, the compliance judgment rule corresponding to the target declaration element data is replaced with the optimal judgment rule, and the key features corresponding to the target declaration element data and the optimal judgment rule are input into the rule matching model for learning and optimization.

[0008] By adopting the above technical solution, if the feedback information is a judgment error, it means that the compliance judgment rule corresponding to the target declaration element data where the target element information is located is poorly matched with this target declaration element data, resulting in a deviation in the non-compliance judgment. If the first number exceeds the preset first number threshold, it means that more of the basic element information associated with the target element information is judged to be non-compliant, then it is determined that this target declaration element data does not match the corresponding compliance judgment rule. Further, the optimal judgment rule that matches the target declaration element data is re-determined, and at the same time, the key features and the optimal judgment rules corresponding to this target declaration element data are input into the rule matching model for training to optimize the model performance, so that the rule matching model matches the corresponding compliance judgment rules according to the key features with higher accuracy.

[0009] Optionally, the method further includes: When the compliance determination of the target declared element data is completed based on the optimal determination rule, determining whether the target element information is compliant; If the target element information is non-compliant, obtaining non-compliant feedback sent by the terminal, and when the non-compliant feedback indicates that the non-compliant determination of the target element information is correct and the non-compliant cause is wrong, determining that the target declaration element data does not match the optimal determination rule; Counting a second number of compliant association element information in each of the association element information, and if the second number exceeds a preset second number threshold, eliminating the optimal determination rule; The historical declaration element data determined to be compliant under the optimal determination rule are obtained, and compliance determination is re-performed on each of the historical declaration element data.

[0010] By adopting the above technical solution, if the non-compliance feedback is that the non-compliance judgment of the target element information is correct and the judgment of the non-compliance reason is wrong, it means that the optimal judgment rule selected by the user still does not match the target declaration element data. Furthermore, if the second number exceeds the second number threshold, it means that when the optimal judgment rule does not match, more basic element information associated with the target element information is judged to be compliant, indicating that there is a problem with this optimal judgment rule itself. In this case, this optimal judgment rule is removed from the compliance judgment rule library. At the same time, the historical declaration element data judged to be compliant under this optimal judgment rule is likely to have problems. In this way, the compliance of these historical element data is re-judged, thereby improving the accuracy of declaration element data detection.

[0011] Optionally, the method further includes: If the feedback information is judged to be correct, determining at least one element adjustment method corresponding to the target element information; Detecting an initial adjustment action of the user on the target element information, and selecting a recommended adjustment method from the element adjustment methods according to the initial adjustment action and virtually displaying the recommended adjustment method on the terminal; A selection instruction sent by the terminal is received, a recommended adjustment method corresponding to the selection instruction is determined as a target adjustment method, and a process of adjusting the target element information by the user is monitored based on the target adjustment method.

[0012] By adopting the above technical solution, if the feedback information is judged to be correct, it means that the target element information has problems reflected by the target non-compliance reasons, and the target element information needs to be adjusted and modified. Then, the element adjustment method matching the target element information is determined, and combined with the initial adjustment action, the recommended adjustment method is screened out and displayed on the terminal, so that the user can choose the appropriate target adjustment method. Based on the target adjustment method, it can not only assist the user to accurately modify the target element information, but also better monitor the user's adjustment process of the target element information to avoid deviations in the user's adjustment.

[0013] Optionally, the determining of at least one element adjustment method corresponding to the target element information specifically includes: Determine the target commodity type corresponding to the target element information; Obtaining a historical adjustment method corresponding to historical target element information in the historical declaration element data under the target commodity type, wherein the non-compliance reason of the historical target element information is the target non-compliance reason; Counting the first occurrence number of each of the historical adjustment methods, and selecting the first historical adjustment method from the historical adjustment methods in descending order of the first occurrence number and determining it as an easy-to-use adjustment method; Obtaining the historical compliance determination rule that determines compliance after the historical target element information is adjusted under each of the ease-of-use adjustment modes, counting the second number of occurrences of each of the historical compliance determination rules, and selecting the historical compliance determination rule with the second number from each of the historical compliance determination rules in descending order of the second number of occurrences and determining it as the easy-to-use compliance rule of the corresponding ease-of-use adjustment mode; The compliance determination rule corresponding to the target element information is determined as the target determination rule, and the easy-to-use adjustment method of the target determination rule in the corresponding easy-to-compliance rule is determined as the element adjustment method.

[0014] By adopting the above technical solution, the more the first occurrences, the easier it is to adopt the corresponding historical adjustment method when the historical target element information has the target non-compliance reason; the larger the second occurrences, the easier it is to determine compliance after adopting this single easy-to-use adjustment method to modify and adjust under the corresponding historical compliance judgment rule. Further, it is determined whether there is a target judgment rule in each easy-to-use compliance rule corresponding to each easy-to-use adjustment method. If so, the corresponding easy-to-use adjustment method is determined as the element adjustment method, that is, the method that can accurately modify the target element information under the target judgment rule with a high probability, so as to facilitate the subsequent determination of a reasonable adjustment method recommended to the user from the element adjustment method.

[0015] Optionally, the selecting, according to the initial adjustment action, a recommended adjustment method from the adjustment methods of each element and virtually displaying the recommended adjustment method on the terminal specifically includes: Selecting the element adjustment method including the initial adjustment action from the element adjustment methods and determining it as the recommended adjustment method; Determine a first weight for each of the recommended adjustment methods, and determine a second weight for the target determination rule corresponding to each of the recommended adjustment methods, wherein the first weight is a ratio of a first occurrence number of each of the recommended adjustment methods to a sum of first occurrence numbers of all of the easy-to-use adjustment methods, and the second weight is a ratio of a second occurrence number of the target determination rule corresponding to each of the recommended adjustment methods to a sum of second occurrence numbers of all corresponding easy-to-use rules; Calculate the weight product of the first weight of each recommended adjustment method and the second weight of the corresponding target judgment rule, and based on each weight product, display the corresponding recommended adjustment method in a virtual body at the corresponding display position of the terminal. The larger the weight product, the closer the corresponding display position is to the center of the terminal's field of view.

[0016] By adopting the above technical solution, the weight product of the first weight of each recommended adjustment method and the second weight of the corresponding target determination rule is calculated. The larger the weight product, the greater the probability of compliance under the target determination rule when the corresponding recommended adjustment method is adopted to modify the target element information. Finally, according to each weight product, the corresponding recommended adjustment method is displayed in a virtual body at the corresponding display position of the terminal. The larger the weight product, the closer the corresponding display position is to the center of the terminal's field of view, and the more it conforms to the user's field of view habits. It is not only convenient for users to adopt recommended adjustment methods that are easier to comply with, but the recommended adjustment method displayed in a virtual body can also guide users to make correct subsequent modification actions in real time, thereby improving the accuracy and efficiency of modifying the target element information.

[0017] Optionally, the method further includes: The test results of each of the declared element data are stored in a database, and a result query interface for enterprises is provided; The enterprise whose results are queried through the result query interface is determined as the target enterprise. If the current test result of the target enterprise is non-compliant, the number of test results of the target enterprise that are non-compliant within a preset time is counted; If the number of the results exceeds a preset number threshold, the test result corresponding to the target enterprise and the enterprises of the same type whose test results comply with the regulations will be sent to the terminal of the target enterprise.

[0018] By adopting the above technical solution, if the number of results exceeds the preset quantity threshold, it means that there are many non-compliant cases in the test results of the target enterprise. In this case, the test results corresponding to the target enterprise and the same type of enterprises with compliant test results will be sent to the terminal of the target enterprise, so as to encourage the target enterprise to better control the quality of the declared factor data by comparing with the peers with compliant test results.

[0019] In a second aspect of the present application, a declaration element compliance detection device is provided, specifically comprising: A data acquisition module, used to acquire at least one piece of declaration element data to be detected, wherein the declaration element data includes multiple basic element information; A feature extraction module is used to perform semantic analysis on each basic element information in each of the declared element data and extract key features through a preset large language model; An element detection module is used to match the corresponding compliance determination rules from a preset compliance determination rule library through a preset rule matching model based on the key features corresponding to the same piece of the declaration element data, and detect whether the basic element information in the corresponding declaration element data is compliant according to the compliance determination rules to obtain the corresponding detection results; An information feedback module, for determining the non-compliant basic element information as target element information and adding a corresponding target non-compliant reason if there is non-compliant basic element information in the detection result, and obtaining feedback information of the user's terminal on the target non-compliant reason; A model optimization module is used to optimize the rule matching model based on the feedback information if the feedback information is a judgment error.

[0020] By adopting the above technical solution, the data acquisition module obtains at least one declaration element data to be detected, and then the feature extraction module extracts key features from the basic element information in the declaration element data. The element detection module matches the corresponding compliance judgment rule for a single declaration element data based on the key features, and performs compliance detection to obtain the detection result. Furthermore, the information feedback module obtains the feedback information of the terminal on the cause of the target non-compliance, and finally the model optimization module optimizes the rule matching model when the feedback information is a judgment error.

[0021] In a third aspect of the present application, a computer-readable storage medium is provided, in which a computer program is stored. When the computer program is loaded and executed by a processor, the method steps described in any one of the first aspects are performed.

[0022] In a fourth aspect of the present application, an electronic device is provided, specifically comprising: A processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the processor is used to load and execute the computer program stored in the memory so that the electronic device performs the method as described in any one of the first aspects.

[0023] In summary, the present application includes at least one of the following beneficial technical effects: semantic analysis of the basic element information in each declaration element data is performed through a large language model, so as to extract key features that can accurately characterize the corresponding basic element information. Further, the key features corresponding to the same declaration element data are input into the rule matching model, and the rule matching model automatically matches the corresponding compliance determination rules for the declaration element data, avoiding manual matching of compliance determination rules. Then, the compliance of the corresponding declaration element data is detected through the compliance determination rules to obtain the corresponding detection results. If the detection results show that the basic element information is non-compliant, the corresponding target non-compliance reasons are added. If the feedback information sent by the terminal is a judgment error, there may be inaccurate matching of the compliance determination rules. Based on this feedback information, the rule matching model is optimized so that the rule matching model can learn autonomously, improve the accuracy of the compliance determination rule matching, avoid multiple re-matching rules, and affect the detection progress of the declaration element data, thereby improving the efficiency of the declaration element data detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a flowchart of a declaration element compliance detection method provided in an embodiment of the present application; Figure 2 It is a flowchart of another declaration element compliance detection method provided in an embodiment of the present application; Figure 3 It is a structural schematic diagram of a declaration element compliance detection device provided in an embodiment of the present application; Figure 4 It is a structural schematic diagram of another declaration element compliance detection device provided in an embodiment of the present application.

[0025] Explanation of the accompanying drawings: 11. Data acquisition module; 12. Feature extraction module; 13. Factor detection module; 14. Information feedback module; 15. Model optimization module; 16. Rule optimization module; 17. Adjustment recommendation module; 18. Result query module. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0027] In the description of the embodiments of the present application, words such as "illustrative", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "illustrative", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "illustrative", "for example" or "for example" is intended to present related concepts in a concrete way.

[0028] In the description of the embodiments of the present application, the term "and / or" is only a kind of association relationship describing the associated objects, indicating that there may be three kinds of relationships, for example, A and / or B, which can represent: A exists alone, B exists alone, and A and B exist at the same time. In addition, unless otherwise specified, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" can explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0029] See also Figure 1 , the embodiment of the present application discloses a flow chart of a declaration element compliance detection method, which can be implemented by a computer program or run on a declaration element compliance detection device based on the von Neumann system. The computer program can be integrated into an application or run as an independent tool application, specifically including: S101: Obtain at least one piece of declaration element data to be tested, where the declaration element data includes multiple basic element information.

[0030] Specifically, in the embodiments of the present application, declaration element data refers to the declaration materials that need to be checked for compliance in customs declaration, which includes a number of basic element information, which are closely related to imported and exported goods and are used to ensure that the goods can complete the customs clearance process accurately and efficiently. A piece of declaration element data to be tested includes a number of basic element information such as the commodity name, specification model, country of origin, quantity and commodity price of the goods, which are the basis for customs to classify goods, calculate tariffs, conduct risk assessment and other important tasks. Therefore, enterprises must provide declaration element data containing complete basic element information when making customs declarations. Among them, customs declaration is a necessary international trade procedure, which involves formally submitting relevant information on the import and export of goods to the customs agency so that the goods can legally enter or leave the customs territory of a country.

[0031] Furthermore, a feasible way to obtain declaration element data is: when an enterprise needs to make a customs declaration, the application element data of the goods is uploaded to the server through the enterprise terminal. The enterprise terminal can be a personal computer, and a client of the enterprise declaration system is installed in the enterprise terminal. Specifically, the application requirement data is uploaded to the server through the client and stored in the database. The server is the background server of the client. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. The server and the enterprise terminal are indirectly connected through a wireless network. Furthermore, the server directly extracts at least one declaration element data from the database for automated compliance testing. Among them, the enterprise declaration system is a system for enterprises to submit and manage customs declarations.

[0032] S102: Perform semantic analysis on each basic element information in each declared element data through a preset large language model and extract key features.

[0033] Specifically, after obtaining the declaration element data that needs to be tested for compliance, the preset large language model is used to perform semantic analysis and understanding on the basic element information contained in each declaration element data. The large language model is a pre-trained language model based on the Transformer architecture, which can better understand human language and can be used for various natural language processing tasks. In the embodiment of the present application, the large language model can perform semantic analysis and understanding on the basic element information and extract the key features in the basic element information. Exemplarily, the basic element information is the name of the product. The large language model can understand the meaning of the product name and extract the characteristic terms related to the product as key features; if the basic element information is a specification signal, then the key parameters are extracted from it as key features. Among them, the training process of the large language model is: the basic element information samples marked with key features are used as training samples and input into the model, thereby improving the performance of the model in extracting key features. In other embodiments, the large language model can also be a pre-trained language model based on the long short-term memory network architecture.

[0034] S103: Based on the key features corresponding to the same declaration element data, the corresponding compliance judgment rules are matched from the preset compliance judgment rule library through the preset rule matching model, and the basic element information in the corresponding declaration element data is detected according to the compliance judgment rules to obtain the corresponding detection results.

[0035] Specifically, after the key features of each basic element information in each declaration element data are determined, the key features corresponding to the single declaration element data are input into the preset rule matching model, and the rule matching model matches the compliance determination rules corresponding to this declaration element data from the preset compliance determination rule library according to each key feature. The compliance determination rule library includes a variety of different judgment rules for determining whether the declaration element data is compliant, all of which are set based on human experience. In an embodiment of the present application, the compliance determination rules include the specification requirements of each basic element information in the application element data. Exemplarily, the compliance determination rules include the specification requirements of the product name, the reasonable range of the product price, and so on. Among them, the rule matching model is a trained convolutional neural network model, and can also be a trained recurrent neural network model. The training process is: the model is trained by using the key features marked with the corresponding compliance determination rules as training samples. This is a prior art and will not be repeated here.

[0036] Furthermore, according to the compliance determination rules for each declaration element data, each basic element information in the corresponding declaration element data is tested and audited to determine whether each basic element information in the declaration element data is compliant, and obtain the corresponding test results. A feasible detection method is to determine whether each basic element information is compliant through natural language processing (NLP). If the basic element information is the price of the commodity, then the compliance is directly determined based on whether the commodity price is within the corresponding reasonable price range. Thereby determining whether the declaration element data meets the customs declaration requirements. It should be noted that in other embodiments, before the key features are input into the rule matching model, the key features can also be pre-processed, including data cleaning, data conversion, etc., so as to improve the performance of the model. This is a prior art and will not be repeated here.

[0037] S104: If there is non-compliance of basic element information in the detection result, the non-compliant basic element information is determined as target element information and a corresponding target non-compliance reason is added, and feedback information on the target non-compliance reason from the user's terminal is obtained.

[0038] Specifically, if the test result corresponding to a single declared element data has non-compliance of basic element information, then the corresponding declared element data is determined as the target element information, and based on the specific requirement information in the target element information not meeting the corresponding specification requirements, the corresponding target non-compliance reason is determined. Exemplarily, if the price is 15, and the corresponding reasonable price range is 8-12, then the non-compliance reason is that the price is too high; if the price is 7, then the non-compliance reason is that the price is too low. Further, the user's terminal receives feedback information on the cause of target non-compliance. In an embodiment of the present application, the user may be a declaration reviewer, and the feedback information is a correct judgment or an incorrect judgment. A correct judgment indicates that the reason for the non-compliance of the target element information is correct, and an incorrect judgment indicates that the reason for the non-compliance of the target element information is incorrect. The terminal may be a smart phone or a personal computer.

[0039] S105: If the feedback information is a judgment error, the large language model is optimized based on the feedback information.

[0040] In one achievable implementation, if the feedback information is a determination error, the declared element data where the target element information is located is determined as the target declared element data, and the associated element information of the target element information is determined from the target declared element data; Counting a first quantity of non-compliant correlation factor information in each correlation factor information, and if the first quantity exceeds a preset first quantity threshold, obtaining a rule selection instruction sent by the terminal; According to the rule selection instructions, the corresponding optimal judgment rule is selected from the compliance judgment rule library, the compliance judgment rule corresponding to the target declaration element data is replaced with the optimal judgment rule, and the key features and optimal judgment rules corresponding to the target declaration element data are input into the rule matching model for learning and optimization.

[0041] Specifically, if the feedback information is a judgment error, it means that the declaration element data where the target element information is located, that is, the compliance judgment rule corresponding to the target declaration element data, has a poor match with this target declaration element data, resulting in a deviation in the non-compliance judgment. In order to further verify the match between this target declaration element data and the corresponding compliance judgment rule, the associated element information associated with the target element information is determined from this target declaration element data, that is, the basic element information that is strongly associated with this target element information according to the corresponding specification requirements. Exemplarily, the target element information in the target declaration element data A is the name of the product, and an associated element information that is strongly associated with it is the price of the product. The reasonable price range for determining whether the product price is compliant is related to the product name. Different products have different reasonable price ranges for different product prices. Further, a feasible way to determine the associated element information is: match the associated element information corresponding to this target element information from a preset associated element matching table. The associated element matching table includes different basic element information and corresponding associated element information, all of which are set based on human experience.

[0042] The first number of associated element information that is judged to be non-compliant in each associated element information is counted. If the first number exceeds the preset first number threshold, it means that more of the basic element information associated with the target element information is judged to be non-compliant. Then it is determined that this target declaration element data does not match the corresponding compliance judgment rule, resulting in the target element information and the associated basic element information being judged to be non-compliant, indicating that the rule matching model has a deviation when matching the compliance judgment rule. Further, each compliance judgment rule in the compliance judgment rule library is displayed on the terminal, and the user selects a rule that is more matched with the target declaration element data. Then the server receives the rule selection instruction sent by the terminal, and then selects the optimal judgment rule corresponding to this rule selection instruction from the compliance judgment rule library, so that the server re-detects the target declaration element data item by item according to this optimal judgment rule. At the same time, the key features and optimal judgment rules corresponding to this target declaration element data are input into the rule matching model for training to optimize the model performance, so that the rule matching model can match the corresponding compliance judgment rules according to the key features with higher accuracy.

[0043] In other embodiments, if the first quantity does not exceed the first quantity threshold, and more basic element information associated with the target element information is judged to be compliant, it means that the target declaration element data and the corresponding compliance determination rules are matched with a high probability, and there is no non-compliance problem with the target element information. It may be that the customs has new declaration requirements for the target element information, and the enterprise uploads this target element information according to the new declaration requirements, resulting in a misjudgment of the corresponding compliance determination rules. In this case, the target element information is adjusted to a compliant state, and the compliance matching rules corresponding to the target declaration element data are updated in a timely manner.

[0044] In another embodiment, when the target declaration element data is re-determined for compliance based on the optimal judgment rule, it is determined whether the target element information is compliant. If the target element information is still determined to be non-compliant, then the non-compliance feedback of the user's terminal on this non-compliance is obtained. If the non-compliance feedback is that the target element information is correctly determined to be non-compliant and the cause of non-compliance is incorrect, it means that the optimal judgment rule selected by the user still does not match the target declaration element data. Further, the second number of compliant associated element information in each associated element information is counted. If the second number exceeds the second number threshold, it means that in the case of mismatch of the optimal judgment rule, more basic element information associated with the target element information is determined to be compliant, indicating that there is a problem with this optimal judgment rule, then this optimal judgment rule is removed from the compliance judgment rule library, and at the same time, the historical declaration element data determined to be compliant under this optimal judgment rule is likely to have problems, then the compliance judgment of these historical element data is re-performed, thereby improving the accuracy of declaration element data detection.

[0045] See also Figure 2 , the present application embodiment discloses a flow chart of another declaration element compliance detection method, which can be implemented by a computer program or run on a declaration element compliance detection device based on the von Neumann system. The computer program can be integrated into an application or run as an independent tool application, specifically including: S201: Obtain at least one piece of declaration element data to be tested, where the declaration element data includes multiple basic element information.

[0046] S202: Perform semantic analysis on each basic element information in each declared element data through a preset large language model and extract key features.

[0047] S203: Based on the key features corresponding to the same declaration element data, the corresponding compliance judgment rules are matched from the preset compliance judgment rule library through the preset rule matching model, and the basic element information in the corresponding declaration element data is detected according to the compliance judgment rules to obtain the corresponding detection results.

[0048] S204: If there is non-compliance of basic element information in the detection result, the non-compliant basic element information is determined as target element information and a corresponding target non-compliance reason is added, and feedback information on the target non-compliance reason from the user's terminal is obtained.

[0049] S205: If the feedback information is a judgment error, the large language model is optimized based on the feedback information.

[0050] For details, please refer to steps S101-S105, which will not be described in detail here.

[0051] S206: If the feedback information indicates that the judgment is correct, at least one element adjustment method corresponding to the target element information is determined.

[0052] Specifically, if the feedback information is judged to be correct, it means that the target element information has the problem reflected by the target non-compliance reason, and the target element information needs to be adjusted and modified. Then, according to the commodity name in the declaration element data to which the target element information belongs, the corresponding target commodity type is determined. Furthermore, in the historical declaration records, the historical adjustment methods of the historical target element information in the historical declaration element data under the target commodity type when it is non-compliant are screened out, and the non-compliance reason of the historical target element information is the target non-compliance reason. It should be noted that the element adjustment method is a method of modifying and adjusting the specific content of the target element information.

[0053] The first occurrence number of each historical adjustment method is counted. The more the first occurrence number is, the easier it is to adopt the corresponding historical adjustment method when the historical target element information has a target non-compliance reason. According to the order of the first occurrence number from large to small, the historical adjustment method with the first number is selected as the easy-to-use adjustment method, which is the adjustment method with a high probability of being adopted when the historical target element information has a target non-compliance reason. Further, the compliance determination rule corresponding to the historical declaration element data is obtained from the rule matching record, and then the historical compliance determination rule in which the historical target element information adjusted and modified by the easy-to-use adjustment method is judged to be compliant is extracted from it. Then the second occurrence number of each historical compliance determination rule is counted. The larger the second occurrence number is, the easier it is to judge compliance after adopting this single easy-to-use adjustment method to modify and adjust under the corresponding historical compliance determination rule. According to the order of the second occurrence number from large to small, the historical compliance determination rule with the second number is selected from each historical compliance determination rule, and it is determined as the easy-to-use compliance rule of the corresponding easy-to-use adjustment method. It should be noted that each easy-to-use adjustment method corresponds to multiple easy-to-use compliance rules.

[0054] Furthermore, the compliance judgment rule corresponding to the target element information is determined as the target judgment rule, and it is determined whether there is a target judgment rule in each easy-to-use compliance rule corresponding to each easy-to-use adjustment method. If so, the corresponding easy-to-use adjustment method is determined as the element adjustment method, that is, a method that is likely to achieve accurate modification of the target element information under the target judgment rule.

[0055] S207: Detecting the user's initial adjustment action on the target element information, and based on the initial adjustment action, selecting a recommended adjustment method from the adjustment methods of each element and virtually displaying it on the terminal.

[0056] Specifically, to detect the user's initial adjustment action on the target element information, a feasible detection method is: through the tracking technology, the mouse operation behavior and keyboard input information of the user when adjusting the target element information are detected in real time, and input into the adjustment action prediction model, so as to finally determine the user's initial adjustment action when adjusting the target element information. The adjustment action prediction model can use a trained convolutional neural network model. The training process is: the mouse operation behavior and keyboard input information of the known desktop action are used as training samples and input into the convolutional neural network model for training. This is a prior art and will not be repeated here.

[0057] Furthermore, the element adjustment method including this initial adjustment action is screened out from each element adjustment method, and is determined as the recommended adjustment method, that is, the element adjustment method recommended to the user. Then the first weight of each recommended adjustment method and the second weight of the target determination rule corresponding to each recommended adjustment method are calculated, wherein the first weight is the ratio of the first occurrence number of each recommended adjustment method to the sum of the first occurrence numbers of all easy-to-use adjustment methods, and the second weight is the ratio of the second occurrence number of the target determination rule corresponding to each recommended adjustment method to the sum of the second occurrence numbers of all corresponding easy-to-comply rules. Further, the weight product of the first weight of each recommended adjustment method and the second weight of the corresponding target determination rule is calculated. The larger the weight product, the greater the probability of determining compliance under the target determination rule by taking the corresponding recommended adjustment method to modify the target element information. Finally, according to the product of each weight, the corresponding recommended adjustment method is displayed in virtual form at the corresponding display position of the terminal. The larger the weight product, the closer the corresponding display position is to the center of the terminal's field of view, and the more it conforms to the user's field of view habits. This not only makes it convenient for users to adopt more compliant recommended adjustment methods, but the virtual displayed recommended adjustment method can also guide users in real time to make subsequent correct modification actions, thereby improving the accuracy and efficiency of the modification of target element information.

[0058] S208: receiving a selection instruction sent by the terminal, determining a recommended adjustment method corresponding to the selection instruction as a target adjustment method, and monitoring a user's adjustment process of the target element information based on the target adjustment method.

[0059] Specifically, after the user clicks and selects the recommended adjustment method he wants through the terminal, the server receives the selection instruction sent by the terminal, and determines the recommended adjustment method corresponding to the selection instruction as the target adjustment method. Through this target adjustment method, combined with real-time monitoring of the user's adjustment actions on the target element information, the user's adjustment process of the target element information can be better monitored to avoid deviations in the user's adjustments. Once the user's adjustment deviates from the target adjustment method, a deviation reminder is sent to the user's terminal in a timely manner.

[0060] In other embodiments, the test results of each declaration element data are stored in a database, and a result query interface for enterprises is provided, and enterprises can query the declaration element data test results through the result query interface, wherein the result query interface adopts RESTful API. Further, when the current test result of the target enterprise of the query result through the result query interface is non-compliant, the number of results of the non-compliant test results of this target enterprise within the preset time is counted. If the number of results exceeds the preset number threshold, it means that the target enterprise test results are more non-compliant, then the current test result corresponding to the target enterprise and the same type of enterprises with compliant test results are sent to the terminal of the target enterprise, so as to encourage the target enterprise to better control the quality of the declaration element data with the same peers with compliant test results. In another embodiment, the number of non-compliant times of the same basic element information in the test results of the target enterprise within the preset time of the query result is counted, and the basic element information with the most non-compliant times is determined as the error-prone element information of the target enterprise. If the non-compliant basic element information in the current test result of the target enterprise is the error-prone element information, then when the target enterprise uploads the declaration element data next time, a check reminder of the error-prone element information is generated.

[0061] The implementation principle of a declaration element compliance detection method in an embodiment of the present application is: semantic analysis of the basic element information in each declaration element data is performed through a large language model, so as to extract key features that can accurately characterize the corresponding basic element information, and further, the key features corresponding to the same declaration element data are input into the rule matching model, and the rule matching model automatically matches the corresponding compliance determination rules for the declaration element data, avoiding manual matching of compliance determination rules. Then, the compliance of the corresponding declaration element data is detected through the compliance determination rules to obtain the corresponding detection results. If the detection results show that the basic element information is non-compliant, the corresponding target non-compliance reasons are added. If the feedback information sent by the terminal is a judgment error, there may be inaccurate matching of the compliance determination rules. Based on this feedback information, the rule matching model is optimized so that the rule matching model can learn autonomously, improve the accuracy of the compliance determination rule matching, avoid multiple re-matching rules, and affect the detection progress of the declaration element data, thereby improving the efficiency of the declaration element data detection.

[0062] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.

[0063] See also Figure 3 , which is a schematic diagram of the structure of the declaration element compliance detection device provided in the embodiment of the present application. The device for declaration element compliance detection can be implemented as all or part of the device through software, hardware or a combination of both. The device includes a data acquisition module 11, a feature extraction module 12, an element detection module 13, an information feedback module 14 and a model optimization module 15.

[0064] The data acquisition module 11 is used to acquire at least one piece of declaration element data to be detected, and the declaration element data includes multiple basic element information; The feature extraction module 12 is used to perform semantic analysis on each basic element information in each declaration element data and extract key features through a preset large language model; The element detection module 13 is used to match the corresponding compliance determination rules from the preset compliance determination rule library through the preset rule matching model based on the key features corresponding to the same declaration element data, and detect whether the basic element information in the corresponding declaration element data is compliant according to the compliance determination rules, and obtain the corresponding detection results; The information feedback module 14 is used to determine the non-compliant basic element information as the target element information and add the corresponding target non-compliant reason if there is non-compliant basic element information in the detection result, and obtain the feedback information of the user's terminal on the target non-compliant reason; The model optimization module 15 is used to optimize the rule matching model based on the feedback information if the feedback information is a judgment error.

[0065] Optionally, the model optimization module 15 is specifically used for: If the feedback information is a judgment error, the declared element data where the target element information is located is determined as the target declared element data, and the associated element information of the target element information is determined from the target declared element data; Counting a first quantity of non-compliant correlation factor information in each correlation factor information, and if the first quantity exceeds a preset first quantity threshold, obtaining a rule selection instruction sent by the terminal; According to the rule selection instructions, the corresponding optimal judgment rule is selected from the compliance judgment rule library, the compliance judgment rule corresponding to the target declaration element data is replaced with the optimal judgment rule, and the key features and optimal judgment rules corresponding to the target declaration element data are input into the rule matching model for learning and optimization.

[0066] Optional, such as Figure 4 As shown, the device also includes a rule optimization module 16, which is specifically used to: When the compliance determination of the target declared element data is completed based on the optimal determination rule, it is determined whether the target element information is compliant; If the target element information is not compliant, the non-compliance feedback sent by the terminal is obtained, and when the non-compliance feedback indicates that the target element information is correctly determined to be non-compliant and the non-compliance reason is incorrect, it is determined that the target declaration element data does not match the optimal determination rule; Counting a second number of compliant association element information in each association element information, and if the second number exceeds a preset second number threshold, eliminating the optimal determination rule; Obtain the historical declaration element data that is determined to be compliant under the optimal determination rules, and re-determine the compliance of each historical declaration element data.

[0067] Optionally, the device further includes an adjustment recommendation module 17, which is specifically used to: If the feedback information is correct, determining at least one element adjustment method corresponding to the target element information; Detecting the user's initial adjustment action on the target element information, and based on the initial adjustment action, selecting a recommended adjustment method from the adjustment methods of each element and virtually displaying it on the terminal; The selection instruction sent by the receiving terminal is determined as the target adjustment method, and the user's adjustment process of the target element information is monitored based on the target adjustment method.

[0068] Optionally, the adjustment recommendation module 17 is specifically used for: Determine the target commodity type corresponding to the target element information; Obtain the historical adjustment method corresponding to the historical target element information in the historical declaration element data under the target commodity type, and the non-compliance reason of the historical target element information is the target non-compliance reason; Count the first occurrence times of each historical adjustment method, and select the first historical adjustment method from each historical adjustment method in descending order of the first occurrence times and determine it as an easy-to-use adjustment method; Obtain the historical compliance determination rules that are determined to be compliant after the historical target element information is adjusted under each easy-to-use adjustment mode, count the second occurrence times of each historical compliance determination rule, and select the historical compliance determination rules with the second number from each historical compliance determination rule in descending order of the second occurrence times and determine them as the easy-to-use compliance rules of the corresponding easy-to-use adjustment mode; The compliance determination rule corresponding to the target element information is determined as the target determination rule, and the easy-to-use adjustment method of the target determination rule in the corresponding easy-to-compliance rule is determined as the element adjustment method.

[0069] Optionally, the adjustment recommendation module 17 is specifically used for: Selecting the element adjustment method including the initial adjustment action from the element adjustment methods and determining it as the recommended adjustment method; Determine a first weight for each recommended adjustment method, and determine a second weight for the target determination rule corresponding to each recommended adjustment method, wherein the first weight is a ratio of a first occurrence number of each recommended adjustment method to a sum of first occurrence numbers of all easy-to-use adjustment methods, and the second weight is a ratio of a second occurrence number of the target determination rule corresponding to each recommended adjustment method to a sum of second occurrence numbers of all corresponding easy-to-use rules; Calculate the weight product of the first weight of each recommended adjustment method and the second weight of the corresponding target judgment rule, and based on each weight product, display the corresponding recommended adjustment method in a virtual body at the corresponding display position of the terminal. The larger the weight product, the closer the corresponding display position is to the center of the terminal's field of view.

[0070] Optionally, the device further includes a result query module 18, which is specifically used to: The test results of each declared element data are stored in the database, and a result query interface is provided for enterprises; The enterprise that has queried the results through the result query interface is determined as the target enterprise. If the test result of the target enterprise is not compliant, the number of test results that are not compliant within the preset time of the target enterprise is counted; If the number of results exceeds the preset threshold, the test results corresponding to the target enterprise and the same type of enterprises that comply with the test results will be sent to the terminal of the target enterprise.

[0071] It should be noted that the declaration element compliance detection device provided in the above embodiment only uses the division of the above-mentioned functional modules as an example when executing the declaration element compliance detection method. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the declaration element compliance detection device provided in the above embodiment and the declaration element compliance detection method embodiment belong to the same concept. The implementation process is detailed in the method embodiment, which will not be repeated here.

[0072] An embodiment of the present application further discloses a computer-readable storage medium, and the computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, a declaration element compliance detection method of the above embodiment is adopted.

[0073] Among them, the computer program can be stored in a computer-readable medium, the computer program includes computer program code, the computer program code can be in the form of source code, object code, executable file or certain middleware, etc. The computer-readable medium includes any entity or device that can carry the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the computer-readable medium includes but is not limited to the above-mentioned components.

[0074] Among them, through this computer-readable storage medium, a declaration element compliance detection method of the above embodiment is stored in a computer-readable storage medium, and is loaded and executed on a processor to facilitate the storage and application of the above method.

[0075] An embodiment of the present application also discloses an electronic device, in which a computer program is stored in a computer-readable storage medium. When the computer program is loaded and executed by a processor, the above-mentioned declaration element compliance detection method is adopted.

[0076] The electronic device may be a desktop computer, a laptop computer, a cloud server or other electronic device, and the electronic device includes but is not limited to a processor and a memory. For example, the electronic device may also include input and output devices, a network access device, and a bus.

[0077] Among them, the processor can adopt a central processing unit (CPU). Of course, according to actual usage, other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. can also be adopted. The general-purpose processor can adopt a microprocessor or any conventional processor, etc., and this application does not impose any restrictions on this.

[0078] Among them, the memory can be an internal storage unit of the electronic device, such as a hard disk or memory of the electronic device, or it can be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (SMC), a secure digital card (SD) or a flash memory card (FC) equipped on the electronic device. Moreover, the memory can also be a combination of an internal storage unit and an external storage device of the electronic device. The memory is used to store computer programs and other programs and data required by the electronic device. The memory can also be used to temporarily store data that has been output or is to be output, and this application does not impose any restrictions on this.

[0079] Among them, through this electronic device, a declaration element compliance detection method of the above embodiment is stored in the memory of the electronic device, and is loaded and executed on the processor of the electronic device for easy use.

[0080] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure here, those skilled in the art will easily think of other embodiments of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field not recorded in the present disclosure. The description and examples are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A method for compliance detection of declaration elements, characterized in that: The method comprises: Acquire at least one piece of declaration element data to be tested, wherein the declaration element data includes multiple basic element information; Perform semantic analysis on each basic element information in each of the declared element data through a preset large language model and extract key features; Based on the key features corresponding to the same piece of the declaration element data, the corresponding compliance determination rules are matched from the preset compliance determination rule library through the preset rule matching model, and the basic element information in the corresponding declaration element data is detected according to the compliance determination rules to obtain the corresponding detection results; If there is non-compliance of basic element information in the detection result, the non-compliant basic element information is determined as target element information and a corresponding target non-compliance reason is added, and feedback information of the user's terminal on the target non-compliance reason is obtained; If the feedback information is a judgment error, the rule matching model is optimized based on the feedback information.

2. The method for compliance detection of declaration elements according to claim 1 is characterized in that: If the feedback information is a judgment error, optimizing the rule matching model based on the target element information specifically includes: If the feedback information is a judgment error, the declared element data where the target element information is located is determined as the target declared element data, and the associated element information of the target element information is determined from the target declared element data; Counting a first number of non-compliant association factor information in each of the association factor information, and if the first number exceeds a preset first number threshold, obtaining a rule selection instruction sent by the terminal; According to the rule selection instruction, the corresponding optimal judgment rule is selected from the compliance judgment rule library, the compliance judgment rule corresponding to the target declaration element data is replaced with the optimal judgment rule, and the key features corresponding to the target declaration element data and the optimal judgment rule are input into the rule matching model for learning and optimization.

3. The method for compliance detection of declaration elements according to claim 2 is characterized in that: The method further comprises: When the compliance determination of the target declared element data is completed based on the optimal determination rule, determining whether the target element information is compliant; If the target element information is non-compliant, obtaining non-compliant feedback sent by the terminal, and when the non-compliant feedback indicates that the non-compliant determination of the target element information is correct and the non-compliant cause is wrong, determining that the target declaration element data does not match the optimal determination rule; Counting a second number of compliant association element information in each of the association element information, and if the second number exceeds a preset second number threshold, eliminating the optimal determination rule; The historical declaration element data determined to be compliant under the optimal determination rule are obtained, and compliance determination is re-performed on each of the historical declaration element data.

4. The method for compliance detection of declaration elements according to claim 1 is characterized in that: The method further comprises: If the feedback information is judged to be correct, determining at least one element adjustment method corresponding to the target element information; Detecting an initial adjustment action of the user on the target element information, and selecting a recommended adjustment method from the element adjustment methods according to the initial adjustment action and virtually displaying the recommended adjustment method on the terminal; A selection instruction sent by the terminal is received, a recommended adjustment method corresponding to the selection instruction is determined as a target adjustment method, and a process of adjusting the target element information by the user is monitored based on the target adjustment method.

5. The method for compliance detection of declaration elements according to claim 4 is characterized in that: The determining of at least one element adjustment method corresponding to the target element information specifically includes: Determine the target commodity type corresponding to the target element information; Obtaining a historical adjustment method corresponding to historical target element information in the historical declaration element data under the target commodity type, wherein the non-compliance reason of the historical target element information is the target non-compliance reason; Counting the first occurrence number of each of the historical adjustment methods, and selecting the first historical adjustment method from the historical adjustment methods in descending order of the first occurrence number and determining it as an easy-to-use adjustment method; Obtaining the historical compliance determination rule that determines compliance after the historical target element information is adjusted under each of the ease-of-use adjustment modes, counting the second number of occurrences of each of the historical compliance determination rules, and selecting the historical compliance determination rule with the second number from each of the historical compliance determination rules in descending order of the second number of occurrences and determining it as the easy-to-use compliance rule of the corresponding ease-of-use adjustment mode; The compliance determination rule corresponding to the target element information is determined as the target determination rule, and the easy-to-use adjustment method of the target determination rule in the corresponding easy-to-compliance rule is determined as the element adjustment method.

6. The method for compliance detection of declaration elements according to claim 5 is characterized in that: The selecting, according to the initial adjustment action, a recommended adjustment method from the adjustment methods of each element and virtually displaying it on the terminal specifically includes: Selecting the element adjustment method including the initial adjustment action from the element adjustment methods and determining it as the recommended adjustment method; Determine a first weight for each of the recommended adjustment methods, and determine a second weight for the target determination rule corresponding to each of the recommended adjustment methods, wherein the first weight is a ratio of a first occurrence number of each of the recommended adjustment methods to a sum of first occurrence numbers of all of the easy-to-use adjustment methods, and the second weight is a ratio of a second occurrence number of the target determination rule corresponding to each of the recommended adjustment methods to a sum of second occurrence numbers of all corresponding easy-to-use rules; Calculate the weight product of the first weight of each recommended adjustment method and the second weight of the corresponding target judgment rule, and based on each weight product, display the corresponding recommended adjustment method in a virtual body at the corresponding display position of the terminal. The larger the weight product, the closer the corresponding display position is to the center of the terminal's field of view.

7. The method for compliance detection of declaration elements according to claim 1 is characterized in that: The method further comprises: The test results of each of the declared element data are stored in a database, and a result query interface for enterprises is provided; The enterprise whose results are queried through the result query interface is determined as the target enterprise. If the current test result of the target enterprise is non-compliant, the number of test results of the target enterprise that are non-compliant within a preset time is counted; If the number of the results exceeds a preset number threshold, the test result corresponding to the target enterprise and the enterprises of the same type whose test results comply with the regulations will be sent to the terminal of the target enterprise.

8. A declaration element compliance detection device, characterized in that: include: A data acquisition module (11) is used to acquire at least one piece of declaration element data to be detected, wherein the declaration element data includes multiple basic element information; A feature extraction module (12) is used to perform semantic analysis on each basic element information in each of the declared element data and extract key features through a preset large language model; An element detection module (13) is used to match corresponding compliance judgment rules from a preset compliance judgment rule library through a preset rule matching model based on each of the key features corresponding to the same piece of declaration element data, and detect whether each basic element information in the corresponding declaration element data is compliant according to the compliance judgment rule, and obtain corresponding detection results; An information feedback module (14) is used to, if there is non-compliant basic element information in the detection result, determine the non-compliant basic element information as target element information and add a corresponding target non-compliant reason, and obtain feedback information on the target non-compliant reason from the user's terminal; A model optimization module (15) is used to optimize the rule matching model based on the feedback information if the feedback information is a judgment error.

9. A computer-readable storage medium having a computer program stored therein, characterized in that: When the computer program is loaded and executed by a processor, the method according to any one of claims 1 to 7 is adopted.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that: When the processor loads and executes the computer program, the method according to any one of claims 1 to 7 is adopted.

Images