Intelligent charging system and method for ship passing lock

Abstract

The present invention provides an intelligent toll collection system and method for ship passing through a lock, and relates to the technical field of lock toll control. In the present invention, a parameter acquisition module collects ship information to obtain a verification hash value corresponding to each ship. In subsequent verification, only the ship information needs to be re-collected to generate a verification hash value. By comparing the two hash values, it can be determined whether the ship's own data has been tampered with during the transportation process. The verification and identification module ensures the consistency and security of the data through the SHA-256 encrypted hash function, provides a strong verification of the ship's own characteristics, and ensures that the goods are not illegally transferred in the middle. The model construction module uses a long short-term memory network to construct a quantity prediction model, which can generate a predicted number of ships according to real-time timestamps, waiting time and weather data, and dynamically determine the toll value according to the real-time data and the prediction results, thereby encouraging ships to use locks during non-peak hours and balancing the use of locks.

Description

Technical Field

[0001] The present invention relates to the technical field of ship lock fee control, and in particular to an intelligent toll collection system and method for ship lock passage. Background Art

[0002] In the existing ship lock charging system, ships passing through the locks usually need to manually record basic information such as the ship's identification code, length, width, weight, etc., and charge based on this information. This traditional charging method relies on manual operation. Although it is simple and intuitive, it is prone to recording errors and low efficiency when there are a large number of ships and busy transportation. In addition, due to the lack of an effective data verification mechanism, the accuracy and security of ship information cannot be guaranteed.

[0003] Although existing technologies have met the basic needs of ships passing through locks to a certain extent, there are still some obvious shortcomings. First, the manual recording and charging process is time-consuming and prone to errors. Especially during peak hours, this inefficient operation mode may cause ships to wait in line for too long, affecting the overall transportation efficiency. Secondly, the existing charging system lacks security protection measures for ship information and cannot effectively prevent data tampering and information leakage. Finally, the existing system is often unable to respond and adjust in a timely manner to the influence of weather and environmental factors, which increases the risk of ships passing through locks to a certain extent.

[0004] In summary, the main technical problems faced by existing technologies include: how to improve the efficiency and accuracy of ship locks, how to ensure the security and consistency of ship information, and how to deal with the impact of weather and environmental factors on ship locks. These problems not only affect the overall efficiency of ship transportation, but also pose a potential threat to ship safety. Therefore, the development of a ship lock toll collection system that can automatically collect ship information, ensure data security, and intelligently respond to changes in the external environment has become an important direction of current technological development.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The object of the present invention is to provide an intelligent toll collection system and method for ship lock passage, so as to solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] An intelligent toll collection system for ships passing through a lock, comprising:

[0009] The parameter collection module is used to collect the identification code, length data, width data and weight data of the ship before transportation, and convert the length data, width data and weight data into binary numbers, and use the SHA-256 encryption hash function to hash the binary numbers to obtain the verification hash value corresponding to each ship, and then map the identification code and verification hash value of each ship one by one and store them in the cloud server;

[0010] A model building module is used to build a quantity prediction model based on a long short-term memory network, collect historical data of ships passing through the locks over multiple days, and train the quantity prediction model. The historical data of ships passing through the locks includes the timestamp of the ships passing through the locks and the weather data when passing through the locks. The current timestamp and the waiting time of the ship, as well as the water level, wind speed, wind direction and rainfall data at the current gate are collected in real time and input into the trained quantity prediction model to obtain the predicted number of ships.

[0011] The verification and identification module is used to collect the length data, width data and weight data of the ship to be passed through the lock in real time, convert the re-collected length data, width data and weight data into binary numbers, and use the same SHA-256 cryptographic hash function to hash these binary numbers to generate a verification hash value;

[0012] The ship verification module is used to receive the identification code sent by the ship, and retrieve the verification hash value corresponding to the identification code in the cloud server through the mapping relationship between the identification code and the ship, compare the verification hash value with the verification hash value, and determine whether the verification hash value and the verification hash value are equal;

[0013] The charging determination module is used to determine the charging value according to the length data, width data, weight data and predicted number of ships collected in real time when the verification hash value and the check hash value are equal, generate the passing priority of the ship according to the waiting time of the ship, and determine the order of ships passing through the lock.

[0014] Furthermore, the logic for converting the length data, width data and weight data into binary numbers is to first convert the length data, width data and weight data of the ship into binary numbers in sequence, and connect the three binary numbers into a single binary number as a whole in the order of length, width and weight, calculate the data length of the single binary number, and ensure that the data length is a multiple of 512 bits. If it is not satisfied, add 0 to the end of the data of the single binary number until the data length of the OTA upgrade package is a multiple of 512 bits.

[0015] Furthermore, the specific method of using the SHA-256 cryptographic hash function to hash the binary number and obtain the verification hash value corresponding to each ship is as follows:

[0016] Split the single binary number with confirmed length into multiple 512-bit data blocks, using the predefined 8 32-bit words as the initial hash value;

[0017] Each 512-bit data block is further decomposed into 16 32-bit words and expanded to 64 32-bit words as sub-word blocks by copying the existing 16 words until 64 words are reached;

[0018] Using 8 initial hash values, perform 64 rounds of logic processing on each 32-bit word. After each round, combine the obtained hash value with the hash value of the previous round to update the hash value.

[0019] The hash value obtained from the processing result of each sub-block is used as the initial value of the next sub-block, and the logical processing is repeated for 64 rounds until all sub-blocks are processed;

[0020] Get the final hash value after all sub-word blocks are processed, and concatenate the eight 32-bit final hash values ​​to form a 256-bit check hash value.

[0021] Further, the logic processing is performed using a logic function within the SHA-256 cryptographic hash function, and the logic functions of adjacent rounds of logic processing are different. After each round, when the obtained hash value is combined with the hash value of the previous round, the obtained hash value is added to the hash value of the previous round;

[0022] The verification hash value and the check hash value being equal means that all the bits of the two check hash values ​​are the same in a one-to-one correspondence.

[0023] Furthermore, the logic for obtaining the predicted number of ships is:

[0024] Collect historical data of ships passing through the lock, the historical data of ships passing through the lock includes the timestamp of the ships passing through the lock and the weather data when passing through the lock, the weather data includes the water level height, wind speed, wind direction and rainfall data at the gate when passing through the lock;

[0025] Divide a day into multiple time periods of equal length, and calculate the number of ships passing through the lock in each time period and the average weather data in each time period based on the historical data of ships passing through the lock, wherein the average weather data includes the average water level height, average wind speed, average wind direction and average rainfall data in each time period;

[0026] A quantity prediction model based on long short-term memory network is constructed. The start timestamp, end timestamp and average weather data of each time period are used as training sets, and the number of ships passing through the lock in each time period is used as labels to train the quantity prediction model.

[0027] Collect the timestamp of the current moment and the waiting time of the ship in real time, determine the time period of the current moment, collect the water level, wind speed, wind direction and rainfall data at the current gate in real time, input the start timestamp, end timestamp, water level, wind speed, wind direction and rainfall data at the gate of the current time period into the trained quantity prediction model, and obtain the predicted number of ships passing through the lock in the current time period.

[0028] Furthermore, the generation logic of the average water level, average wind speed, average wind direction and average rainfall data in each time period is:

[0029] Obtain the water level, wind speed, wind direction and rainfall data at the gate when all ships pass through the lock during the time period, sum them up, and then divide them by the number of ships passing through during the time period. The formula is: , , , ,in, Respectively represent The average water level, average wind speed, average wind direction and average rainfall data for a period of time. For the The number of ships passing through in a time period, Respectively represent In the time period, The water level height, wind speed, wind direction and rainfall data at the gate when a ship passes through the lock, The time interval of the time period is Respectively represent The start and end timestamps of the time period. is the time period number, is the number of the ship passing through the lock, is a positive integer, , Indicates the number of time periods into which a day is divided.

[0030] Furthermore, the logic for determining the charging value based on the real-time collected ship length data, width data, weight data and the predicted number of ships is as follows:

[0031] Based on the collected length, width and weight data of the ship, check the charging policies and standards issued by the local government and lock management agency;

[0032] Classify ships into corresponding size and weight classes, and determine the basic fees for ships passing through the locks according to the charging policies and standards;

[0033] Based on the historical data of ships passing through the locks collected over multiple days, the average number of ships passing through the locks in one day is generated, and combined with the predicted number of ships passing through the locks in the current time period, an additional discount coefficient is generated. The formula is:

[0034] in, The average number of ships passing through the lock in one day. Indicates the number of days of historical data collected on ship passing through the locks, Indicates the historical data Number of ships passing through per day, represents the additional discount factor, Indicates the predicted number of ships passing through the lock in the current time period. Indicates the number of equal-length time periods into which a day is divided. is a positive integer, ;

[0035] The actual cost of ship passing through the lock is generated based on the additional discount coefficient and the basic cost of ship passing through the lock, based on the formula:

[0036] in, Indicates the actual cost of a ship passing through a lock. Indicates the basic fee for a ship passing through a lock.

[0037] Furthermore, the ship's passing priority is generated according to the ship's waiting time, and the logic for determining the ship's passing order is as follows:

[0038] Compare all the verified hash values ​​with the check hash values, number the ships waiting to pass through the lock, and obtain the waiting time of each ship and the length, width and weight data of the ship;

[0039] Calculate the priority value of each ship waiting to pass through the lock, and then sort them from high to low according to the priority value to determine the order of ships passing through the lock. The higher the priority value, the higher the order of ships passing through the lock. The formula for calculating the priority value is:

[0040] in, Indicates The priority value of the ships waiting to pass through the lock, Indicates The waiting time for ships waiting to pass through the locks, Respectively represent The weight, length and width data of the ships waiting to pass through the locks, They represent the average weight, average length and average width of ships waiting to pass through the lock, are the time weight coefficient and the ship weight coefficient respectively, ,and ;

[0041] The calculation formula for the average weight, average length and average width of the ships waiting to pass through the lock is:

[0042] , , ,in, represents the total number of ships waiting to pass through the lock, Indicates the number of the ship waiting to pass through the lock, is a positive integer, .

[0043] The invention also provides an intelligent charging method for ship passing through a lock, which is executed by the above-mentioned intelligent charging system for ship passing through a lock, and the specific steps include:

[0044] Collect the identification code, length data, width data and weight data of the ship before transportation, convert the length data, width data and weight data into binary numbers, use the SHA-256 encryption hash function to hash the binary numbers, obtain the verification hash value corresponding to each ship, map the identification code and verification hash value of each ship one by one and store them in the cloud server;

[0045] Construct a quantity prediction model based on the long short-term memory network, collect historical data of ships passing through the locks over multiple days, and train the quantity prediction model. The historical data of ships passing through the locks includes the timestamp of the ships passing through the locks and the weather data when passing through the locks. The timestamp of the current moment and the waiting time of the ship, as well as the water level, wind speed, wind direction and rainfall data at the current gate are collected in real time and input into the trained quantity prediction model to obtain the predicted number of ships;

[0046] Collect the length, width and weight data of the ship to be passed through the lock in real time, convert the re-collected length, width and weight data into binary numbers, and use the same SHA-256 cryptographic hash function to hash these binary numbers to generate a verification hash value;

[0047] Receive the identification code sent by the ship, and retrieve the verification hash value corresponding to the identification code in the cloud server through the mapping relationship between the identification code and the ship, compare the verification hash value with the verification hash value, and determine whether the verification hash value and the verification hash value are equal;

[0048] When the verification hash value and the check hash value are equal, the charging value is determined based on the real-time collected ship length data, width data, weight data and predicted number of ships, and the ship's passing priority is generated based on the ship's waiting time to determine the order in which the ships pass through the lock.

[0049] Compared with the prior art, the present invention has the following beneficial effects:

[0050] The present invention solves the problem of low efficiency in the existing ship lock charging system through a parameter acquisition module and a verification identification module. The parameter acquisition module acquires ship information, obtains the verification hash value corresponding to each ship, and maps the identification code of each ship to the verification hash value one by one. In subsequent verification, it is only necessary to re-collect the ship information to generate the verification hash value. By comparing the hash value generated before transportation with the hash value acquired and processed in real time, it can be determined whether the ship's own data has been tampered with during the transportation process, providing accurate data support for the ship lock manager, greatly reducing the time and error rate of manual operation verification. The verification identification module ensures the consistency and security of the data through the SHA-256 encrypted hash function, avoids the risk of data tampering and information leakage, provides strong verification of the ship's own characteristics, and ensures that the goods are not illegally transferred in the middle. The combined use of these two modules improves the overall efficiency of the ship lock charging system in identity verification of ships and reduces the waiting time for ships to pass through the lock.

[0051] The present invention solves the problem that the existing ship lock charging system cannot respond to the changes of the external environment in time through the model building module. The model building module constructs a quantity prediction model by using the long short-term memory network, which can quickly and accurately predict the number of ships according to the real-time timestamp, waiting time and weather data. The charging determination module dynamically determines the charging value according to the real-time data and the prediction results, so as to encourage ships to use the ship locks during non-peak hours, balance the use of the ship locks, reduce congestion during peak hours, and maintain the stability of charging to a certain extent when the number of ships is small. At the same time, the passing priority is generated according to the waiting time of the ship, so as to ensure the fairness and rationality of the lock passing sequence and improve the ship's satisfaction with the lock passing. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a schematic diagram of the overall system structure of the present invention;

[0053] Figure 2 It is a schematic diagram of the overall method flow of the present invention. DETAILED DESCRIPTION

[0054] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0055] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0056] Example

[0057] See also Figure 1 , the present invention provides a technical solution:

[0058] An intelligent toll collection system for ships passing through a lock includes a parameter collection module, a model building module, a verification and identification module, a ship verification module and a toll determination module, wherein:

[0059] The parameter acquisition module is used to collect the identification code, length data, width data and weight data of the ship before transportation, and convert the length data, width data and weight data into binary numbers, and hash the binary numbers using the SHA-256 encryption hash function to obtain the verification hash value corresponding to each ship, and map the identification code and verification hash value of each ship one by one and store them in the cloud server.

[0060] In this embodiment, the identification code generally refers to the unique identifier of the ship, which is the number of the ship's internal automatic identification system (AIS), which is automatically obtained through the ship's AIS system, or provided by the ship when the ship is registered and declared. The length data refers to the total length of the ship, including the hull and any protruding parts. The width data refers to the maximum width of the ship, which generally refers to the size of the widest part of the hull. The weight data refers to the deadweight of the ship, which depends on specific needs. Displacement refers to the weight of the water displaced by the ship in the water, and deadweight refers to the weight of the cargo and passengers that the ship can carry. The weight data can be obtained through the ship's load table, ship registration information, or through weighing equipment.

[0061] When collecting the identification code, length data, width data and weight data of the ship before transportation, after the cargo is loaded, the weight data of the ship is recorded and compared with the data during subsequent passage through the lock to ensure that the cargo has not been illegally transferred in the middle.

[0062] The parameter acquisition module performs binary conversion and SHA-256 hash processing on the data, and stores the results in the cloud server. An important feature of the hash function is that even if the input data is only slightly different, the output hash value will be significantly different. Therefore, by using SHA-256 to hash the original data, a unique hash value can be generated. In the subsequent stage, as long as the hash value of the data is recalculated and compared with the hash value recorded in the cloud server, it is possible to verify whether the data is complete and whether it has been tampered with. The hash function is one-way, that is, the original data cannot be inferred from the hash value. In addition, SHA-256 is a widely recognized secure hash algorithm that is extremely difficult to crack. Therefore, even if the hash value is intercepted during transmission, or the hash value stored in the cloud server is illegally accessed, the attacker cannot obtain the original ship data, which protects the security of the data. The length of the data after hashing is fixed, and the storage and transmission costs are lower than the original data. At the same time, the hash value can be used as a unique identifier for ship data, facilitating data management and query.

[0063] By generating a verification hash value for the ship data, subsequent data verification is possible, ensuring the integrity and accuracy of the data during the ship's transportation process. Secondly, by mapping and storing the hash value with the ship's identification code one by one, data management is facilitated and the efficiency of data query is improved. In addition, by hashing and encrypting the stored data, the security of the ship's important information is protected, preventing data tampering and illegal access.

[0064] Furthermore, the logic for converting the length data, width data and weight data into binary numbers is as follows: first, the length data, width data and weight data of the ship are converted into binary numbers in sequence, and the three binary numbers are connected into a single binary number as a whole in the order of length, width and weight. The data length of the single binary number is calculated to ensure that the data length is a multiple of 512 bits. If it is not satisfied, 0 is added to the end of the data of the single binary number until the data length of the OTA upgrade package is a multiple of 512 bits. By ensuring that the data length is a multiple of 512 bits and accurately dividing the data blocks, the accuracy and consistency of the hash calculation are guaranteed. This precise data processing helps to generate reliable verification hash values.

[0065] In this embodiment, the SHA-256 cryptographic hash function is used to hash the binary number, and the specific method for obtaining the verification hash value corresponding to each ship is as follows:

[0066] Split the single binary number with confirmed length into multiple 512-bit data blocks, using the predefined 8 32-bit words as the initial hash value;

[0067] Each 512-bit data block is further decomposed into 16 32-bit words and expanded to 64 32-bit words as sub-word blocks by copying the existing 16 words until 64 words are reached;

[0068] Using 8 initial hash values, perform 64 rounds of logic processing on each 32-bit word. After each round, combine the obtained hash value with the hash value of the previous round to update the hash value.

[0069] The hash value obtained from the processing result of each sub-block is used as the initial value of the next sub-block, and the logical processing is repeated for 64 rounds until all sub-blocks are processed;

[0070] Get the final hash value after all sub-word blocks are processed, and concatenate the eight 32-bit final hash values ​​to form a 256-bit check hash value.

[0071] The SHA-256 hash function can generate a unique fixed-length (256-bit) hash value for a binary number based on length, width and weight. Any slight change in any ship parameter will result in a huge change in the hash value, which is called the avalanche effect. Therefore, this method provides a strong verification of the ship's own characteristics and ensures that the cargo has not been illegally transferred in the middle. In this embodiment, the use of the SHA-256 hash processing step can promote the implementation of the overall solution because it fundamentally improves the data credibility and system security during the OTA upgrade process. The SHA-256 hash function defines a sequence of 64 constants, which are used with each sub-word block (512-bit block) processed. SHA-256 also defines 8 initial hash values ​​that can be obtained based on the decimal part of the square root of the first 8 prime numbers (2 to 19). 32-bit words, logical processing methods include bit operations including bitwise AND, bitwise NOT, bitwise XOR, addition, as well as loops and right shifts.

[0072] Furthermore, the logic processing is performed using the logic function within the SHA-256 cryptographic hash function, and the logic functions between adjacent rounds of logic processing are different. After each round, when the obtained hash value is combined with the hash value of the previous round, the obtained hash value is added to the hash value of the previous round.

[0073] In this embodiment, the logic function operation includes bitwise operations and modular addition operations. Bitwise operations include AND, OR, XOR and NOT. By accumulating the hash value after each round, it is ensured that slight changes in information can be quickly diffused to the entire hash value. To ensure that every small part of the change can have a big impact on the final result, SHA-256 significantly increases the computational complexity required to construct a collision by introducing different logic processing and accumulating hash values ​​in each round, thereby improving the ability to resist collisions. A collision attack refers to finding two different inputs that produce the same output hash value.

[0074] The model building module is used to build a quantity prediction model based on a long short-term memory network, collect historical data of ships passing through the locks over multiple days, and train the quantity prediction model. The historical data of ships passing through the locks includes the timestamp of the ship passing through the locks and the weather data when passing through the locks. The current timestamp and the waiting time of the ship, as well as the water level, wind speed, wind direction and rainfall data at the current gate are collected in real time and input into the trained quantity prediction model to obtain the predicted number of ships.

[0075] A quantity prediction model based on the long short-term memory network (LSTM) is used to predict the number of ships. LSTM is a special recurrent neural network (RNN) that can effectively solve long-term dependency problems when processing time series data. Therefore, it is suitable for predicting the number of ships passing through the locks, which involves time series.

[0076] In this embodiment, the logic for obtaining the predicted number of ships is:

[0077] Collect historical data of ships passing through the lock, the historical data of ships passing through the lock includes the timestamp of the ships passing through the lock and the weather data when passing through the lock, the weather data includes the water level height, wind speed, wind direction and rainfall data at the gate when passing through the lock;

[0078] Divide a day into multiple time periods of equal length, and calculate the number of ships passing through the lock in each time period and the average weather data in each time period based on the historical data of ships passing through the lock, wherein the average weather data includes the average water level height, average wind speed, average wind direction and average rainfall data in each time period;

[0079] A quantity prediction model based on long short-term memory network is constructed. The start timestamp, end timestamp and average weather data of each time period are used as training sets, and the number of ships passing through the lock in each time period is used as labels to train the quantity prediction model.

[0080] Collect the timestamp of the current moment and the waiting time of the ship in real time, determine the time period of the current moment, collect the water level, wind speed, wind direction and rainfall data at the current gate in real time, input the start timestamp, end timestamp, water level, wind speed, wind direction and rainfall data at the gate of the current time period into the trained quantity prediction model, and obtain the predicted number of ships passing through the lock in the current time period.

[0081] For example, if each day is divided into 12 time periods, each of which is two hours long, then the time interval of the first time period is The start and end timestamps of this time period are 0:00 and 2:00 respectively. The method to determine the time period of the current moment is: if the timestamp of the current moment is 3:20, then the time period of the current moment is The start and end timestamps of this time period are 2:00 and 4:00 respectively.

[0082] The water level height data refers to the height of the water surface in the water area where the gate is located relative to the design reference plane of the gate, in meters. The wind speed data refers to the moving speed of the air wind at the gate, in meters per second. The wind direction data refers to the source direction of the air wind at the gate, expressed in azimuth, such as north wind (0 degrees), east wind (90 degrees), south wind (180 degrees) and west wind (270 degrees). The rainfall data refers to the instantaneous rainfall intensity that falls at the gate within a certain period of time, that is, the amount of precipitation during the time when the ship passes through the lock. The instantaneous rainfall intensity can be expressed in millimeters per hour, which reflects the immediate intensity of the rainfall.

[0083] The steps construct a quantity prediction model based on a long short-term memory network (LSTM) to predict the number of ships passing through the lock in the current time period. The LSTM model has excellent performance in processing time series data and can effectively capture the time dependency in past data. Therefore, it has a good effect on predicting the number of ships in the lock. The model not only considers the time factor, but also takes weather data into consideration. Weather factors are important environmental factors that may affect the operation of the lock, which can make the prediction results more accurate and stable. The model can collect and process data in real time and predict the number of ships passing through the lock in real time. This is very important for the operation and management of the lock, and the operation strategy can be adjusted in time to improve efficiency.

[0084] Due to the excellent performance of the LSTM model and the consideration of more relevant factors, the prediction results are more accurate than traditional prediction methods. Accurate prediction results can help operators prepare in advance. The start timestamp and end timestamp provide information in the time dimension, helping the model understand the law of ship passing behavior over time. For example, the model can learn that the number of ships passing through the lock may increase during certain periods of the day. This time series analysis is crucial for predicting the number of ships because it reveals the temporal pattern of ship activities. The water level, wind speed, wind direction and rainfall data at the gate are external environmental factors that affect the passage of ships through the lock. The water level may affect the ship's ability to pass, the wind speed and wind direction may affect the navigation safety of the ship, and the rainfall may affect the visibility of the water area and the navigation speed of the ship. Changes in these environmental factors will affect the behavior of ships passing through the lock. Therefore, incorporating these data into the model can improve the accuracy of the prediction because they provide important clues about the possibility of current and future ship passing through the lock.

[0085] By combining time series data and environmental factor data, the LSTM model is able to learn the complex relationship between the number of ships passing through the locks and these input variables. During the training process, the model will identify which time periods and environmental conditions are more likely to promote or inhibit the passage of ships through the locks. Therefore, when the model receives the timestamp and environmental data of the current moment, it can predict the number of ships passing through the locks in the current time period based on the patterns and associations learned previously. This predictive ability is based on the results of in-depth analysis of historical data, allowing the model to make educated guesses about the future.

[0086] In this embodiment, the generation logic of the average water level, average wind speed, average wind direction and average rainfall data in each time period is:

[0087] Obtain the water level, wind speed, wind direction and rainfall data at the gate when all ships pass through the lock during the time period, sum them up, and then divide them by the number of ships passing through during the time period. The formula is: , , , ,in, Respectively represent The average water level, average wind speed, average wind direction and average rainfall data for a period of time. For the The number of ships passing through in a time period, Respectively represent In the time period, The water level height, wind speed, wind direction and rainfall data at the gate when a ship passes through the lock, The time interval of the time period is Respectively represent The start and end timestamps of the time period. is the time period number, is the number of the ship passing through the lock, is a positive integer, , Indicates the number of time periods into which a day is divided.

[0088] The verification and identification module is used to collect the length data, width data and weight data of the ship to be passed through the lock in real time, convert the re-collected length data, width data and weight data into binary numbers, and use the same SHA-256 encrypted hash function to hash these binary numbers to generate a verification hash value.

[0089] The verification and identification module collects the length, width and weight data of the ship in real time, and uses the SHA-256 cryptographic hash function to hash these data to generate a verification hash value, thereby ensuring the integrity and security of the data. Through hash processing, any tampering with the data will cause a change in the hash value, so that data inconsistencies can be immediately discovered. In addition, the high anti-collision performance of the SHA-256 algorithm ensures that the data is difficult to be tampered with, thereby improving the security of the data.

[0090] It can enhance the overall solution's system security and improve system reliability. By comparing the hash value generated before transportation with the hash value collected and processed in real time, it can be determined whether the ship's own data has been tampered with during transportation. If the two hash values ​​are consistent, it means that the data has not been tampered with; if the hash values ​​are inconsistent, it means that the data may have been tampered with. This comparison mechanism ensures the integrity of the data, thereby protecting the safe operation of the lock system and providing accurate data support for lock managers to make more reasonable decisions.

[0091] The ship verification module is used to receive the identification code sent by the ship, and retrieve the verification hash value corresponding to the identification code in the cloud server through the mapping relationship between the identification code and the ship, compare the verification hash value with the verification hash value, and determine whether the verification hash value and the verification hash value are equal.

[0092] In this embodiment, the verification hash value and the check hash value are equal, which means that all the digits of the two check hash values ​​are the same in a one-to-one correspondence. The ship verification module first receives the identification code sent by the ship, and retrieves the verification hash value corresponding to the identification code in the cloud server through the mapping relationship between the identification code and the ship. This verification hash value is generated when the ship information is initially entered or the last verification is performed, and is stored in the server. The retrieved verification hash value is compared with the check hash value generated after real-time collection and processing. If the two hash values ​​are equal, it is judged that the ship information has not been tampered with; if they are not equal, it is judged that the ship information may have been tampered with.

[0093] Traditional ship information verification methods may rely on complex comparison processes. This embodiment provides an efficient and accurate way to verify the integrity and consistency of ship information. By using hash value comparison, any tampering with ship information can be quickly and accurately detected. This rapid verification is very important for real-time monitoring and verification of ship information, which can ensure the efficient operation of the lock system.

[0094] If the verification hash value and the check hash value are equal, it means that the ship's information has not been tampered with, thus ensuring the safety of the lock system. At the same time, since the operation process of this step is simple, the work efficiency of the entire system can be improved. In addition, this step also helps to reduce misjudgments and misoperations, thereby improving the effectiveness of lock management and the efficiency of ship passing through the lock.

[0095] In this embodiment, the problem of low efficiency in the existing ship lock charging system is solved through the parameter collection module and the verification and identification module. The parameter collection module collects ship information, obtains the verification hash value corresponding to each ship, and maps the identification code of each ship to the verification hash value one by one. In subsequent verification, it is only necessary to re-collect the ship information to generate the verification hash value. By comparing the hash value generated before transportation with the hash value collected and processed in real time, it can be determined whether the ship's own data has been tampered with during the transportation process, providing accurate data support for the lock manager, greatly reducing the time and error rate of manual operation verification. The verification and identification module uses the SHA-256 encrypted hash function to ensure the consistency and security of the data, avoid the risk of data tampering and information leakage, provide strong verification of the ship's own characteristics, and ensure that the goods are not illegally transferred in the middle. The combined use of these two modules improves the overall efficiency of the ship lock charging system in identity authentication of ships and reduces the waiting time for ships to pass through the lock.

[0096] The charging determination module is used to determine the charging value according to the length data, width data, weight data of the ship collected in real time and the predicted number of ships when the verification hash value and the check hash value are equal, generate the passing priority of the ship according to the waiting time of the ship, and determine the order of the ships passing through the lock.

[0097] By charging each ship based on its specific size and weight, this ensures that larger or heavier ships pay more as they put more pressure on the use and maintenance of the locks. By incorporating the predicted number of ships into the billing formula, discounts can be provided during peak lock usage periods, encouraging ships to use the locks during off-peak hours, thereby balancing the use of the locks and reducing pressure on the locks. This can more accurately reflect the actual cost of ships using the locks, resulting in fairer charging.

[0098] In this embodiment, the logic for determining the charging value based on the real-time collected ship length data, width data, weight data and the predicted number of ships is as follows:

[0099] Based on the collected length, width and weight data of the ship, and the charging policies and standards issued by the local government and lock management agency, the ship is classified into the corresponding size and weight level, and the basic fee for the ship to pass through the lock is determined according to the charging policies and standards.

[0100] Collect the length, width and weight data of the ship, which is usually provided by sensors on the ship or measuring equipment at the entrance of the lock, and consult the charging policies and standards issued by the local government of the lock and the lock management agency. These policies and standards usually set different charging levels based on the size and weight of the ship. According to the collected ship data, the ship is classified into the corresponding size and weight level. For example, there may be classifications of small, medium and large ships, or the levels are divided according to specific size ranges and weight ranges. According to the size and weight class to which the ship belongs, and the charging policies and standards consulted, the system will determine the basic fee for the ship to pass through the lock. The basic fee refers to the basic service fee for the ship to use the lock. It is usually set according to the ship's use of the lock resources. Larger ships or heavier ships will cause greater wear and tear on the lock facilities, so they need to pay higher basic fees. These policies and standards are formulated by the lock management agency based on operating costs, maintenance needs and market conditions. They stipulate the charging standards for different levels of ships.

[0101] Based on the historical data of ships passing through the locks collected over multiple days, the average number of ships passing through the locks in one day is generated, and combined with the predicted number of ships passing through the locks in the current time period, an additional discount coefficient is generated. The formula is:

[0102] in, The average number of ships passing through the lock in one day. Indicates the number of days of historical data collected on ship passing through the locks, Indicates the historical data Number of ships passing through per day, represents the additional discount factor, Indicates the predicted number of ships passing through the lock in the current time period. Indicates the number of equal-length time periods into which a day is divided. is a positive integer, .

[0103] In this embodiment, the purpose of the additional discount factor is to provide discounts when the forecasted number of ships is lower than the average, so as to encourage ships to use the locks during off-peak hours, thereby balancing the use of the locks. Indicates the average number of ships passing through the locks in each time period in the historical data. If the predicted number of ships is much lower than the average, will be less than 1, indicating a larger discount, if the forecasted number of ships is close to or above the average. It will be close to or less than 1, indicating a small discount or no discount.

[0104] The exponential function has nonlinear characteristics. It can nonlinearly amplify or reduce the ratio between the predicted number of ships and the average number of ships, making the additional discount factor more sensitive to the predicted number of ships. Even if the difference between the predicted number of ships and the average number of ships is very small, a significant discount can be generated. The value of the exponential function in its domain is always greater than 0, which is consistent with the additional discount factor. The actual demand, the larger the number of ships, if the ratio of the predicted number of ships to the average number of ships in each time period is larger, then this ratio as the input value of the exponential function will also be larger. Due to the exponential growth characteristics of the exponential function, the larger the predicted number of ships, the faster the additional discount coefficient grows, and a larger additional discount coefficient can be provided when the number of ships is large, thereby encouraging ships to use the locks during non-peak hours, balancing the use of the locks, and reducing congestion during peak hours. When the number of ships is small, the growth of the additional discount coefficient will be relatively slow, thereby maintaining the stability of charges to a certain extent. Therefore, in this embodiment, an exponential function is used to fit and generate the additional discount coefficient.

[0105] The actual cost of ship passing through the lock is generated based on the additional discount coefficient and the basic cost of ship passing through the lock, based on the formula:

[0106] in, Indicates the actual cost of a ship passing through a lock. Indicates the basic fee for a ship passing through a lock.

[0107] This embodiment calculates the actual cost of a ship passing through the lock by multiplying the additional discount coefficient with the basic fee for a ship passing through the lock. By introducing the additional discount coefficient, the cost of a ship passing through the lock can be dynamically adjusted according to actual conditions. The cost of passing through the lock during peak hours will be relatively higher. The additional discount coefficient serves as an incentive mechanism to encourage ships to pass through the lock during non-peak hours, thereby balancing the use of the lock and reducing congestion during peak hours. Reasonable fee adjustments can improve the overall efficiency of lock operations, reduce waiting time, provide flexible operating strategies, and help improve the efficiency and benefits of lock operations.

[0108] In this embodiment, the ship's passing priority is generated according to the waiting time of the ship, and the logic for determining the ship's passing order is as follows:

[0109] Compare all the verified hash values ​​with the check hash values, number the ships waiting to pass through the lock, and obtain the waiting time of each ship and the length, width and weight data of the ship;

[0110] Calculate the priority value of each ship waiting to pass through the lock, and then sort them from high to low according to the priority value to determine the order of ships passing through the lock. The higher the priority value, the higher the order of ships passing through the lock. The formula for calculating the priority value is:

[0111] in, Indicates The priority value of the ships waiting to pass through the lock, Indicates The waiting time for ships waiting to pass through the locks, Respectively represent The weight, length and width data of the ships waiting to pass through the locks, They represent the average weight, average length and average width of ships waiting to pass through the lock, are the time weight coefficient and the ship weight coefficient respectively, ,and .

[0112] Furthermore, using the logarithmic function This is because it can amplify the impact of waiting time, making the ships with longer waiting time have higher priority. The characteristic of the logarithmic function is that when the input value is small, the output value changes faster, which helps to highlight the priority of ships with longer waiting time.

[0113] Using the square root function This is because it can balance the impact of each size data, giving larger ships a higher priority. The characteristic of the square root function is that when the input value is small, the output value changes slowly, which helps to smooth the impact of the size data. The relative values ​​of the ship's length, width and weight data are used to standardize the size data so that ships of different sizes can be compared on the same scale.

[0114] Weight coefficient , ensuring that the sum of the weights of the two parts is 1, which helps to maintain the scale consistency of the priority value. The weight of the waiting time is higher than the weight of the size data because the waiting time has a more important impact on the lock-passing order, especially during peak hours. Ships with long waiting times should be given priority to pass through the lock. By giving priority to ships with long waiting times and large sizes, the waiting time can be effectively reduced, the passing efficiency of the lock can be improved, and resource utilization can be optimized. This embodiment comprehensively considers the waiting time and size data through logarithmic functions and square root functions, and balances the influence of various factors through the setting of weight coefficients to ensure the fairness and rationality of the lock-passing order. With the increase of waiting time or the increase of size data (relative to the average value), the priority value of the ship will increase, ensuring that ships with long waiting times and large sizes can obtain higher priority and thus be ranked first in the lock-passing order.

[0115] The calculation formula for the average weight, average length and average width of the ships waiting to pass through the lock is:

[0116] , , ,in, represents the total number of ships waiting to pass through the lock, Indicates the number of the ship waiting to pass through the lock, is a positive integer, .

[0117] In this embodiment, the problem that the existing ship lock charging system cannot respond to changes in the external environment in a timely manner is solved through the model building module. The model building module uses a long short-term memory network to construct a quantity prediction model, which can quickly and accurately predict the number of ships based on real-time timestamps, waiting time and weather data. The charging determination module dynamically determines the charging value based on real-time data and prediction results, thereby encouraging ships to use locks during non-peak hours, balancing the use of locks, reducing congestion during peak hours, and maintaining the stability of charges to a certain extent when the number of ships is small. At the same time, the passing priority is generated according to the waiting time of the ship to ensure the fairness and rationality of the lock passing order, thereby improving the ship's satisfaction with the lock passing.

[0118] See also Figure 2The present invention also provides a method for charging ships passing through a lock intelligently. The charging method is executed by the above-mentioned intelligent charging system for charging ships passing through a lock, and the specific steps include:

[0119] Step 1: Collect the identification code, length data, width data and weight data of the ship before transportation, and convert the length data, width data and weight data into binary numbers. Use the SHA-256 encryption hash function to hash the binary numbers to obtain the verification hash value corresponding to each ship. Map the identification code and verification hash value of each ship one by one and store them in the cloud server;

[0120] Step 2: Construct a quantity prediction model based on the long short-term memory network, collect historical data of ships passing through the locks over multiple days, and train the quantity prediction model. The historical data of ships passing through the locks includes the timestamp of the ships passing through the locks and the weather data when passing through the locks. The timestamp of the current moment and the waiting time of the ship, as well as the water level, wind speed, wind direction and rainfall data at the current gate are collected in real time and input into the trained quantity prediction model to obtain the predicted number of ships;

[0121] Step 3: Collect the length data, width data and weight data of the ship to be passed through the lock in real time, convert the re-collected length data, width data and weight data into binary numbers, and use the same SHA-256 cryptographic hash function to hash these binary numbers to generate a verification hash value;

[0122] Step 4: Receive the identification code sent by the ship, and retrieve the verification hash value corresponding to the identification code in the cloud server through the mapping relationship between the identification code and the ship, compare the verification hash value with the verification hash value, and determine whether the verification hash value and the verification hash value are equal;

[0123] Step 5: When the verification hash value and the check hash value are equal, the charging value is determined based on the real-time collected ship length data, width data, weight data and predicted number of ships, and the ship's passing priority is generated based on the ship's waiting time to determine the order in which the ships pass through the lock.

[0124] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0125] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0126] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0127] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. An intelligent toll collection system for ships passing through locks, characterized in that: include: The parameter collection module is used to collect the identification code, length data, width data and weight data of the ship before transportation, and convert the length data, width data and weight data into binary numbers, and use the SHA-256 encryption hash function to hash the binary numbers to obtain the verification hash value corresponding to each ship, and then map the identification code and verification hash value of each ship one by one and store them in the cloud server; A model building module is used to build a quantity prediction model based on a long short-term memory network, collect historical data of ships passing through the locks over multiple days, and train the quantity prediction model. The historical data of ships passing through the locks includes the timestamp of the ships passing through the locks and the weather data when passing through the locks. The current timestamp and the waiting time of the ship, as well as the water level, wind speed, wind direction and rainfall data at the current gate are collected in real time and input into the trained quantity prediction model to obtain the predicted number of ships. The verification and identification module is used to collect the length data, width data and weight data of the ship to be passed through the lock in real time, convert the re-collected length data, width data and weight data into binary numbers, and use the same SHA-256 cryptographic hash function to hash these binary numbers to generate a verification hash value; The ship verification module is used to receive the identification code sent by the ship, and retrieve the verification hash value corresponding to the identification code in the cloud server through the mapping relationship between the identification code and the ship, compare the verification hash value with the verification hash value, and determine whether the verification hash value and the verification hash value are equal; The charging determination module is used to determine the charging value according to the length data, width data, weight data and predicted number of ships collected in real time when the verification hash value and the check hash value are equal, generate the passing priority of the ship according to the waiting time of the ship, and determine the order of the ships passing through the lock.

2. The intelligent toll collection system for ship lock passage according to claim 1 is characterized in that: The logic for converting the length data, width data and weight data into binary numbers is to first convert the length data, width data and weight data of the ship into binary numbers in sequence, and connect the three binary numbers into a single binary number as a whole in the order of length, width and weight, calculate the data length of the single binary number, and ensure that the data length is a multiple of 512 bits. If it is not satisfied, add 0 to the end of the data of the single binary number until the data length of the OTA upgrade package is a multiple of 512 bits.

3. The intelligent toll collection system for ship passing through a lock according to claim 2 is characterized in that: The specific method of using the SHA-256 cryptographic hash function to hash the binary number and obtain the verification hash value corresponding to each ship is as follows: Split the single binary number with confirmed length into multiple 512-bit data blocks, using the predefined 8 32-bit words as the initial hash value; Each 512-bit data block is further decomposed into 16 32-bit words and expanded to 64 32-bit words as sub-word blocks by copying the existing 16 words until 64 words are reached; Using 8 initial hash values, perform 64 rounds of logical processing on each 32-bit word. After each round, combine the obtained hash value with the hash value of the previous round to update the hash value. The hash value obtained from the processing result of each sub-block is used as the initial value of the next sub-block, and the logical processing is repeated for 64 rounds until all sub-blocks are processed; Get the final hash value after all sub-word blocks are processed, and concatenate the eight 32-bit final hash values ​​to form a 256-bit check hash value.

4. The intelligent toll collection system for ship lock passage according to claim 3 is characterized in that: The logic processing is performed using the logic function inside the SHA-256 encrypted hash function, and the logic functions of adjacent rounds of logic processing are different. After each round, when the obtained hash value is combined with the hash value of the previous round, the obtained hash value is added to the hash value of the previous round; The verification hash value and the check hash value being equal means that all the bits of the two check hash values ​​are the same in a one-to-one correspondence.

5. The intelligent toll collection system for ship lock passage according to claim 1 is characterized in that: The logic for obtaining the predicted number of ships is: Collect historical data of ships passing through the lock, the historical data of ships passing through the lock includes the timestamp of the ships passing through the lock and the weather data when passing through the lock, the weather data includes the water level height, wind speed, wind direction and rainfall data at the gate when passing through the lock; Divide a day into multiple time periods of equal length, and calculate the number of ships passing through the lock in each time period and the average weather data in each time period based on the historical data of ships passing through the lock, wherein the average weather data includes the average water level height, average wind speed, average wind direction and average rainfall data in each time period; A quantity prediction model based on long short-term memory network is constructed. The start timestamp, end timestamp and average weather data of each time period are used as training sets, and the number of ships passing through the lock in each time period is used as labels to train the quantity prediction model. Collect the timestamp of the current moment and the waiting time of the ship in real time, determine the time period of the current moment, collect the water level, wind speed, wind direction and rainfall data at the current gate in real time, input the start timestamp, end timestamp, water level, wind speed, wind direction and rainfall data at the gate of the current time period into the trained quantity prediction model, and obtain the predicted number of ships passing through the lock in the current time period.

6. The intelligent toll collection system for ship lock passage according to claim 4 is characterized in that: The generation logic of the average water level, average wind speed, average wind direction and average rainfall data in each time period is: Obtain the water level, wind speed, wind direction and rainfall data at the gate when all ships pass through the lock during the time period, sum them up, and then divide them by the number of ships passing through during the time period. The formula is: , , , ,in, Respectively represent The average water level, average wind speed, average wind direction and average rainfall data for a period of time. For the The number of ships passing through in a time period, Respectively represent In the time period, The water level height, wind speed, wind direction and rainfall data at the gate when a ship passes through the lock, The time interval of the time period is Respectively represent The start and end timestamps of the time period. is the time period number, is the number of the ship passing through the lock, is a positive integer, , Indicates the number of time periods into which a day is divided.

7. The intelligent toll collection system for ship lock passage according to claim 6 is characterized in that: The logic for determining the charging value based on the real-time collected ship length data, width data, weight data and predicted number of ships is as follows: Based on the collected length, width and weight data of the ship, check the charging policies and standards issued by the local government and lock management agency; Classify ships into corresponding size and weight classes, and determine the basic fees for ships passing through the locks according to the charging policies and standards; Based on the historical data of ships passing through the locks collected over multiple days, the average number of ships passing through the locks in one day is generated, and combined with the predicted number of ships passing through the locks in the current time period, an additional discount coefficient is generated. The formula is: in, The average number of ships passing through the lock in one day. Indicates the number of days of historical data collected on ship passing through the locks, Indicates the historical data Number of ships passing through per day, represents the additional discount factor, Indicates the predicted number of ships passing through the lock in the current time period. Indicates the number of equal-length time periods into which a day is divided. is a positive integer, ; The actual cost of ship passing through the lock is generated based on the additional discount coefficient and the basic cost of ship passing through the lock, based on the formula: in, Indicates the actual cost of a ship passing through the lock. Indicates the basic fee for a ship passing through a lock.

8. The intelligent toll collection system for ship lock passage according to claim 1 is characterized in that: The ship's passing priority is generated based on the ship's waiting time. The logic for determining the ship's passing order is as follows: Compare all the verified hash values ​​with the check hash values, number the ships waiting to pass through the lock, and obtain the waiting time of each ship and the length, width and weight data of the ship; Calculate the priority value of each ship waiting to pass through the lock, and then sort them from high to low according to the priority value to determine the order of ships passing through the lock. The higher the priority value, the higher the order of ships passing through the lock. The formula for calculating the priority value is: in, Indicates The priority value of the ships waiting to pass through the lock, Indicates The waiting time for ships waiting to pass through the locks, Respectively represent The weight, length and width data of the ships waiting to pass through the locks, They represent the average weight, average length and average width of ships waiting to pass through the lock, are the time weight coefficient and the ship weight coefficient respectively, ,and ; The calculation formula for the average weight, average length and average width of the ships waiting to pass through the lock is: , , ,in, represents the total number of ships waiting to pass through the lock, Indicates the number of the ship waiting to pass through the lock, is a positive integer, .

9. An intelligent charging method for ships passing through locks, characterized in that: The charging method is executed by the ship lock intelligent charging system according to any one of claims 1 to 8, and the specific steps include: Collect the identification code, length data, width data and weight data of the ship before transportation, convert the length data, width data and weight data into binary numbers, use the SHA-256 encryption hash function to hash the binary numbers, obtain the verification hash value corresponding to each ship, map the identification code and verification hash value of each ship one by one and store them in the cloud server; Construct a quantity prediction model based on the long short-term memory network, collect historical data of ships passing through the locks over multiple days, and train the quantity prediction model. The historical data of ships passing through the locks includes the timestamp of the ships passing through the locks and the weather data when passing through the locks. The timestamp of the current moment and the waiting time of the ship, as well as the water level height, wind speed, wind direction and rainfall data at the current gate are collected in real time and input into the trained quantity prediction model to obtain the predicted number of ships; Collect the length, width and weight data of the ship to be passed through the lock in real time, convert the re-collected length, width and weight data into binary numbers, and use the same SHA-256 cryptographic hash function to hash these binary numbers to generate a verification hash value; Receive the identification code sent by the ship, and retrieve the verification hash value corresponding to the identification code in the cloud server through the mapping relationship between the identification code and the ship, compare the verification hash value with the verification hash value, and determine whether the verification hash value and the verification hash value are equal; When the verification hash value and the check hash value are equal, the charging value is determined based on the real-time collected ship length data, width data, weight data and predicted number of ships, and the ship's passing priority is generated based on the ship's waiting time to determine the order in which the ships pass through the lock.

Images