Marine distress alarm method and system based on ship wireless communication

Abstract

The invention discloses a marine distress alarm method and system based on ship wireless communication, and particularly relates to the technical field of ray recognition, and the method comprises the steps: obtaining a first communication text and a second communication text sent by a ship operator, and carrying out the preprocessing operation, so as to obtain a first communication feature word group and a second communication word group, obtaining a first communication alarm probability corresponding to the first communication text through an intelligent communication model according to the first communication feature phrase; determining a preferred feature word in the first communication feature word group according to a preferred feature word in the second communication feature word group, and constructing a third communication feature word group through the first feature word; according to the intelligent communication model, obtaining a second communication alarm probability corresponding to the third communication feature phrase, obtaining an alarm processing model, and obtaining an alarm evaluation value; according to the invention, the alarm evaluation value is sent to the ship operator according to the preset feedback method, so that the speed of ship wireless communication marine alarm and the accuracy of data analysis are greatly improved.

Description

Technical Field

[0001] The present invention relates to the field of wireless communication technology, and more specifically, to a method and system for marine distress alarm based on ship wireless communication. Background Art

[0002] Wireless communication is currently in a period of rapid development and change. The continuous progress of radio frequency technology and integrated circuit technology has made it easier to realize wireless communication functions, and the data transmission speed has continued to increase, gradually becoming comparable to that of wired networks. At the same time, people's strong demand for free communication and convenient mobility has also prompted the continuous expansion of the application scenarios of wireless communication. For example, satellite communication technology can solve long-distance communication problems, and microwave communication technology can transmit large-capacity information. Bluetooth technology is widely used in short-distance communications, facilitating data sharing between mobile devices. The development of wireless broadband technology, such as microwave broadband access technology, has reduced power consumption and achieved short-range image and voice transmission.

[0003] At present, in the maritime distress alarm method and system based on ship wireless communication, the risk problem is analyzed by the ship's maritime distress, and then the method is obtained from a pre-prepared database to detect the risk of the data. However, only the current risk problem is analyzed to detect its risk, and it is impossible to perform in-depth risk detection on the same risk problem, which leads to reduced data security performance and reduced alarm efficiency.

[0004] There is an urgent need for a method and system for maritime distress alarm based on ship wireless communication. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a method and system for maritime distress alarm based on ship wireless communication, which solves the problems raised in the above-mentioned background technology through the field of wireless communication technology.

[0006] To achieve the above object, the present invention provides the following technical solution: a method for marine distress alarm based on ship wireless communication, comprising:

[0007] S1: In response to an alarm operation of wireless communication, a first communication text sent by a ship operator is obtained.

[0008] S2: The first communication text is preprocessed, where the preprocessing operation is used to obtain a first communication feature phrase corresponding to the first communication text.

[0009] S3: Acquire an intelligent communication model, and acquire a first communication alarm probability corresponding to the first communication text through the first communication feature phrase according to the intelligent communication model.

[0010] S4: Acquire a second communication text sent by the ship operator, where the second communication text is a communication text subsequent to the first communication text sent by the ship operator.

[0011] S5: The second communication text is subjected to the preprocessing operation, where the preprocessing is used to obtain a second communication feature phrase corresponding to the second communication text.

[0012] S6: Obtain preferred feature words in the second communication feature word group, and use the preferred feature words in the second communication feature word group to determine the preferred feature words in the first communication feature word group, the preferred feature words in the first communication feature word group are the first feature words, and the preferred feature words in the second communication feature word group are the second feature words, so as to construct a third communication feature word group through multiple first feature words.

[0013] S7: Obtain a second communication alarm probability corresponding to the third communication feature phrase according to the intelligent communication model through the third communication feature phrase.

[0014] S8: Acquire an alarm processing model, and acquire an alarm evaluation value according to the alarm processing model through the first communication alarm probability and the second communication alarm probability; the alarm evaluation value is sent to the ship operator according to a preset feedback method.

[0015] Preferably, obtaining the intelligent communication model specifically includes:

[0016] According to the first communication characteristic phrase, a classification operation is performed on the first communication text to obtain a communication subject corresponding to the first communication text, wherein the communication subject corresponding to the first communication text is target information data corresponding to the first communication text;

[0017] In a preset communication database, an intelligent communication model corresponding to a communication subject is obtained, and the preset communication database is used to store a corresponding relationship between a communication subject and an intelligent communication model.

[0018] Preferably, obtaining the communication subject corresponding to the first communication text specifically includes: obtaining a plurality of preselected communication subjects, the plurality of preselected communication subjects including a target communication subject, the target communication subject being any one of the plurality of preselected communication subjects; determining whether the similarity value is within a preselected threshold value by using a similarity value between the communication subject corresponding to the first communication text and the target communication subject; if the similarity value is within the preselected threshold value, confirming that the preselected communication subject is the communication subject corresponding to the first communication text.

[0019] Preferably, the target information data includes signal strength data, communication interference degree data and communication device remaining power data, which are respectively denoted as Xq, Xt and Xs.

[0020] Preferably, according to the intelligent communication model, before obtaining the communication subject corresponding to the first communication text through the first communication feature phrase, an intelligent communication model is constructed, specifically including: obtaining a communication processing unit corresponding to the target information data; and constructing an intelligent communication model according to the communication processing unit.

[0021] Preferably, obtaining the target information data specifically includes: setting a time period through a counter, and obtaining the target information data from the data of the target ship through a crawler method, and the crawler methods mainly include python data reading, web crawler, and database query.

[0022] Preferably, the preferred characteristic words in the second communication characteristic word group are used to determine the preferred characteristic words in the first communication characteristic word group, specifically including:

[0023] The preferred feature word in the first communication feature word group is obtained as the first feature word, and the preferred feature word in the second communication feature word group is obtained as the second feature word, the first feature word is any preferred feature word among the preferred feature words in the first communication feature word group, and the second feature word is any preferred feature word among the preferred feature words in the second communication feature word group; by calculating the feature correlation value between the second feature word and the first feature word; judging whether the feature correlation value is within the safety threshold range; if the feature correlation value is within the safety threshold range, the preferred feature word in the second communication feature word group determines the preferred feature word in the first communication feature word group.

[0024] Preferably, the preset feedback method mainly includes but is not limited to: any one of sound display, table display and picture display.

[0025] Preferably, a marine distress alarm system based on ship wireless communication comprises:

[0026] A text acquisition module: in response to an alarm operation of wireless communication, acquires a first communication text sent by a ship operator; acquires a second communication text sent by the ship operator, wherein the second communication text is a communication text subsequent to the first communication text sent by the ship operator;

[0027] Preprocessing module: the first communication text is preprocessed, the preprocessing operation is used to obtain the first communication feature phrase corresponding to the first communication text; the second communication text is preprocessed, the preprocessing is used to obtain the second communication feature phrase corresponding to the second communication text;

[0028] Communication analysis module: obtaining an intelligent communication model, and obtaining a first communication alarm probability corresponding to the first communication text through the first communication feature phrase group according to the intelligent communication model; obtaining preferred feature words in the second communication feature phrase group, and determining preferred feature words in the first communication feature phrase group by using the preferred feature words in the second communication feature phrase group, wherein the preferred feature words in the first communication feature phrase group are first feature words, and the preferred feature words in the second communication feature phrase group are second feature words, so as to construct a third communication feature phrase group by using the first feature words; the intelligent communication model obtains a second communication alarm probability corresponding to the third communication feature phrase group through the third communication feature phrase group;

[0029] Feedback module: obtain an alarm processing model, and obtain an alarm evaluation value according to the alarm processing model through the first communication alarm probability and the second communication alarm probability; the alarm evaluation value is sent to the ship operator according to a preset feedback method.

[0030] Technical effects and advantages of the present invention:

[0031] 1. The present invention receives the first communication text sent by the ship operator and performs a preprocessing operation on the first communication text to obtain the first communication feature phrase, thereby obtaining the first communication alarm probability according to the first communication feature phrase through the intelligent communication model; when the ship operator sends the second communication text, the second communication text performs the preprocessing operation to obtain the preferred feature words in the second communication feature phrase, and determines the preferred feature words in the first communication feature phrase by the preferred feature words in the second communication feature phrase, and the preferred feature words in the first communication feature phrase are the first feature words, so as to construct the third communication feature phrase through the first feature words. According to the intelligent communication model, the second communication alarm probability corresponding to the third communication feature phrase is obtained through the third communication feature phrase; according to the alarm processing model, the alarm evaluation value is obtained through the first communication alarm probability and the second communication alarm probability; thereafter, the alarm evaluation value is sent to the ship operator according to the preset feedback method. Through this method, the speed of marine alarm of ship wireless communication and the accuracy of communication data analysis are greatly improved;

[0032] 2. The present invention performs classification operations through first communication texts of different communication subjects, and selects an intelligent communication model corresponding to the communication subject in a preset communication database, which helps to improve the accuracy of analysis of communication data.

[0033] 3. The present invention calculates the feature correlation value between the second feature word and the first feature word, and determines whether the feature correlation value is within the safety threshold range, so as to make the communication data more accurate, so that the ship operator can obtain more detailed feedback information. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a schematic diagram of the overall method of the present invention.

[0035] Figure 2 It is a schematic diagram of the overall system of the present invention. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] The terms used in the following embodiments of the present invention are only for the purpose of describing specific embodiments and are not intended to be limiting of the present application. As used in the specification of the present application, the singular expressions "a", "a", "said", "above", "the" and "this" are intended to also include plural expressions unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in the present application refers to and includes any or all possible combinations of one or more of the listed items.

[0038] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0039] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0040] As attached Figure 1 As shown, it shows an overall schematic diagram of a maritime distress alarm method based on ship wireless communication provided in an embodiment of the present application. The method is applied to a maritime distress alarm system based on ship wireless communication. The overall method schematic diagram mainly includes the following steps: S1 to S7.

[0041] S1: In response to an alarm operation of wireless communication, a first communication text sent by a ship operator is obtained.

[0042] In this embodiment, it should be specifically noted that ship operators can perform operations on the communication information of the ship at sea through corresponding terminal devices, including ship radar terminals, PC terminals, computer terminals, mobile phone terminals, etc. The ship operator performs an alarm assessment based on the first communication text input through the terminal device. The ship operator can input the communication text in various ways, including but not limited to: text, tables, images, etc. In this embodiment, there are no restrictions on the terminal device and the input method of the communication text; during the operation, the ship operator establishes multiple status windows, and in each status window, the ship operator can perform operations. Each status window exists independently, and there is no mutual influence between each status window. In this embodiment, taking one of the status windows as an example, the first communication text is all the historical first communication texts before the ship operator inputs the first communication text in this status window.

[0043] S2: Perform a preprocessing operation on the first communication text, and the preprocessing operation is used to obtain the first communication feature phrase corresponding to the first communication text.

[0044] In this embodiment, it should be specifically noted that after obtaining the first communication text input by the ship operator, the preprocessing operation is used to obtain multiple feature words and the first communication feature phrase corresponding to the first communication text. The specific steps of the preprocessing operation are as follows:

[0045] A1: Text cleaning: In the first communication text, remove special characters, punctuation marks (such as commas, periods, exclamation marks, etc.), special symbols (such as #, @, $, etc.) and other non-alphanumeric characters; remove stop words, which refer to words that frequently appear in the first communication text but contribute little to the text semantics, such as "de", "shi", "zai", etc.; case conversion: Convert all letters in the first communication text to uppercase or lowercase to ensure the consistency of the first communication text.

[0046] A2: Text standardization: Perform stemming and part-of-speech tagging on the result of text cleaning: Tag the part of speech of each word in the text, such as noun, verb, adjective, etc. Part-of-speech tagging can help understand the grammatical structure and semantics of the text and provide more information for subsequent natural language processing tasks.

[0047] A3: Feature word extraction: Based on the part-of-speech tagging method, perform part-of-speech tagging according to the tagging of the first communication text, and then extract multiple communication feature words, that is, the first communication feature phrase, according to specific part-of-speech rules.

[0048] S3: Obtain an intelligent communication model, and obtain the first communication alarm probability corresponding to the first communication text through the first communication feature phrase according to the intelligent communication model.

[0049] In this embodiment, it should be specifically explained that the intelligent communication model is a communication model constructed in advance. The first communication feature phrase is input into the intelligent communication model. The intelligent communication model will obtain the first communication alarm probability based on the first communication feature phrase and send the first communication alarm probability to the corresponding operator.

[0050] In a possible implementation, step S3 further includes obtaining an intelligent communication model:

[0051] B1: performing a classification operation on the first communication text according to the first communication characteristic phrase to obtain a communication subject corresponding to the first communication text, wherein the communication subject corresponding to the first communication text is target information data corresponding to the first communication text;

[0052] B2: Obtain the intelligent communication model corresponding to the communication subject in a preset communication database, wherein the preset communication database is used to store the corresponding relationship between the communication subject and the intelligent communication model.

[0053] In this embodiment, it is specifically necessary to explain that the first communication text is classified by the first communication feature word, and the communication subject corresponding to the first communication text is obtained. The communication subject is the target information data involved in the first question and answer text, that is, by confirming the information data of the first communication text, the information data involved in this communication subject is confirmed. The target information data includes: signal strength data, communication interference degree data, and communication equipment remaining power data, which are respectively denoted as Xq, Xt, and Xs. After determining the communication subject of the first communication text, the corresponding relationship between the communication subject and the intelligent communication model in the preset communication database can be used to obtain a suitable intelligent communication model in the preset communication database. The preset communication database is a pre-constructed database for storing multiple intelligent communication models, multiple communication subjects, and the corresponding relationship between multiple communication subjects and multiple intelligent communication models. The communication subject corresponds one-to-one to the intelligent communication model, which includes: a signal strength management intelligent model corresponding to the signal strength data, a communication interference degree management intelligent model corresponding to the communication interference degree data, and a communication equipment remaining power management intelligent model corresponding to the communication equipment remaining power data; on the other hand, obtaining target information data specifically includes: setting a time period through a counter, and obtaining the target information data of the target ship through a crawler method, and the crawler methods include python data reading, web crawler, database query, etc.

[0054] The signal strength data can be used to calculate the signal strength data probability value through the signal strength management intelligent model; the communication interference degree data can be used to calculate the communication interference probability value through the communication interference degree management intelligent model; the communication equipment remaining power data can be used to calculate the communication equipment remaining power probability value through the communication equipment remaining power management intelligent model.

[0055] In a possible implementation, step S3 further includes:

[0056] C1: Acquire a plurality of pre-selected communication subjects, wherein the plurality of pre-selected communication subjects include a target communication subject, and the target communication subject is any one of the plurality of pre-selected communication subjects;

[0057] C2: judging whether the similarity value between the first communication feature phrase corresponding to the first communication text and the target communication subject is within a preselected threshold value;

[0058] C3: If the similarity value is within the preselected threshold, confirm that the preselected communication subject is the communication subject corresponding to the first communication text.

[0059] In the present embodiment, it is specifically necessary to explain that a preset subject database is constructed in advance to store multiple preset communication subjects, each preset communication subject includes communication feature words associated with the communication field corresponding to the preset communication subject, and the communication feature words corresponding to each preset communication subject can be obtained from the corresponding target information data through a crawler program. After classification according to different information data, the preset communication subject, the communication feature words associated with the communication field corresponding to the preset communication subject, and the corresponding relationship between the preset communication subject and the communication feature words associated with the communication field corresponding to the preset communication subject are stored in the database. Afterwards, when obtaining the first communication feature phrase corresponding to the first communication text, the similarity value between the first communication feature phrase and the target communication subject is calculated, and the target communication subject is any one of the multiple preset communication subjects; through programming calculation, each communication feature word in the first communication feature phrase is compared with each communication feature keyword corresponding to the preset communication subject one by one, and multiple calculation results are obtained, and then the multiple calculation results are calculated to obtain the arithmetic mean, which is the similarity value between the first communication feature phrase and the specific safety point; it is determined whether the similarity value is within the preselected threshold value. If the similarity value is within the preselected threshold value, it is confirmed that the preset communication subject is the communication subject corresponding to the first communication text. The preset similarity value is the statistical data of the target ship in previous years. This embodiment does not limit the setting of the preset similarity value.

[0060] In a possible implementation, step S3 also includes constructing an intelligent communication model: obtaining a communication processing unit corresponding to the target information data; constructing the intelligent communication model based on the communication processing unit; and calculating a first communication alarm probability corresponding to the first communication text based on the intelligent communication model.

[0061] In this embodiment, it should be specifically noted that the communication processing unit is a pre-built processing unit, and the specific manner in which the probability of the first communication alarm corresponding to the first communication text is calculated based on the intelligent communication model built by the communication processing unit is:

[0062]

[0063] P1 represents the first communication alarm probability corresponding to the first communication text, P1(Xq) represents the first probability value of signal strength data, P1(Xt) represents the first probability value of communication interference, P1(Xc) represents the first probability value of the remaining power of the communication device, and α represents the first communication alarm probability fitting value.

[0064] S4: Acquire a second communication text sent by the ship operator, where the second communication text is a communication text subsequent to the first communication text sent by the ship operator.

[0065] In this embodiment, it should be specifically explained that the second communication text sent by the ship operator is obtained, which is a communication text sent after the first communication text, and the second communication text and the first communication text are communication texts in the same dialog box.

[0066] S5: The second communication text is subjected to the preprocessing operation, where the preprocessing is used to obtain a second communication feature phrase corresponding to the second communication text.

[0067] In this embodiment, it should be specifically explained that the second communication feature phrase corresponding to the second communication text is obtained according to the same preprocessing operation as in step S2.

[0068] S6: Obtain preferred feature words in the second communication feature word group, and use the preferred feature words in the second communication feature word group to determine the preferred feature words in the first communication feature word group, the preferred feature words in the first communication feature word group are the first feature words, and the preferred feature words in the second communication feature word group are the second feature words, so as to construct a third communication feature word group through multiple first feature words.

[0069] In a possible implementation, step S6 also includes: by constructing a preset feature word database, to obtain multiple preset preferred feature words including a target feature word, the target feature word is any one of the preset multiple preferred feature words, and then, the target feature word is compared one by one with the second communication feature word group to confirm the preferred feature word in the second communication feature word group, that is, the second feature word.

[0070] In a possible implementation, step S6 further includes the following specific steps: determining the preferred feature words in the first communication feature word group by using the preferred feature words in the second communication feature word group:

[0071] E1: obtaining a preferred feature word in the first communication feature word group as the first feature word, and a preferred feature word in the second communication feature word group as the second feature word, wherein the first feature word is any preferred feature word among the preferred feature words in the first communication feature word group, and the second feature word is any preferred feature word among the preferred feature words in the second communication feature word group;

[0072] E2: by calculating the feature correlation value between the second feature word and the first feature word;

[0073] E3: Determine whether the feature correlation value is within the safety threshold range;

[0074] E4: If the feature association value is within the safety threshold range, the preferred feature words in the second communication feature word group are used to determine the preferred feature words in the first communication feature word group.

[0075] In this embodiment, it is specifically necessary to explain that the preferred feature word in the first communication feature word group is the first feature word, the preferred feature word in the second communication feature word group is the second feature word, the first feature word is any one of the preferred feature words in the first communication feature word group, the second feature word is any one of the preferred feature words in the second communication feature word group, and the feature correlation value of the second feature word and the first feature word is calculated, that is, the feature correlation value of each preferred feature word in the second communication feature word group and each preferred feature word in the first communication feature word group is calculated respectively. If any feature word in the first communication feature word group has any second feature word in the second communication feature word group and the feature correlation degree of the first feature word is within the safety threshold, the preferred feature word in the second communication feature word group is confirmed to determine the preferred feature word in the first communication feature word group; if any feature word in the first communication feature word group has any second feature word in the second communication feature word group and the feature correlation degree of the first feature word exceeds the safety threshold, then continue to determine whether there is a feature correlation value of the second communication feature word group with other first feature words and second feature words in the first communication feature word group. The above operation is performed on each first feature word in the first communication feature word group, the traversal is completed, and all communication feature words whose feature correlation degree between the second feature word and the first feature word is consistent are counted, that is, as the third communication feature word group. In the above scheme, the feature correlation degree between the second feature word and the first feature word means that there is a warning relationship between the second feature word and the first feature word.

[0076] S7: Obtain a second communication alarm probability corresponding to the third communication feature phrase according to the intelligent communication model through the third communication feature phrase.

[0077] In this embodiment, it should be specifically noted that the method of obtaining the second communication alarm probability corresponding to the third communication feature phrase through the intelligent communication model is consistent with the calculation method in the above step 3. The calculation method for obtaining the second communication alarm probability is as follows:

[0078]

[0079] P2 represents the second communication alarm probability, P2(Xq) represents the second probability value of signal strength data, P2(Xt) represents the second probability value of communication interference, P2(Xc) represents the second probability value of the remaining power of the communication device, and β represents the second communication alarm probability fitting value.

[0080] S8: Acquire an alarm processing model, and acquire an alarm evaluation value according to the alarm processing model through the first communication alarm probability and the second communication alarm probability; the alarm evaluation value is sent to the ship operator according to a preset feedback method.

[0081] In this embodiment, it is specifically necessary to explain the specific method of obtaining the alarm evaluation value:

[0082]

[0083] T is the alarm evaluation value, P2 represents the second communication alarm probability, and P1 represents the first communication alarm probability corresponding to the first communication text. The alarm evaluation value is based on the preset feedback method, mainly including but not limited to: any one of sound display, table display and picture display.

[0084] As attached Figure 2 FIG. 1 is a schematic diagram of an overall system of a marine distress alarm system based on ship wireless communication, and the system specifically includes:

[0085] A text acquisition module: in response to an alarm operation of wireless communication, acquires a first communication text sent by a ship operator; acquires a second communication text sent by the ship operator, the second communication text being a communication text subsequent to the first communication text sent by the ship operator;

[0086] Preprocessing module: a first communication text is preprocessed to obtain a first communication feature phrase corresponding to the first communication text; a second communication text is preprocessed to obtain a second communication feature phrase corresponding to the second communication text;

[0087] Communication analysis module: obtaining an intelligent communication model, and obtaining a first communication alarm probability corresponding to a first communication text through a first communication feature phrase group according to the intelligent communication model; obtaining preferred feature words in a second communication feature phrase group, and determining preferred feature words in a first communication feature phrase group by using preferred feature words in a second communication feature phrase group, wherein the preferred feature words in the first communication feature phrase group are first feature words, and the preferred feature words in the second communication feature phrase group are second feature words, so as to construct a third communication feature phrase group by using the first feature words; the intelligent communication model obtains a second communication alarm probability corresponding to a third communication feature phrase group by using the third communication feature phrase group;

[0088] Feedback module: obtains an alarm processing model, and obtains an alarm evaluation value according to the alarm processing model through a first communication alarm probability and a second communication alarm probability; the alarm evaluation value is sent to the ship operator according to a preset feedback method.

[0089] The present invention adopts the above method to obtain the first communication text sent by the ship operator, and preprocess the first communication text to obtain the first communication feature phrase corresponding to the first communication text, so as to obtain the first communication alarm probability corresponding to the first communication text according to the first communication feature phrase through the intelligent communication model. The second communication text sent by the ship operator is obtained, and the second communication text is preprocessed to obtain the preferred feature words in the second communication feature phrase, and the preferred feature words in the first communication feature phrase are determined by the preferred feature words in the second communication feature phrase, the preferred feature words in the first communication feature phrase are the first feature words, and the preferred feature words in the second communication feature phrase are the second feature words, so as to construct the third communication feature phrase through the first feature words;

[0090] According to the intelligent communication model, the second communication alarm probability corresponding to the third communication characteristic phrase is obtained through the third communication characteristic phrase. The alarm processing model is obtained, and the alarm evaluation value is obtained through the first communication alarm probability and the second communication alarm probability according to the alarm processing model; then, the alarm evaluation value is sent to the ship operator according to the preset feedback method. Through this method, the speed of ship wireless communication marine alarm and the accuracy of data analysis are greatly improved.

[0091] Secondly, in the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other;

[0092] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for marine distress alarm based on ship wireless communication, characterized in that: include: In response to an alarm operation of the wireless communication, obtaining a first communication text sent by a ship operator; Performing a preprocessing operation on the first communication text, wherein the preprocessing operation is used to obtain a first communication feature phrase corresponding to the first communication text; Acquire an intelligent communication model, and acquire a first communication alarm probability corresponding to the first communication text according to the intelligent communication model and the first communication feature phrase; Acquire a second communication text sent by a ship operator, where the second communication text is a communication text subsequent to the first communication text sent by the ship operator; performing the preprocessing operation on the second communication text, wherein the preprocessing is used to obtain a second communication characteristic phrase corresponding to the second communication text; Acquire the preferred characteristic words in the second communication characteristic phrase group, determine the preferred characteristic words in the first communication characteristic phrase group by using the preferred characteristic words in the second communication characteristic phrase group, the preferred characteristic words in the first communication characteristic phrase group are the first characteristic words, and the preferred characteristic words in the second communication characteristic phrase group are used as the second characteristic words, so as to construct a third communication characteristic phrase group by using the first characteristic words; Acquire, according to the intelligent communication model, a second communication alarm probability corresponding to the third communication feature phrase group through the third communication feature phrase group; An alarm processing model is obtained, and an alarm evaluation value is obtained according to the alarm processing model through the first communication alarm probability and the second communication alarm probability; the alarm evaluation value is sent to the ship operator according to a preset feedback method.

2. A method for marine distress alarm based on ship wireless communication according to claim 1, characterized in that: The obtaining of the intelligent communication model specifically includes: According to the first communication characteristic phrase, a classification operation is performed on the first communication text to obtain a communication subject corresponding to the first communication text, wherein the communication subject corresponding to the first communication text is target information data corresponding to the first communication text; The intelligent communication model corresponding to the communication subject is obtained in a preset communication database, and the preset communication database is used to store the corresponding relationship between the communication subject and the intelligent communication model.

3. A method for marine distress alarm based on ship wireless communication according to claim 2, characterized in that: The obtaining of the communication subject corresponding to the first communication text specifically includes: Acquire a plurality of preselected communication subjects, wherein the plurality of preselected communication subjects include a target communication subject, and the target communication subject is any one of the plurality of preselected communication subjects; Using a similarity value between a communication subject corresponding to the first communication text and the target communication subject, determining whether the similarity value is within a preselected threshold; If the similarity value is within the preselected threshold, the preselected communication subject is confirmed to be the communication subject corresponding to the first communication text.

4. A method for marine distress alarm based on ship wireless communication according to claim 2, characterized in that: The target information data includes signal strength data, communication interference degree data and communication equipment remaining power data, which are respectively denoted as Xq, Xt and Xs.

5. A method for marine distress alarm based on ship wireless communication according to claim 2, characterized in that: According to the intelligent communication model, before obtaining the communication subject corresponding to the first communication text through the first communication feature phrase, constructing the intelligent communication model specifically includes: Acquire a communication processing unit corresponding to the target information data; The intelligent communication model is constructed according to the communication processing unit.

6. A method for marine distress alarm based on ship wireless communication according to claim 4, characterized in that: Acquiring the target information data specifically includes: setting a time period through a counter, and acquiring the target information data of the target ship through a crawler method, wherein the crawler method includes python data reading, web crawler, and database query.

7. A method for marine distress alarm based on ship wireless communication according to claim 1, characterized in that: Determining the preferred feature words in the first communication feature word group by using the preferred feature words in the second communication feature word group specifically includes: Acquire a preferred feature word in the first communication feature word group as a first feature word, and a preferred feature word in the second communication feature word group as a second feature word, wherein the first feature word is any one of the preferred feature words in the first communication feature word group, and the second feature word is any one of the preferred feature words in the second communication feature word group; By calculating the feature correlation value between the second feature word and the first feature word; Determine whether the feature correlation value is within the safety threshold range; If the feature association value is within the safety threshold range, the preferred feature words in the second communication feature word group are used to determine the preferred feature words in the first communication feature word group.

8. A method for marine distress alarm based on ship wireless communication according to claim 1, characterized in that: The preset feedback method includes: any one of sound display, table display and picture display.

9. A marine distress alarm system based on ship wireless communication, used to implement the marine distress alarm method based on ship wireless communication according to any one of claims 1 to 8, characterized in that: A text acquisition module: in response to an alarm operation of wireless communication, acquires a first communication text sent by a ship operator; acquires a second communication text sent by the ship operator, wherein the second communication text is a communication text subsequent to the first communication text sent by the ship operator; Preprocessing module: the first communication text is preprocessed, the preprocessing operation is used to obtain the first communication feature phrase corresponding to the first communication text; the second communication text is preprocessed, the preprocessing is used to obtain the second communication feature phrase corresponding to the second communication text; Communication analysis module: obtaining an intelligent communication model, and obtaining a first communication alarm probability corresponding to the first communication text through the first communication feature phrase group according to the intelligent communication model; obtaining preferred feature words in the second communication feature phrase group, and determining preferred feature words in the first communication feature phrase group by using the preferred feature words in the second communication feature phrase group, wherein the preferred feature words in the first communication feature phrase group are first feature words, and the preferred feature words in the second communication feature phrase group are second feature words, so as to construct a third communication feature phrase group by using the first feature words; the intelligent communication model obtains a second communication alarm probability corresponding to the third communication feature phrase group through the third communication feature phrase group; Feedback module: obtain an alarm processing model, and obtain an alarm evaluation value according to the alarm processing model through the first communication alarm probability and the second communication alarm probability; the alarm evaluation value is sent to the ship operator according to a preset feedback method.

Images