A specific path generation method, system, device and computer storage medium
By classifying prepositions and processing entities in texts related to specific routes, structured data is generated and stored in a database. This solves the problem of time-consuming manual processing in railway freight dispatching systems and enables automated processing and accurate entry of information on specific routes.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CRSC RESEARCH & DESIGN INSTITUTE GROUP CO LTD
- Filing Date
- 2023-03-15
- Publication Date
- 2026-05-29
AI Technical Summary
In the existing technology, railway freight and dispatching information systems lack methods for automating the processing of specific route files, resulting in time-consuming and error-prone manual processing, making it difficult to achieve structured data entry and automated services for specific route information.
By classifying prepositions in specific route texts, processing entities in specific route rules, generating structured data, and storing it in a database, specific routes are generated based on specific route requests.
It has enabled automated processing of specific route information, reduced human error, improved processing efficiency and data entry accuracy, and supported automated services for traffic flow routes by various modules.
Smart Images
Figure CN116414835B_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of railway data processing technology, and specifically relates to a method, system, device, and computer storage medium for generating a specific route. Background Technology
[0002] In the information system for railway freight and dispatching, all modules rely on train routes, such as automatic marshalling plans, freight calculations, and customer marketing. The generation of specific routes involves a wide range of complex factors. The current specific route schemes of China Railway are mainly based on past practical experience, modified in conjunction with new lines and changes in transportation demand. Finally, the specific route documents issued by China Railway Corporation, along with supplementary and modified documents, are distributed to downstream departments and companies. However, the information systems of the downstream companies vary, and there is no unified structured data interface to process text files and input specific route information. Therefore, they all face the challenge of automatically inputting specific route-related documents into their own systems to meet the needs of various modules for train route requests.
[0003] Using manual analysis and processing of specific path files, and converting them from natural language to structured data, would be extremely time-consuming, prone to errors, and difficult to verify. It would require repeated manual labor every time the files were updated, making it a poor choice.
[0004] In existing technologies, for example, the literature "Research on Specific Route Language in Railway Traffic Flow Route Management System" proposes the necessity of a specific route compilation system and discusses its composition. Its technical solution description only includes the analysis results and description criteria of specific route files, and infers the feasibility of using specific route statement elements to describe specific route schemes in a computer system. This falls under the category of preliminary analysis of how to solve this natural language processing problem. Its specific route calculation method only provides the basic logic for how to use specific route description statements after they are available. Therefore, the entire work lacks a technical solution that can automatically parse the natural language of specific route files and generate specific route description statements that conform to computer logic.
[0005] Therefore, it is necessary to design a specific path generation method, system, device, and computer storage medium to solve the above-mentioned technical problems. Summary of the Invention
[0006] To address the above problems, this invention proposes a specific path generation method, wherein the method includes:
[0007] Classify prepositions contained within specific path rules in texts about specific paths;
[0008] Based on the classification results, the entities involved in specific path rules are processed as elements of structured specific path data;
[0009] The entity describing a specific path is disassembled and processed, and a digital set that can be judged by a programming language is generated based on the disassembled entity.
[0010] Based on the digitized set, specific path rules that already conform to the structured data format are stored in the database;
[0011] Based on a specific path request, if the database is hit, a specific path is generated.
[0012] Furthermore, the method also includes:
[0013] Before classifying the prepositions contained in the specific path rules, the specific path text and the dictionary data involved in the specific path text are read in.
[0014] Furthermore, the dictionary data includes the names, location information, and corresponding ID information of each entity involved in the specific path text.
[0015] Furthermore, when reading in text about a specific route, the following steps are also included:
[0016] Each specific route rule in a specific route text is stored as a list element.
[0017] Furthermore, after classifying the prepositions contained within a specific path rule, the classified specific path rules include the following types:
[0018] Class A: via / and / mutual / through, which includes subclasses that can be resolved using similar logic;
[0019] Class B: AND / mutual / interchange, which includes subclasses that can be resolved using similar logic;
[0020] Class C: via / loaded / via, which includes subclasses that can be parsed using similar logic;
[0021] Class D: Loaded / processed, which contains subclasses that can be resolved using similar logic;
[0022] Category E: Arrival and departure on this line.
[0023] Furthermore, the step of processing the entities involved in specific path rules based on the classification results as elements of structured specific path data includes:
[0024] Set up the first database table structure to store specific route rules;
[0025] A second database table structure is set up to store the entities that describe a specific route.
[0026] Furthermore, the step of storing the classified specific path rules into the database in the form of the corresponding entity's numeric ID, based on the digitized set, includes:
[0027] Based on the digitized set, the numerical ID of the line or station in the system is obtained by searching and comparing the line or station name;
[0028] Specific path rules with start point, end point, path, and passing point entities are stored in the database as the corresponding entity's numeric ID.
[0029] Furthermore, the step of determining, based on a specific path request, to generate a specific path when the database is hit includes:
[0030] For each specific route request that provides origin, destination, and cargo type, generate a shortest path;
[0031] In all the specific path rules, it is checked one by one to see if they match a specific path. If they match, the specific path is generated.
[0032] On the other hand, the present invention also provides a specific path generation system, wherein the system comprises:
[0033] The classification module is used to classify prepositions contained in specific path rules within specific path texts;
[0034] The entity processing module is used to process entities involved in specific path rules based on the classification results, and use them as elements of structured specific path data.
[0035] The disassembly module is used to disassemble the entity describing a specific path and generate a digital set that can be judged by a programming language based on the disassembled entity.
[0036] The storage module is used to store specific path rules that already conform to the structured data format into the database based on the digitized set;
[0037] The generation module is used to generate a specific path when the database is hit, based on a specific path request.
[0038] Furthermore, after classifying the prepositions contained within a specific path rule, the classified specific path rules include the following types:
[0039] Class A: via / and / mutual / through, which includes subclasses that can be resolved using similar logic;
[0040] Class B: AND / mutual / interchange, which includes subclasses that can be resolved using similar logic;
[0041] Class C: via / loaded / via, which includes subclasses that can be parsed using similar logic;
[0042] Class D: Loaded / processed, which contains subclasses that can be resolved using similar logic;
[0043] Category E: Arrival and departure on this line.
[0044] On the other hand, the present invention also provides an apparatus, wherein the apparatus comprises:
[0045] A processor and memory for storing computer programs that can run on the processor.
[0046] When the processor is used to run the computer program, it performs the steps of the method according to any one of claims 1 to 8.
[0047] On the other hand, the present invention also provides a computer storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method according to any one of claims 1 to 8.
[0048] This invention provides a method, system, device, and computer storage medium for generating specific routes. This invention processes all entities involved in a specific route file in a set manner, which makes it very convenient to determine whether a specific path request hits a specific route and how to generate a specific route according to the specific route specification.
[0049] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures pointed out in the description, claims and drawings. Attached Figure Description
[0050] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0051] Figure 1 A flowchart of a specific path generation method according to an embodiment of the present invention is shown.
[0052] Figure 2 A structural diagram of a specific path generation system according to an embodiment of the present invention is shown.
[0053] Figure 3A schematic diagram of the structure of a device according to an embodiment of the present invention is shown.
[0054] Figure 4 A schematic diagram of the structure of a computer storage medium according to an embodiment of the present invention is shown. Detailed Implementation
[0055] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0056] Furthermore, in this invention, the terms “first,” “second,” and other similar terms are not intended to imply any order, quantity, or importance, but are merely used to distinguish different elements.
[0057] In the prior art, for example, the patent with publication number CN114168637A, the entire patent mentions a predefined specific path language, but never explains how the language is defined, where it comes from, or whether it is manually entered or generated by an automated algorithm.
[0058] Based on the problems existing in the current technology, such as Figure 1 As shown, the present invention provides a method for generating a specific path, wherein the method includes:
[0059] Classify prepositions contained within specific path rules in texts about specific paths;
[0060] Based on the classification results, the entities involved in specific path rules are processed as elements of structured specific path data;
[0061] The entity describing a specific path is disassembled and processed, and a digital set that can be judged by a programming language is generated based on the disassembled entity.
[0062] Based on the digitized set, specific path rules that already conform to the structured data format will be stored in the database;
[0063] Based on a specific path request, if the database is hit, a specific path is generated.
[0064] A detailed description follows.
[0065] In one embodiment of the present invention, a method for generating a specific path includes step one:
[0066] Step 1: Before classifying the prepositions contained in the specific path rules, read in the specific path text and the dictionary data involved in the specific path text.
[0067] In this embodiment, the dictionary data includes the names, location information, and corresponding ID information of each entity involved in the specific route text, such as the names, latitude and longitude information, and distances between adjacent stations of railway bureaus, lines, and stations.
[0068] In this embodiment, when reading in specific route text, the following steps are also included:
[0069] Each specific route rule in a specific route text is stored as a list element.
[0070] In one embodiment of the present invention, a specific path generation method includes step two:
[0071] Step 2: Classify the prepositions contained in the specific path rules within the specific path text.
[0072] In this embodiment, based on the specific route file issued by China Railway Corporation (in the process of describing the algorithm, we generally do not care about the format or other content of the specific route file, but only focus on the specific route text corresponding to the text part of the specific route file), the words mainly used for sentence segmentation are: via, loaded to, according to, between each other, via, and, shortest route, arrival and departure of this line, etc.
[0073] If we use only common sense-based segmentation words to segment a specific path rule, it is easy to miss or make mistakes. Therefore, we need to use probabilistic language models or semantic segmentation deep learning models that have been pre-trained on a large amount of natural language corpus to assist in the segmentation of sentences.
[0074] This classification (i.e., step two: classifying the prepositions contained in the specific route rules in the specific route text) is mainly because specific routes impose restrictions on transportation from multiple aspects such as the starting point, intermediate points, destination, and cargo type. Different types of specific route rules correspond to different judgment logics, and the generation rules of specific routes are also different.
[0075] In this example, after classifying the prepositions contained within a specific path rule, the classified specific path rules include the following types:
[0076] Class A: via / and / mutual / through, including subclasses that can be resolved using similar logic:
[0077] a. Transported via set C through the type X between sets A and B.
[0078] b. Transported via type X from set A and set B through pivot C.
[0079] c. Transported via set C and pivot D through the type X between sets A and B.
[0080] Class B: AND / mutual / interchange, including subclasses that can be resolved using similar logic:
[0081] a. Type X of sets A and B is transported through set C.
[0082] b. The type X between set A and set B is transported via pivot C.
[0083] c. The type X between set A and set B is transported via set C, centered at point C.
[0084] Class C: Via / Load to / Via, which includes subclasses that can be parsed using similar logic:
[0085] a. Type X, loaded from set A into set B, is transported via set C.
[0086] b. Type X transported from set A to set B via pivot point C.
[0087] c. Type X, loaded from set A to set B, is transported via set C at fulcrum D;
[0088] Class D: Loaded / processed, containing subclasses that can be resolved using similar logic:
[0089] a. Type X, which is loaded from set A into set B, is transported via set C.
[0090] b. Type X of set A is transported to set B via pivot point C.
[0091] c. Type X, which is loaded from set A into set B, is transported via set C by pivot D.
[0092] Category E: Arrival and departure on this line:
[0093] a. Settlement A only handles arrivals and departures on this line.
[0094] In this embodiment, apart from the classifications summarized above, the other specific path rule descriptions can be obtained through simple set operations (e.g., A and B, A or B, etc.).
[0095] In one embodiment of the present invention, a specific path generation method includes step three:
[0096] Step 3: Based on the classification results (the results of the classification in Step 2), process the entities involved in the specific path rules as elements of the structured specific path data:
[0097] 1. In this embodiment, the entities extracted by the word segmentation model in step two, such as set A and type X, are elements describing a specific path rule. Broadly speaking, a specific path rule can be determined by the following descriptive fields: starting point, ending point, route, passing points, and cargo type. For example, such as:
[0098] Specific route rule: Loaded cars from Guangzhou Railway Bureau station A and stations south of it to station B or further are transported via line C to station D. Therefore, all traffic flow route requests originating at stations south of Guangzhou Railway Bureau station A and ending at stations further than station B, and whose cargo type is loaded car, will match this specific route rule. They will need to travel along line C and pass through station D to generate the route.
[0099] 2. Therefore, in this embodiment, two database table structures are set up for storing specific route data, one of which is a first database table structure and the other is a second database table structure, wherein:
[0100] Set up the first database table structure to store specific route rules, which mainly includes the following fields: specific route id, category id, starting point type, starting point entity id, ending point entity, ending point entity id, passing line type, passing line entity id, passing point type, passing point id, cargo type, and cargo id.
[0101] A second database table structure is set up to store the entities describing a specific route. This table is associated with the specific route rule table (the first database table structure) through the starting point entity ID, ending point entity ID, route entity ID, and route point ID. It mainly includes the following fields: entity type, entity ID, and entity data.
[0102] In one embodiment of the present invention, a specific path generation method includes step four:
[0103] Step 4: Decompose the entity describing the specific path and generate a set of digits that can be determined by a programming language based on the decomposed entities:
[0104] In a real-world path file, the entities depicted in step three can be very complex. Therefore, for example, the entities depicted can be categorized as follows (Table 1):
[0105] Table 1
[0106]
[0107]
[0108] The entities summarized in the above categories are parsed into a digital set with stations or lines as elements through the decomposition processing logic in Table 1.
[0109] All other description methods can be processed through simple set operations of the descriptions already categorized above.
[0110] In one embodiment of the present invention, a specific path generation method includes step five:
[0111] Step 5: Based on the digitized set, store the specific route rules, which now conform to the structured data format, into the database. It's important to note that through steps two, three, and four, each specific route rule statement can be broken down into the following fields in the first database table structure: Specific Route ID, Category ID, Starting Point Type, Starting Point Entity ID, Ending Point Entity ID, Ending Point Entity ID, Passing Line Type, Passing Line Entity ID, Passing Point Type, Passing Point ID, Cargo Type, and Cargo ID. Furthermore, each entity ID has a corresponding set of station or line IDs in the second database table structure. This table structure constitutes structured data, which can be easily processed by the program. Therefore, in addition to the entity IDs, the cargo type described by the specific route rule and the classification of the specific route based on prepositions are also stored in the database.
[0112] 1. After classifying the entities in step four and obtaining a digital set with routes or stations as elements through different processing logics, the digital set is used to obtain the digital ID of the route or station in the system (an information system that treats specific route text processing methods as a service) by searching and comparing the route or station names.
[0113] 2. Store specific path rules with start point, end point, path, and passing point entities in the database as the corresponding entity's numeric ID.
[0114] In one embodiment of the present invention, a specific path generation method includes step six:
[0115] Step Six: Based on the specific path request, determine whether the database is hit, and generate a specific path according to the following cases. For example, if the database is hit, generate a specific path:
[0116] 1. For each specific route request that provides origin, destination, and cargo type, generate a shortest path;
[0117] 2. Iterate through all the specific path rules to determine whether they match a specific path:
[0118] First, it can be easily determined whether the type of goods matches the specific route requirements. Second, the start and end point judgment logic is different for each category in step two, and the judgment and processing logic is as follows (Table 2):
[0119] Table 2
[0120]
[0121] 3. If not, search for the shortest path directly in the directed graph consisting of all railway stations and return the result.
[0122] 4. If a hit is found, a specific path will be generated according to the specified path rules, and the result will be returned.
[0123] In one embodiment of the present invention, such as Figure 2 As shown, a specific path generation system is also provided, wherein the system includes:
[0124] The classification module is used to classify prepositions contained in specific path rules within specific path texts;
[0125] The entity processing module is used to process entities involved in specific path rules based on the classification results, and use them as elements of structured specific path data.
[0126] The disassembly module is used to disassemble the entity describing a specific path and generate a digital set that can be judged by a programming language based on the disassembled entity.
[0127] The storage module is used to store specific path rules that already conform to the structured data format into the database based on the digitized set;
[0128] The generation module is used to generate a specific path when the database is hit, based on a specific path request.
[0129] In one embodiment of the present invention, such as Figure 3 As shown, an apparatus is also provided, wherein the apparatus includes:
[0130] A processor and memory for storing computer programs that can run on the processor.
[0131] When the processor runs the computer program, it executes the steps of the above method.
[0132] In one embodiment of the present invention, such as Figure 4 As shown, a computer storage medium is also provided, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the steps of the above method.
[0133] In summary, compared with manual processing methods, this invention is reusable, time-saving, and easily adaptable for secondary development to accommodate modifications. This invention processes all entities involved in a specific path file in a set manner, which greatly facilitates determining whether a specific path request matches a specific path and how to generate a specific path according to its specifications.
[0134] Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A specific path generation method, wherein, The method includes: Classify prepositions contained within specific path rules in texts about specific paths; Based on the classification results, the entities involved in specific path rules are processed as elements of structured specific path data; The entity describing a specific path is disassembled and processed, and a set of digits that can be determined by a programming language is generated based on the disassembled entity. Based on the digitized set, specific path rules that already conform to the structured data format are stored in the database; Based on a specific path request, determine if the database is hit and generate a specific path; Among them, after classifying the prepositions contained in specific path rules, the classified specific path rules include the following types: Class A: via / and / mutual / through, which includes subclasses that can be resolved using similar logic; Class B: AND / mutual / interchange, which includes subclasses that can be resolved using similar logic; Class C: via / loaded / via, which includes subclasses that can be parsed using similar logic; Class D: Loaded / processed, which includes subclasses that can be parsed using similar logic; Category E: Arrival and departure on this line; The step of determining, based on a specific path request, to generate a specific path when the database is hit includes: For each specific route request that provides origin, destination, and cargo type, generate a shortest path; In all the specific path rules, it is checked one by one to see if they match a specific path. If they match, the specific path is generated.
2. The method for generating a specific path according to claim 1, wherein, The method further includes: Before classifying the prepositions contained in the specific path rules, the specific path text and the dictionary data involved in the specific path text are read in.
3. The method for generating a specific path according to claim 2, wherein, The dictionary data includes the names, location information, and corresponding ID information of each entity involved in the specific path text.
4. The method for generating a specific path according to claim 2, wherein, When reading in text for a specific route, the following steps are also included: Each specific route rule in a specific route text is stored as a list element.
5. A method for generating a specific path according to any one of claims 1-3, wherein, The step of processing entities involved in specific path rules based on the classification results, as elements of structured specific path data, includes: Set up the first database table structure to store specific route rules; A second database table structure is set up to store the entities that describe a specific route.
6. A method for generating a specific path according to any one of claims 1-3, wherein, The step of storing the classified specific path rules into the database in the form of the corresponding entity's numeric ID, based on the digitized set, includes: Based on the digitized set, the numerical ID of the line or station in the system is obtained by searching and comparing the line or station name; Specific path rules with start point, end point, path, and passing point entities are stored in the database as the corresponding entity's numeric ID.
7. A specific path generation system, wherein, The system includes: The classification module is used to classify prepositions contained in specific path rules within specific path texts; The entity processing module is used to process entities involved in specific path rules based on the classification results, and use them as elements of structured specific path data. The disassembly module is used to disassemble the entity describing a specific path and generate a digital set that can be judged by a programming language based on the disassembled entity. The storage module is used to store specific path rules that already conform to the structured data format into the database based on the digitized set; The generation module is used to generate a specific path based on a specific path request, when the database is hit. Among them, after classifying the prepositions contained in specific path rules, the classified specific path rules include the following types: Class A: via / and / mutual / through, which includes subclasses that can be resolved using similar logic; Class B: AND / mutual / interchange, which includes subclasses that can be resolved using similar logic; Class C: via / loaded / via, which includes subclasses that can be parsed using similar logic; Class D: Loaded / processed, which contains subclasses that can be resolved using similar logic; Category E: Arrival and departure on this line; The step of determining, based on a specific path request, to generate a specific path when the database is hit includes: For each specific route request that provides origin, destination, and cargo type, generate a shortest path; In all the specific path rules, it is checked one by one to see if they match a specific path. If they match, the specific path is generated.
8. A device, wherein, The device includes: A processor and memory for storing computer programs that can run on the processor. When the processor is used to run the computer program, it performs the steps of the method according to any one of claims 1 to 6.
9. A computer storage medium having a computer program stored thereon, wherein, When executed by a processor, the computer program performs the steps of the method according to any one of claims 1 to 6.