Training outline digital management method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of data processing, and provides a training outline digital management method and device, electronic equipment and a storage medium, and the method comprises the steps: carrying out the structured processing of each training outline text, so as to generate a structured training outline corresponding to each training outline text, and enabling different training outline texts to correspond to different training objects; generating each training outline knowledge graph based on each structured training outline; and pushing each training outline knowledge graph to a training planning system to constrain a training plan formulated by the training planning system for the training target to meet the requirements of constraint items in the training outline knowledge graph corresponding to the training target. According to the invention, the training outline knowledge graph is associated with the training planning system, so that when the user makes the training plan, the data content of the training outline in the training outline knowledge graph can be obtained through the training planning system, and the problems of information isolated island and difficult data integration are solved; therefore, the formulated training plan is ensured to meet the requirements of the training outline.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular to a training outline digital management method and device, electronic equipment and storage medium. BACKGROUND

[0002] In the prior art, the management and release of training outlines (for example, training outlines for flight training, training outlines for driving school automobile training, etc.) are based on traditional training outline texts, and the relationship between data in the training outline texts cannot be clearly determined. When a user uses a training outline to specify a training plan, there is an information island, and data integration is difficult, so that the training plan cannot be guaranteed to meet the requirements of the training outline. SUMMARY

[0003] The present application provides a training outline digital management method, device, electronic equipment and storage medium to solve the problem of information island and difficult data integration in the prior art training outline management method, so that the training plan cannot be guaranteed to meet the requirements of the training outline.

[0004] The present application provides a training outline digital management method, comprising: structurally processing each training outline text to generate a structured training outline corresponding to each training outline text, different training outline texts corresponding to different training targets; generating a training outline knowledge graph based on each structured training outline; pushing each training outline knowledge graph to a training plan system to constrain the training plan system to develop a training plan for the training target that meets the requirements of the constraint item in the training outline knowledge graph corresponding to the training target.

[0005] According to the training outline digital management method provided by the present application, before generating each training outline knowledge graph based on each structured training outline, it further comprises: filling in missing values in the data in each structured training outline; performing a deduplication process on the data in each structured training outline after filling in the missing values to remove duplicate data items.

[0006] According to the training outline digital management method provided by the present application, before generating each training outline knowledge graph based on each structured training outline, it further comprises: editing each structured training outline after deduplication based on user input and generating an editing report; generating each training outline knowledge graph based on each structured training outline, comprising: generating a corresponding training outline knowledge graph based on each structured training outline after editing.

[0007] The training outline digital management method provided by the present application comprises the following steps: For the structured training outlines of different training subjects of the same type, the same content parts are extracted to generate shared training outlines, and different content parts form differential training outlines.

[0008] The training outline digital management method provided by the present application comprises the following steps: The entity recognition, attribute extraction and relationship extraction operations are performed on each structured training outline to obtain the triples of all entities, attributes and relationships in each structured training outline. For all triples of any structured training outline, the first similarity of the attributes corresponding to the different entity names in any two triples is calculated, and the entity names are unified in the case that the first similarity is greater than a first threshold. In the case that the entity names of two triples are the same and the corresponding attributes and / or attribute values are different, the second similarity of the corresponding attributes and the third similarity of the attribute values are calculated, and the entity name is prompted to be renamed in the case that the second similarity and the third similarity are both less than a second threshold, wherein the second threshold is less than the first threshold. Based on the triples in each structured training outline, the corresponding training outline knowledge graph is generated.

[0009] The training outline digital management method provided by the present application comprises the following steps: The constraint items of each training outline knowledge graph are pushed to the training plan system to establish the association relationship between the constraint items and the corresponding check items in the training plan system, and the training plan meets the requirement of the constraint items in the training outline knowledge graph corresponding to the training subject in the case that the check items meet the corresponding constraint items.

[0010] The training outline digital management method provided by the present application comprises the following steps: After the training outline knowledge graph is updated, the updated content in the training outline knowledge graph is automatically pushed to the training plan system.

[0011] The present application further provides a training outline digital management device comprising the following modules: The training outline structured module is configured to structure each training outline text to generate a structured training outline corresponding to each training outline text, and different training outline texts correspond to different training targets; The knowledge graph generation module is configured to generate a training outline knowledge graph based on each structured training outline; The knowledge graph pushing module is configured to push each training outline knowledge graph to a training plan system to constrain the training plan formulated by the training plan system for the training target to meet the requirements of the constraint items in the training outline knowledge graph corresponding to the training target.

[0012] The present application also provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the training outline digital management method according to any one of the above when executing the program.

[0013] The present application also provides a non-transitory computer readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the training outline digital management method according to any one of the above.

[0014] The training outline digital management method, device, electronic device, and storage medium provided by the present application structure each training outline text to generate a structured training outline corresponding to each training outline text, and different training outline texts correspond to different training targets; generate a training outline knowledge graph based on each structured training outline; and push each training outline knowledge graph to a training plan system to constrain the training plan formulated by the training plan system for the training target to meet the requirements of the constraint items in the training outline knowledge graph corresponding to the training target. That is, the training outline knowledge graph is associated with the training plan system, and the user can obtain the data content of the training outline in the training outline knowledge graph through the training plan system when formulating the training plan, thereby solving the problems of information silos and data integration difficulties, and ensuring that the formulated training plan meets the requirements of the training outline. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor based on these drawings.

[0016] Figure 1 is a flowchart of the training outline digital management method provided by the present application.

[0017] Figure 2It is a structural schematic view of the training outline digital management device provided by the present application.

[0018] Figure 3 It is a structural schematic view of the electronic device provided by the present application. DETAILED DESCRIPTION

[0019] To make the objectives, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below with reference to the drawings in the present application. Obviously, the described embodiments are some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0020] The training outline digital management method of the embodiment of the present application, as shown in the figure, comprises steps S110 to S130. Figure 1

[0021] Step S110: structuring processing is performed on each training outline text to generate a structured training outline corresponding to each training outline text, and different training outline texts correspond to different training targets. The training outline text can be any format of text, for example, a word document or a PDF document, etc. In addition to text strings, the training outline text can also include tables and pictures (which can also contain text descriptions). The training outline text usually includes training subjects, training contents, training conditions, training methods and training purposes, etc.

[0022] In this step, the structuring processing is to extract the corresponding content according to the keywords of the training subjects, training contents, training conditions, training methods and training purposes (for example, in the flight training, one of the keywords of the training conditions is weather conditions, and the content after the weather conditions is the corresponding content of the training conditions), and convert it into a data structure of a structured database for storing the content of the training outline text in a related format. The training subjects, training contents, training conditions, training methods and training purposes can be fields in the database. For the pictures, the text in the pictures can be recognized by OCR first, and then the keywords in the text are recognized to determine which item of the training subjects, training contents, training conditions, training methods and training purposes the picture represents.

[0023] Different training targets have different training outlines. For example, for the flight training, different types of civil aviation aircraft have different training outline texts, and for example, for the automobile driving training, different types of vehicles (such as small cars, minibuses, buses, medium trucks and large trucks, etc.), the corresponding training subjects, training contents, training conditions, training methods and training purposes are different for different training targets, ​Step S120: generating each training outline knowledge graph based on each structured training outline. The generation step of the training outline knowledge graph includes knowledge extraction, knowledge fusion, knowledge reasoning, knowledge representation and knowledge graph application. In the knowledge extraction stage, entities can be extracted by BERT model + rule matching, attributes and relationships can be extracted by rule matching, and finally the training outline knowledge graph is obtained.

[0024] The training outline knowledge graph at least includes a triple of a training constraint item, wherein the entity is a training subject, the attribute is a related description of a training purpose corresponding to the training subject, and the relationship is at least one of a training content, a training condition and a training method corresponding to the training subject. For example, for automobile driving training, the entity is a training subject (such as subject one) and the training content of subject one (traffic law), the attribute is a related description of the training purpose of subject one, and the relationship is the training content (content description), the training method (course learning traffic law) and the training condition (learning site) for realizing subject one.

[0025] Step S130: pushing each training outline knowledge graph to the training plan system, so that the training plan system formulates a training plan for the training target in accordance with the requirements of the constraint items in the training outline knowledge graph corresponding to the training target.

[0026] In this step, after the training outline knowledge graph is pushed to the training plan system, when the training plan system formulates a training plan, the training plan must meet the requirements of the constraint items in the training outline knowledge graph. If not, the training plan cannot pass: for example, when formulating a training plan for automobile driving, the learning site of subject one is not mentioned, which does not meet the requirements of the constraint items in the training outline knowledge graph.

[0027] The training outline digital management method of the embodiment generates a structured training outline corresponding to each training outline text by structuring each training outline text, different training outline texts correspond to different training targets; generates each training outline knowledge graph based on each structured training outline; and pushes each training outline knowledge graph to the training plan system, so that the training plan system formulates a training plan for the training target in accordance with the requirements of the constraint items in the training outline knowledge graph corresponding to the training target. That is, the training outline knowledge graph is associated with the training plan system. When a user formulates a training plan, the data content of the training outline in the training outline knowledge graph can be obtained through the training plan system, solving the problems of information island and data integration difficulty, so as to ensure that the formulated training plan meets the requirements of the training outline.

[0028] In some embodiments, before generating each training outline knowledge graph based on each structured training outline, the following steps are further included: The data in each of the structured training outlines is subjected to missing value filling.

[0029] The data in each of the structured training outlines after missing value filling is subjected to deduplication processing to remove duplicate data items.

[0030] After the structured processing of the training outline text, some data may be missing in the training outline text itself, for example, the description of the training condition is missing, or data is missing in the structured outline due to an abnormality in the structured process. Specifically, missing items in the structured training outline are checked, missing value filling is prompted, and the filling content input by the user is received as the missing value to fill in the missing items. After missing value filling, each piece of data in the structured training outline is checked, and if there is duplicate data, deduplication processing is performed. After deduplication, the structured training outline is stored in the corresponding structured database.

[0031] In this embodiment, the structured training outline is subjected to missing value filling and deduplication processing, especially for filling the missing values instead of deleting the data corresponding to the missing values, which ensures the integrity of the training outline data and makes the subsequent training outline knowledge graph more accurate.

[0032] In some embodiments, before generating each training outline knowledge graph based on each of the structured training outlines, the method further comprises: Based on the user input, each of the structured training outlines after deduplication is edited, and an editing report is generated.

[0033] Based on the editing of each structured training outline, each training outline knowledge graph is generated based on each of the structured training outlines, including generating a corresponding training outline knowledge graph based on each of the edited structured training outlines.

[0034] In this embodiment, editing the training outline includes revising an existing structured training outline, proofreading the structured training outline, or formulating a new structured training outline for a different training subject of the same type. During editing, the user's editing input is received through a user interface, and the structured training outline is edited in the background. Online collaborative editing by multiple people can be supported, and auxiliary tools can be used to support content matching analysis, intelligent proofreading, etc., and an intelligent auxiliary revision and proofreading report can be automatically generated. All operations during the outline editing process are recorded and can be traced back.

[0035] In this embodiment, the editing of the structured training outline is realized through interaction with the user, so that the content of the edited structured training outline is more accurate, which is conducive to the generation of the subsequent training outline knowledge graph. Moreover, by formulating a new structured training outline for a different training subject of the same type, the same content of different training subjects can be shared, thereby more efficiently generating training outlines of the same type but different training subjects.

[0036] In some embodiments, after structuring each training outline text to generate a structured training outline corresponding to each training outline text, the method further includes: for structured training outlines of different training targets of the same type, extracting the common content to generate a shared training outline, and forming differential training outlines for the different content. For example, for buses with different numbers of seats (45, 50, or 55 seats), the type of training target is always a bus, but the body size of each training target is different, resulting in slight differences in the corresponding training outlines, but the majority of the content is the same. Therefore, in this embodiment, for structured training outlines of different training targets of the same type, extracting the common content to generate a shared training outline and forming differential training outlines for the different content reduces the size of the structured training outline and saves storage space.

[0037] Specifically, a training target type flag is set for the shared training outline, and a target ID is set for the differential training outline. A binding relationship table between the type flag and multiple target IDs is created. When a structured training outline for a certain training target is needed later, the corresponding type flag is found in the binding relationship table according to its target ID. The corresponding shared training outline and differential training outline are obtained according to the type flag and target ID respectively, so as to form a complete structured training outline for the training target.

[0038] In some embodiments, generating knowledge graphs for each training syllabus based on each of the structured training syllabus includes: Entity recognition, attribute and relation extraction operations are performed on each of the structured training outlines to obtain triples of all entities, attributes and relations in each structured training outline.

[0039] For all triples in any structured training syllabus, the entity names are unified if the first similarity of the corresponding attributes of the entities with different entity names in any two triples is greater than a first threshold (e.g., the first threshold is 80%).

[0040] If two triples have the same entity name but different corresponding attributes and / or attribute values, calculate the second similarity of the corresponding attributes and the third similarity of the attribute values. If both the second similarity and the third similarity are less than the second threshold (e.g., 60%), prompt the user to rename the entity name. The second threshold is less than the first threshold.

[0041] Based on the triples in each of the structured training outlines, a corresponding training outline knowledge graph is generated.

[0042] In the embodiment, the knowledge graph generation method avoids redundant triples, and more clearly distinguishes triples with the same or similar entity names but different in fact, so that the generated training outline knowledge graph is more accurate.

[0043] In some embodiments, each of the training outline knowledge graphs is pushed to a training plan system to constrain the training plan formulated by the training plan system for a training target to meet the requirements of the constraint items in the corresponding training outline knowledge graph of the training target, including: The constraint items of each of the training outline knowledge graphs are pushed to the training plan system to establish an association relationship between the constraint items and corresponding check items in the training plan system, and in the case that the check items meet the corresponding constraint items, the training plan meets the requirements of the constraint items in the corresponding training outline knowledge graph of the training target.

[0044] Specifically, the constraint items of the training outline knowledge graph are triples, and the check items in the training plan system are contents about training subjects, training contents, training conditions, training methods and training purposes extracted based on the training plan content, and the training subjects, training contents, training conditions, training methods and training purposes in the check items are associated with the training subjects, training contents, training conditions, training methods and training purposes in the constraint items, respectively. When a user formulates a training plan in the training plan system, the training plan system takes the training subjects, training contents, training conditions, training methods and training purposes in the training plan as check items to check whether they meet the requirements of the corresponding training subjects, training contents, training conditions, training methods and training purposes of the constraint items.

[0045] In the embodiment, by pushing the training outline knowledge graph to the training plan system, the information silos between systems are broken down, and it is ensured that the formulated training plan meets the requirements of the training outline.

[0046] In some embodiments, after each of the training outline knowledge graphs is pushed to the training plan system, the updated content in the training outline knowledge graph is automatically pushed to the training plan system after the training outline knowledge graph is updated. In the embodiment, only the updated content in the training outline knowledge graph is pushed, and while realizing the annual training plan update based on the training outline knowledge graph, the amount of interactive data with the training plan system is saved.

[0047] The training outline digital management device provided by the present application is described below, and the training outline digital management device described below can be referred to each other corresponding to the training outline digital management method described above.

[0048] The training outline digital management device of the embodiment of the present application, as shown in Figure 2 includes: The training outline structured module 210 is configured to structure each training outline text to generate a structured training outline corresponding to the training outline text, and different training outline texts correspond to different training targets.

[0049] The knowledge graph generation module 220 is configured to generate a training outline knowledge graph based on each structured training outline.

[0050] The knowledge graph pushing module 230 is configured to push each training outline knowledge graph to a training plan system, so that the training plan formulated by the training plan system for a training target meets the requirements of the constraint items in the training outline knowledge graph corresponding to the training target.

[0051] The training outline digital management device according to the embodiment of the present application structures each training outline text to generate a structured training outline corresponding to the training outline text, and different training outline texts correspond to different training targets. The training outline knowledge graph is generated based on each structured training outline. Each training outline knowledge graph is pushed to a training plan system, so that the training plan formulated by the training plan system for a training target meets the requirements of the constraint items in the training outline knowledge graph corresponding to the training target. That is, the training outline knowledge graph is associated with the training plan system. When formulating a training plan, the user can obtain the data content of the training outline in the training outline knowledge graph through the training plan system, thereby solving the problem of information island and data integration difficulty, and ensuring that the formulated training plan meets the requirements of the training outline.

[0052] In some embodiments, the training outline digital management device further comprises a training outline preprocessing module configured to, before generating each training outline knowledge graph based on each structured training outline, fill in missing values in the data in each structured training outline, and perform deduplication processing on the data in each structured training outline after filling in the missing values to remove duplicate data items.

[0053] In some embodiments, the training outline digital management device further comprises a training outline editing module configured to, before generating each training outline knowledge graph based on each structured training outline, edit each structured training outline after deduplication based on user input, and generate an editing report.

[0054] The knowledge graph generation module 220 is specifically configured to generate a corresponding training outline knowledge graph based on each structured training outline after editing.

[0055] In some embodiments, the training outline digital management device further comprises a training outline extraction module configured to, after the structural processing of each training outline text to generate the structured training outline corresponding to each training outline text, extract the same content part to generate a shared training outline and the different content part to form a differential training outline for different training subjects of the same type.

[0056] In some embodiments, the knowledge graph generation module 220 is specifically configured to: perform entity recognition, attribute and relationship extraction operations on each of the structured training outlines to obtain triples of all entities, attributes and relationships in the structured training outlines; for all triples of any structured training outline, calculate a first similarity of the attributes corresponding to different entity names in any two triples, and in the case that the first similarity is greater than a first threshold, unify the entity names; in the case that the entity names of two triples are the same and the corresponding attributes and / or attribute values are different, calculate a second similarity of the corresponding attributes and a third similarity of the attribute values, and in the case that the second similarity and the third similarity are both less than a second threshold, prompt to rename the entity name, the second threshold being less than the first threshold; generate a corresponding training outline knowledge graph based on the triples in each of the structured training outlines.

[0057] In some embodiments, the knowledge graph pushing module 230 is specifically configured to push the constraint items of each of the training outline knowledge graphs to the training plan system to establish an association relationship between the constraint items and the corresponding check items in the training plan system, and in the case that the check items meet the corresponding constraint items, the training plan meets the requirements of the constraint items in the training outline knowledge graph corresponding to the training subject.

[0058] In some embodiments, the training outline digital management device further comprises an update pushing module configured to, after pushing each of the training outline knowledge graphs to the training plan system, automatically push the updated content in the training outline knowledge graph to the training plan system after the training outline knowledge graph is updated.

[0059] Figure 3 An entity structure diagram of an electronic device is shown as follows, Figure 3As shown, the electronic device can include a processor 310, a communications interface 320, a memory 330, and a communications bus 340, wherein the processor 310, the communications interface 320, and the memory 330 communicate with each other through the communications bus 340. The processor 310 can invoke the logical instructions in the memory 330 to execute the training outline digital management method, which includes: Structural processing is performed on each training outline text to generate a structured training outline corresponding to each training outline text, and different training outline texts correspond to different training targets.

[0060] Based on each of the structured training outlines, a training outline knowledge graph is generated.

[0061] Each of the training outline knowledge graphs is pushed to a training plan system to constrain the training plan system to develop a training plan for the training target to meet the requirements of the constraint items in the training outline knowledge graph corresponding to the training target.

[0062] In addition, the logical instructions in the memory 330 described above can be implemented in the form of a software function unit and sold or used as a standalone product, which can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes instructions for making a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0063] On the other hand, the present application also provides a computer program product, which includes a computer program, the computer program can be stored on a non-transitory computer readable storage medium, and the computer program is executed by a processor, and the computer can execute the training outline digital management method provided by the above-mentioned methods, which includes: Structural processing is performed on each training outline text to generate a structured training outline corresponding to each training outline text, and different training outline texts correspond to different training targets.

[0064] Based on each of the structured training outlines, a training outline knowledge graph is generated.

[0065] The training program knowledge graph is pushed to a training plan system, so that the training plan formulated by the training plan system for a training target meets the requirements of the constraint items in the training program knowledge graph corresponding to the training target.

[0066] In another aspect, the present application also provides a non-transitory computer readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the training program digitization management method provided by the above method, the method comprising: The training program texts are structured to generate structured training programs corresponding to the training program texts, different training program texts corresponding to different training targets.

[0067] The training program knowledge graphs are generated based on the structured training programs.

[0068] The training program knowledge graphs are pushed to a training plan system, so that the training plan formulated by the training plan system for a training target meets the requirements of the constraint items in the training program knowledge graph corresponding to the training target.

[0069] The device embodiments described above are only schematic, wherein the units illustrated as separate components can or can not be physically separated, and the components illustrated as units can or can not be physical units, i.e., can be located in one place or distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the present embodiment. Those skilled in the art can understand and implement without creative labor.

[0070] From the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be implemented by means of software plus necessary general hardware platforms, and of course can also be implemented by hardware. Based on such understanding, the above technical solutions, essentially or in other words, the part that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0071] It should be pointed out finally that the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit the same; and although the present application has been described in detail with reference to the foregoing embodiments, it should be appreciated by those skilled in the art that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features thereof can be replaced equivalently; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for digital management of training outlines, characterized in that, include: Each training outline text is processed into a structured form to generate a structured training outline corresponding to each training outline text. Different training outline texts correspond to different training targets. Knowledge graphs for each training outline are generated based on the structured training outlines described above. The training outline knowledge graphs are pushed to the training planning system to ensure that the training plans formulated by the training planning system for the training targets meet the requirements of the constraints in the training outline knowledge graphs corresponding to the training targets.

2. The digital management method for training outlines according to claim 1, characterized in that, Before generating the knowledge graphs for each training outline based on the aforementioned structured training outlines, the process also includes: Missing values ​​are filled in the data in each of the structured training outlines; The data in each structured training outline after missing values ​​are filled are deduplicated to remove duplicate data items.

3. The digital management method for training outlines according to claim 2, characterized in that, Before generating the knowledge graphs for each training outline based on the aforementioned structured training outlines, the process also includes: Edit the deduplicated structured training outlines based on user input and generate an editing report; Based on the aforementioned structured training outlines, knowledge graphs for each training outline are generated, including: Based on the edited structured training outlines, a corresponding training outline knowledge graph is generated.

4. The method for digital management of training outlines according to claim 1, characterized in that, After structuring each training outline text to generate a structured training outline corresponding to each training outline text, the process also includes: For structured training outlines of the same type but different training targets, extract the common content to generate a shared training outline, and form differentiated training outlines for the different content.

5. The digital management method for training outlines according to claim 1, characterized in that, Based on the aforementioned structured training outlines, knowledge graphs for each training outline are generated, including: Entity recognition, attribute and relation extraction operations are performed on each of the structured training outlines to obtain triples of all entities, attributes and relations in each structured training outline; For all triples of any structured training outline, calculate the first similarity of the corresponding attributes of entities with different entity names in any two triples, and unify the entity names if the first similarity is greater than the first threshold. When two triples have the same entity name but different corresponding attributes and / or attribute values, calculate the second similarity of the corresponding attributes and the third similarity of the attribute values. If both the second similarity and the third similarity are less than the second threshold, prompt to rename the entity name. The second threshold is less than the first threshold. Based on the triples in each of the structured training outlines, a corresponding training outline knowledge graph is generated.

6. The method for digital management of training outlines according to any one of claims 1 to 5, characterized in that, The training outline knowledge graphs are pushed to the training planning system to constrain the training plans formulated by the training planning system for the training targets to meet the requirements of the constraints in the training outline knowledge graphs corresponding to the training targets, including: The constraints of each training outline knowledge graph are pushed to the training plan system to establish the association between the constraints and the corresponding check items in the training plan system. When the check items meet the corresponding constraints, the training plan meets the requirements of the constraints in the training outline knowledge graph corresponding to the training target.

7. The digital management method for training outlines according to claim 6, characterized in that, After pushing the aforementioned training outline knowledge graphs to the training plan system, the following is also included: After the training outline knowledge graph is updated, the updated content in the training outline knowledge graph will be automatically pushed to the training plan system.

8. A digital management device for training syllabi, characterized in that, include: The training outline structuring module is used to process each training outline text in a structured manner to generate a structured training outline corresponding to each training outline text. Different training outline texts correspond to different training targets. The knowledge graph generation module is used to generate knowledge graphs for each training outline based on the structured training outlines. The knowledge graph push module is used to push the knowledge graphs of each training outline to the training plan system, so as to constrain the training plan formulated by the training plan system for the training target to meet the requirements of the constraint items in the knowledge graph of the training outline corresponding to the training target.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the training syllabus digital management method as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the training syllabus digital management method as described in any one of claims 1 to 7.

Images