Method for constructing knowledge graph based on grammar teaching content

Abstract

The application discloses a knowledge graph construction method based on grammar teaching content, and relates to the technical field of knowledge graph construction.The application solves the problems of fuzzy boundaries of similar grammar, difficulties in correlation relation analysis and difficulty in forming a structured knowledge system.The application adopts a two-step strategy of "partition construction-integration optimization", first constructs a tree branch graph in each similar partition according to the value column sorting, makes the same grammar content form a unified branch and the different content form hierarchical sub-branches, and ensures the clear context of grammar knowledge in a single partition;then realizes the organic integration of multi-partition graph through the partition characteristic mean sorting, and finally forms a complete knowledge graph which presents the independence of each grammar unit and highlights the correlation between different grammar systems, provides a panoramic cognitive framework from a micro grammar point to a macro grammar system for users, and greatly improves the systematicness and understandability of grammar knowledge.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of knowledge graph construction, in particular to a knowledge graph construction method based on grammar teaching content. BACKGROUND

[0002] In the field of grammar teaching, with the continuous enrichment of teaching resources, the characteristic grammar rules and supporting examples show the characteristics of large quantity and various types, and their effective organization and efficient application become the key to improving teaching quality.

[0003] However, the prior art has significant limitations in grammar knowledge management:

[0004] On the one hand, the classification of characteristic grammar depends on artificial experience or simple keyword division, lacks unified quantitative standard, and leads to fuzzy boundaries of similar grammar, difficult to comb the correlation, difficult to form a structured knowledge system, which is not conducive to systematic explanation by teachers, and also brings obstacles to learners to understand grammar logic;

[0005] On the other hand, the retrieval method of grammar knowledge is relatively traditional, mostly using item-by-item traversal or basic keyword matching, when facing massive content, not only the retrieval process is time-consuming, but also it is difficult to quickly locate the target grammar point and its deep associated information, which seriously restricts the teaching efficiency and knowledge acquisition speed. In addition, the existing knowledge graph construction method lacks adaptability in the context of grammar teaching, and does not fully consider the hierarchical and associated properties of grammar rules, resulting in a loose structure of the constructed graph, which cannot accurately reflect the internal logic between different characteristic grammars.

[0006] These problems make it difficult for grammar teaching resources to fully play their value, and there is an urgent need for a technical solution that can achieve accurate classification of characteristic grammar, systematic graph construction and efficient retrieval to meet the actual needs of grammar teaching for knowledge structured management and rapid application. SUMMARY

[0007] In view of the deficiencies of the prior art, the present application provides a knowledge graph construction method based on grammar teaching content, which solves the problems of fuzzy boundaries of similar grammar, difficult to comb the correlation, and difficult to form a structured knowledge system.

[0008] To achieve the above purpose, the present application realizes the following technical scheme: a knowledge graph construction method based on grammar teaching content, comprising the following steps:

[0009] Step 1, value processing is performed on different types of characteristic grammar of grammar teaching content, different value columns associated with different characteristic grammar are confirmed, and then the confirmed value columns are classified, and the associated characteristic grammar is classified at the same time, and a plurality of different similar partitions are confirmed, and the specific method is:

[0010] According to the preset assignment table, the assignment associated with different syntax keywords is confirmed, and the assignment corresponding to each position syntax keyword is sorted according to the sorting mode of the characteristic syntax, and the assignment column associated with the corresponding characteristic syntax is confirmed;

[0011] Confirm the position characteristics associated with each assignment column: confirm the assignment associated with different positions in the corresponding assignment column, extract the first assignment associated with each assignment, sort the extracted several groups of first assignments, confirm the first assignment column, and then extract the second assignment associated with each assignment, and sort the extracted several groups of second assignments to confirm the second assignment column., and so on, select and sort the assignment at each same arrangement position, and confirm the assignment column associated with the corresponding order;

[0012] Confirm several characteristic syntaxes: confirm the first assignment column associated with each characteristic syntax, and confirm the value difference associated between each first assignment column. The value associated with different sorting positions in the first assignment column is denoted as S i , where i represents different sorting positions, and the value S i at the same sorting position is processed by difference value, and the pending difference value is confirmed, which is greater than or equal to 0. The several groups of pending difference values confirmed at each sorting position are processed by mean value, and the confirmed value is locked. If the confirmed value is less than or equal to Y1, the two groups of characteristic syntaxes are divided into the same type of syntax. If the confirmed value is greater than Y1, the same type of syntax is not marked;

[0013] Again, the same type of syntax is again confirmed, and this time the confirmation process combines the second assignment column associated with different characteristic syntaxes and other assignment columns associated subsequently. The same confirmation method of the first assignment column is used to confirm the same type of syntax. The different characteristic syntaxes are again classified, so that several characteristic syntaxes of the same type of syntax are divided into multiple different classification partitions, and the characteristic syntaxes associated with each same type of partition are marked.

[0014] Step 2: Construct a knowledge graph for the characteristic syntax associated with each same type of partition. According to the different characteristic syntaxes associated with each same type of partition, and according to the different assignment columns associated with different characteristic syntaxes, construct a knowledge graph for several characteristic syntaxes, complete the knowledge graph construction process associated with each same type of partition, and the specific method is:

[0015] Confirm the characteristic syntax belonging to the same type of partition, confirm the assignment column associated with each characteristic syntax, and arrange the several characteristic syntaxes associated according to the sorting mode of the assignment column from small to large. According to the determined arrangement order, complete the knowledge graph construction process of several characteristic syntaxes of the same type of partition;

[0016] The average value of the assignment columns associated with each same type partition is processed as the partition characteristic of the corresponding same type partition, the knowledge graphs of the same type partitions are integrated in the order of the partition characteristics from small to large, and the complete knowledge graph is obtained.

[0017] Step three, reprocessing the constructed complete knowledge graph, confirming the column associated with different characteristic grammars from top to bottom, and marking the assignment column associated with each characteristic grammar according to the column, determining the strongest associated column, and recording the strongest associated column, the specific way is:

[0018] From the complete knowledge graph, the column of different characteristic grammars is confirmed from top to bottom, and the column is marked as Z q , wherein q represents different characteristic grammars, and Z q =1, 2, …, n.

[0019] The assignment column associated with the corresponding characteristic grammar and the column Z q are verified: the assignment associated with different grammar keywords in the assignment column is confirmed, and the total sum value is confirmed by randomly summing the associated several assignments, a plurality of random summation processes are performed, and the total sum value associated with each random summation process is processed by difference value processing, and Cz q =|Z q -Total sum value| confirms the difference value Cz q associated with different total sum values. q From the confirmed several difference values Cz q , select the minimum value Cz q min, and record the random summation process associated with Cz q min as the confirmation process, the assignment summed in the confirmation process is recorded as the selected assignment, and the selected assignment is sorted in the order from front to back to generate the strongest associated column belonging to the corresponding characteristic grammar.

[0020] The strongest associated column recorded by each characteristic grammar is preferentially confirmed, and the different assignments in the strongest associated column are summed to confirm the summation parameter.

[0021] The column consistent with the summation parameter is confirmed from the complete knowledge graph, and the column is used as the index source, and the grammar index is performed from top or bottom to lock the corresponding characteristic grammar.

[0022] The related content associated with the locked characteristic grammar is displayed.

[0023] The present application provides a knowledge graph construction method based on grammar teaching content. Compared with the prior art, the following beneficial effects are achieved:

[0024] The present application introduces a multi-order assignment column classification mechanism, converts the characteristic grammar into a quantifiable assignment sequence through a preset assignment table, and realizes progressive classification of the characteristic grammar through hierarchical comparison of the first-order, second-order and subsequent assignment columns, combined with difference mean value judgment; this hierarchical classification logic not only retains the integrity of the grammar feature, but also accurately captures the subtle differences between different grammars, making the grouping of similar grammars more logical and consistent, effectively avoiding the boundary ambiguity problem caused by relying on subjective judgment in traditional classification, and laying a structured and standardized foundation for the construction of a knowledge graph.

[0025] The two-step strategy of "partition construction-integration optimization" is adopted, first, the tree branch graph is constructed in each similar partition according to the assignment column sorting, so that the same grammar content forms a unified branch and the different content forms a hierarchical sub-branch, ensuring that the grammar knowledge in a single partition is clear; then, the organic integration of the multi-partition graph is realized through the partition feature mean value sorting, and finally the complete knowledge graph is formed, which not only presents the independence of each grammar unit, but also highlights the relevance between different grammar systems, providing a panoramic cognitive framework from the micro grammar point to the macro grammar system, greatly improving the systematicness and understandability of grammar knowledge.

[0026] The design of the strongest correlation column breaks through the traditional column-by-column traversal retrieval mode, and locks the optimal correlation sequence through random summation and difference calculation with the column, so that each characteristic grammar has a unique "retrieval tag". This design changes the linear scanning of grammar retrieval to precise positioning based on feature values, and users can directly lock the target column through the summation parameter of the strongest correlation column, and then quickly match the characteristic grammar and related example content combined with the upper and lower indexes, significantly reducing the retrieval time; especially for teaching scenarios that contain a large number of grammar rules and examples, this mechanism can help learners or teachers quickly locate the target content, effectively improve the knowledge acquisition efficiency, and enhance the practicality and convenience of grammar teaching. BRIEF DESCRIPTION OF DRAWINGS

[0027] Figure 1 The present application provides a method flowchart. DETAILED DESCRIPTION

[0028] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0029] Please refer to Figure 1 The present application provides a knowledge graph construction method based on grammar teaching content, including the following steps:

[0030] Step one, the different types of feature grammar in the teaching content of grammar is assigned, the different assignment column associated with different feature grammar is confirmed, and the assignment column confirmed is classified, and the associated feature grammar is classified at the same time, and a plurality of different feature grammar is classified, and the different feature grammar is divided into different partitions according to the classification process, and the specific classification process can effectively divide the different feature grammar into different partitions to perform the specific division of the same type of partition;

[0031] Among them, the specific way of classifying feature grammar is:

[0032] According to the preset assignment table, the assignment associated with different grammar keywords is confirmed, and the assignment corresponding to each position grammar keyword is sorted according to the sorting method of feature grammar, and the assignment column associated with the corresponding feature grammar is confirmed. Specifically, in the corresponding feature grammar, for example, the keywords of the corresponding grammar of "subject-predicate-object" are all associated with different assignments, which can be confirmed in the corresponding assignment table. Assuming that the assignment associated with the subject is 11, the assignment associated with the predicate is 12, and the assignment associated with the subsequent object is 13, then the assignment column associated with the corresponding feature grammar is 11-12-13.

[0033] Confirm the position feature associated with each assignment column: confirm the assignment associated with different positions in the corresponding assignment column, extract the first assignment associated with each assignment, sort the extracted several groups of first assignment, confirm the first assignment column, extract the second assignment associated with each assignment, and sort the extracted several groups of second assignment, confirm the second assignment column, and so on. Select and sort the assignment at each same arrangement position to confirm the assignment column associated with the corresponding stage. Specifically, taking the assignment column 11-12-13 associated as an example, the first assignment is confirmed first, which is "1, 1, 1". Then the first assignment column confirmed is 111. The second assignment column is confirmed, and the second assignment column confirmed is "123".

[0034] Classify the same type of several feature grammars: confirm the first assignment column associated with each feature grammar, and confirm the value difference associated between each first assignment column. The value associated with different sorting positions in the first assignment column is recorded as S i Where i represents different sorting positions, and the value S iThe difference value is processed, and the pending difference value is confirmed, which is greater than or equal to 0 (that is, the difference value needs to be processed after the absolute value processing), the average value of the pending difference value of each sorting position is processed, the confirmed value is locked, and the two groups of feature syntaxes with a confirmed value less than or equal to Y1 are divided into the same type of syntax, otherwise, the same type of syntax is not marked;

[0035] The same type of syntax is again divided into the same type of syntax, and this time the confirmation process is combined with the second-order value column associated with the different feature syntaxes and the subsequent other value columns associated with the different feature syntaxes. The first value column is used to confirm the same type of syntax, and the different feature syntaxes are again classified (that is, the division is performed again based on the first classification), so that the same type of syntax is divided into a plurality of different classification partitions, and the feature syntaxes associated with each same type of partition are marked;

[0036] Specifically, each feature syntax has different value columns, and according to the confirmation process of the corresponding value, each value column has a first value column, a second-order value column, and other subsequent order value columns. First, according to the first value column, the same type of syntax is preliminarily marked in the corresponding marking partition, and then the second-order value column and other related value columns are confirmed, so as to lock different classification partitions, thereby dividing a plurality of different feature syntaxes into a plurality of different same type of partitions, and each same type of partition has different syntax content, so that each syntax content can be effectively divided.

[0037] Step 2: Construct a graph for the feature syntax associated with each same type of partition. According to the different feature syntaxes associated with each same type of partition, the different value columns associated with the different feature syntaxes are used to construct a graph for a plurality of feature syntaxes, complete the knowledge graph construction process associated with each same type of partition. Specifically, in different partitions, different feature syntaxes are associated. In order to complete the corresponding graph classification construction process between different feature syntaxes, the value column associated with each feature syntax is used for construction.

[0038] Among them, the specific way of constructing a graph for a plurality of feature syntaxes is:

[0039] Confirming the feature syntaxes belonging to the same type of partition, confirming the assignment columns associated with each feature syntax, and arranging the associated feature syntaxes in ascending order of the assignment columns, completing the knowledge graph construction process of the feature syntaxes of the same type of partition according to the determined arrangement order. Specifically, when constructing the knowledge graph, branch construction is sequentially performed according to the order of each feature syntax from front to back. The same syntax content is identified by the same branch. The subsequent different syntax content of the same syntax content in the pre-order is sequentially sorted by multiple branches. The overall assignment column associated with the feature syntax at the top of the sorting is smaller, and the assignment column gradually increases downwards, and so on. The graph construction process is similar to the existing tree graph, and therefore is not described in detail here.

[0040] The mean value of each assignment column associated with each same type of partition is processed as the partition feature of the corresponding same type of partition. The knowledge graphs of the same type of partitions are integrated in ascending order of the partition features to obtain a complete knowledge graph.

[0041] Step three, reprocessing the constructed complete knowledge graph (that is, the overall graph associated with all same type of partitions), confirming the column associated with different feature syntaxes from top to bottom, and marking the assignment column associated with each feature syntax according to the column, determining the strongest associated column, and recording the strongest associated column to facilitate fast indexing of the feature syntax in the later stage and improve the indexing rate.

[0042] Specifically, the strongest associated column associated with each feature syntax is confirmed as follows:

[0043] From the complete knowledge graph, the column of different feature syntaxes is confirmed from top to bottom, and the column is marked as Z q where q represents different feature syntaxes, and Z q =1, 2, …, n, Z q =1 represents that the corresponding feature syntax is located in the first column, Z q =2 represents that the corresponding feature syntax is located in the second column. According to the ascending order from top to bottom, the different columns associated with different feature syntaxes (that is, corresponding to different Arabic numerals) can be sequentially confirmed.

[0044] The assignment column associated with the corresponding feature syntax and the column Z q are verified: the assignment associated with different syntax keywords in the assignment column is confirmed, and the total sum value is confirmed by randomly summing the associated assignments. A plurality of random summation processes are performed, and the total sum value associated with each random summation process is compared with the column Z qThe difference value processing is performed using Cz q =|Z q The difference value Cz associated with the different total value is confirmed q From the confirmed several difference values Cz q , the minimum value Cz q min is selected, and the random summation process associated with Cz q min is recorded as a confirmed process, the assignment summed in the confirmed process is recorded as a selected assignment, and the selected assignment is sorted in the order from front to back to generate the strongest associated column belonging to the corresponding feature syntax.

[0045] After the strongest associated column of each feature syntax is confirmed, the specific way of subsequent content indexing includes:

[0046] When indexing, the strongest associated column recorded by each feature syntax is confirmed first, and different assignments in the strongest associated column are summed to confirm the summation parameter.

[0047] The column consistent with the summation parameter is confirmed from the complete knowledge graph, and the column is used as the index source to index the syntax from top or bottom to lock the corresponding feature syntax.

[0048] The related content associated with the locked feature syntax is then displayed (specifically, each feature syntax is not only a single feature syntax, but also includes a large amount of example content, which needs to be displayed here. The corresponding example content is convenient for the searcher to understand the feature syntax).

[0049] Specifically, the original retrieval method is to confirm different feature syntaxes from top to bottom in the corresponding knowledge graph, identify whether the confirmed feature syntax is consistent with the syntax content of the search, if consistent, output, if not consistent, continue to search, but this retrieval method is too slow from top to bottom, and cannot achieve a faster and more effective retrieval effect. According to the retrieval method of the embodiment, the column is quickly confirmed according to the indicated strongest associated column, and the top and bottom indexing methods are used to quickly confirm the associated feature syntax, so as to quickly lock the associated content, which has a faster indexing rate, higher efficiency, and can achieve the fastest and optimal retrieval effect.

[0050] Some data in the above formula are dimensionless numerical calculations, and the contents not described in detail in the specification all belong to the prior art known to those skilled in the art.

[0051] The above examples are only used to illustrate the technical method of the present application but not limit the present application. Although the present application is described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present application can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present application.

Claims

1.A method for constructing a knowledge graph based on grammar teaching content, characterized in that, It comprises the following steps: Step one, the characteristic grammar of different types of grammar teaching content is valued, the different value columns associated with different characteristic grammars are confirmed, and the value columns confirmed are classified, and the associated characteristic grammar is classified at the same time, and several different same type partitions are confirmed; Step two, the associated characteristic grammar of each same type partition is constructed, the different characteristic grammars associated in each same type partition are classified according to the different value columns associated with different characteristic grammars, and the knowledge graph associated with each same type partition is constructed; Step three, the complete knowledge graph constructed is reprocessed, the column where the different characteristic grammars are associated is confirmed from top to bottom, and the value column associated with each characteristic grammar is marked according to the column, the strongest associated column is determined, and the strongest associated column is recorded; The specific way of confirming the strongest associated column is: From the complete knowledge graph, the column where the different feature grammar is located is identified from top to bottom, and the column where it is located is marked as Z q where q represents different feature grammars, and Z q =1, 2, …, n; Assign the column associated with the corresponding feature syntax and the column Z it belongs to. q Perform validation: Identify the assignments associated with different syntax keywords from the assignment column, randomly sum the associated assignments, confirm the total sum, execute several random summation processes, and compare the total sum associated with each random summation process with the corresponding column Z. q Perform interpolation using Cz. q =|Z q -Sum Values ​​| Identify the differences Cz associated with different sum values. q Then, from the confirmed differences Cz q In the middle, select the minimum value Cz q min, and Cz q The random summation process associated with min is called the confirmation process. The summation assignment in the confirmation process is called the selected assignment. The selected assignment is sorted from front to back to generate the strongest association column associated with the corresponding feature syntax. The step three also includes subsequent retrieval steps, which specifically include: The strongest associated column recorded by each characteristic grammar is confirmed first, the different values in the strongest associated column are summed up, the sum parameter is confirmed, the column consistent with the sum parameter is confirmed from the complete knowledge graph, and the corresponding characteristic grammar is locked by taking the column as the index source and indexing from top or bottom; The related content associated with the locked characteristic grammar is displayed. In step one, the specific way of classifying the characteristic grammar is: 2.The method of claim 1, wherein, According to the preset value table, the value associated with different grammar keywords is confirmed, and the value corresponding to each position grammar keyword is sorted according to the sorting method of characteristic grammar, and the value column associated with the corresponding characteristic grammar is confirmed; The position characteristics associated with each value column are confirmed: the values associated with different positions in the corresponding value column are confirmed, and the first value associated with each value is extracted, the extracted several groups of first values are sorted, the first value column is confirmed, the second value associated with each value is extracted, and the extracted several groups of second values are sorted, the second value column is confirmed, and so on. The values at each same arrangement position are selected and sorted, and the value column associated with the corresponding order is confirmed; The same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, and the same type grammar is classified again, Confirming the same kind of several characteristic grammars: confirming the first assignment column associated with each characteristic grammar, and confirming the value difference associated between each first assignment column, and recording the value S associated with different sorting positions in the first assignment column i , where i represents different sorting positions, and then recording the value S at the same sorting position i , and performing difference processing to confirm the pending difference, and the pending difference ≥ 0, and performing mean processing on several groups of pending differences confirmed at each sorting position, and locking the confirmed value, and dividing the two groups of characteristic grammars with the confirmed value ≤ Y1 into the same kind of grammars; ​ 3.The method of claim 2, wherein, ​ 4.The method of claim 1, wherein, ​ Confirming the feature grammar belonging to the same type of partition, confirming the assignment column associated with each feature grammar, and arranging the associated several feature grammars in ascending order of the assignment column, completing the knowledge graph construction process of several feature grammars of the same type of partition according to the determined arrangement order; Then, the mean value of the several assignment columns associated with each same type of partition is processed as the partition feature of the corresponding same type of partition, and the knowledge graphs of the several same type of partitions are integrated in ascending order of the partition feature, to obtain a complete knowledge graph.

Images