An operation information determination method and apparatus

Abstract

Embodiments of the present application disclose a method for determining operation information, which comprises: receiving information to be queried, performing word segmentation on the information to be queried to obtain first words; performing word segmentation on operation names in an operation description mapping table to obtain second words of each operation name; wherein the operation description mapping table represents the relationship between operation names in a text to be processed and operation information; determining a target operation name based on the first words and the second words; determining target operation information of the information to be queried from the text to be processed based on the target operation name and the operation description mapping table, and outputting the target operation information. Embodiments of the present application also disclose a device for determining operation information.

Description

Technical Field

[0001] This application relates to operational information determination technology in the field of document processing, and more particularly to an operational information determination method and device. Background Technology

[0002] Currently, the widely available electronic documents such as equipment instruction manuals and operation manuals contain a large amount of explanatory text about operation (referred to as operation instructions or operation information), which has high application value.

[0003] In related technologies, when determining the operation instructions for a target operation from an electronic document, the operation and its instructions are extracted from any segment of text in the electronic document. The user then confirms whether the extracted operation instructions are those for the target operation. If the extracted operation instructions are not those for the target operation, the next segment of text in the document is extracted until the extracted operation instructions are confirmed to be those for the target operation. This method can only analyze and extract operation instructions from one segment of text at a time, resulting in low efficiency and low accuracy in extracting the operation instructions (i.e., operation information) for the target operation. Summary of the Invention

[0004] To address the aforementioned technical problems, this application aims to provide a method and apparatus for determining operation information, thereby resolving the issues of low efficiency and low accuracy in extracting operation information.

[0005] The technical solution of this application is implemented as follows:

[0006] A method for determining operation information, the method comprising:

[0007] Receive the query information, perform word segmentation on the query information, and obtain the first word;

[0008] The operation names in the operation description mapping table are segmented to obtain the second word of each operation name; wherein, the operation description mapping table represents the relationship between the operation names and operation information in the text to be processed;

[0009] Based on the first word and the second word, determine the target operation name;

[0010] Based on the target operation name and the operation description mapping table, the target operation information of the query information is determined from the text to be processed, and the target operation information is output.

[0011] The method in the above scheme further includes:

[0012] Obtain the text to be processed, and determine the first statement from the text to be processed;

[0013] Obtain the part-of-speech tagging parameters of the first statement;

[0014] Based on the part-of-speech tagging parameters of the first statement, the first statement is filtered to obtain a set of target statements;

[0015] Based on the second statement in the target statement set, determine the operation instruction mapping table for the text to be processed.

[0016] In the above scheme, determining the first statement from the text to be processed includes:

[0017] Identify the statements in the text to be processed, and determine the part-of-speech of the words in the statements in the text to be processed;

[0018] The first statement is obtained by extracting statements containing both verbs and nouns from the text to be processed.

[0019] In the above scheme, obtaining the part-of-speech tagging parameters of the first statement includes:

[0020] Extract the words from the first statement and construct a dependency parsing tree based on the words in the first statement;

[0021] Based on the dependency parsing tree, the part-of-speech parameters of the first statement are determined.

[0022] In the above scheme, the step of filtering the first statement based on the part-of-speech tagging parameters of the first statement to obtain the target statement set includes:

[0023] Based on the part-of-speech association parameters, a third word is determined from the words in the first statement; wherein the part of speech of the third word is a verb, and there is no part-of-speech association relationship pointing to the third word in the first statement; there are words in the first statement that have a verb-object relationship with the third word, but there are no words that have a subject-predicate relationship with the third word;

[0024] Based on the statement corresponding to the third word, the third statement is determined from the first statement;

[0025] Based on the position information of the third statement in the text to be processed, the target statement set is determined from the third statement.

[0026] In the above scheme, determining the target statement set from the third statement based on the position information of the third statement in the text to be processed includes:

[0027] Obtain the line number of each third statement in the text to be processed, the first-line indentation distance of the paragraph containing each third statement, and the paragraph number containing each third statement.

[0028] Based on the first-line indentation distance, the line number, and the paragraph number, determine the pointing relationship between the fourth statement and the third statement;

[0029] Based on the pointing relationships between the fourth statements, construct a directed tree of the fourth statements;

[0030] Based on the directed tree, determine the hierarchical relationship between the fourth statements;

[0031] Based on the hierarchical relationship and the fourth statement, the target statement set is determined.

[0032] In the above scheme, determining the target statement set based on the hierarchical relationship and the fourth statement includes:

[0033] Each node in the directed tree is labeled with the first label;

[0034] For each directed tree, based on the hierarchy, determine the i-th node with the first label, the m-th node with the first label, and the n-th node with the first label; wherein the level of the m-th node is greater than the level of the i-th node; the level of the n-th node is the same as the level of the i-th node; wherein i, m, and n are all positive integers;

[0035] For each directed tree, based on the statement corresponding to the i-th node, the statement corresponding to the m-th node, and the statement corresponding to the n-th node, the nodes in each directed tree are updated to determine multiple target directed trees;

[0036] Based on the statements corresponding to the nodes of the multiple target directed trees, the target statement set is determined.

[0037] In the above scheme, the step of updating the nodes in each directed tree based on the statement corresponding to the i-th node, the statement corresponding to the m-th node, and the statement corresponding to the n-th node to determine multiple target directed trees includes:

[0038] Determine the first lexical commonality between the words of the statement corresponding to the i-th node and the words of the statement corresponding to the m-th node;

[0039] Determine the second lexical commonality between the words of the statement corresponding to the nth node and the words of the statement corresponding to the mth node;

[0040] The third word share is determined based on the first word share and the second word share.

[0041] Determine the fourth lexical commonality degree between the words of the statement corresponding to the i-th node and the words of the statement corresponding to the parent node of the i-th node;

[0042] Based on the third and fourth word commonness, the nodes in the directed tree are updated to determine the target directed tree; wherein, the statement corresponding to the node of the target directed tree is the second statement.

[0043] In the above scheme, determining the operation instruction mapping table of the text to be processed based on the second statement in the target statement set includes:

[0044] From multiple target directed trees, determine candidate nodes with the same statement, and determine the number of descendant nodes of the candidate nodes;

[0045] From the candidate nodes, determine the target node that has the largest number of descendant nodes;

[0046] A correspondence is established between the statement corresponding to the target node and the identifiers of the statements corresponding to the descendant nodes of the target node to obtain an operation description mapping table; wherein, the statement corresponding to the target node in the operation description mapping table represents the operation name; and the identifier in the operation description mapping table represents the operation information corresponding to the operation name.

[0047] An operation information determining device, the device comprising: a processor, a memory, and a communication bus;

[0048] The communication bus is used to realize the communication connection between the processor and the memory;

[0049] The processor is used to execute a program for determining operation information in memory to perform the following steps:

[0050] Receive the query information, perform word segmentation on the query information, and obtain the first word;

[0051] The operation names in the operation description mapping table are segmented to obtain the second word of each operation name; wherein, the operation description mapping table represents the relationship between the operation names and operation information in the text to be processed;

[0052] Based on the first word and the second word, determine the target operation name;

[0053] Based on the target operation name and the operation description mapping table, the target operation information of the query information is determined from the text to be processed, and the target operation information is output.

[0054] The operation information determination method and device provided in this application embodiment receive query information, perform word segmentation on the query information to obtain a first word; segment the operation names in the operation description mapping table to obtain a second word for each operation name; wherein, the operation description mapping table represents the relationship between operation names and operation information in the text to be processed; determine the target operation name based on the first word and the second word; determine the target operation information of the query information from the text to be processed based on the target operation name and the operation description mapping table, and output the target operation information. In this way, the target operation information of the query information is determined according to the operation description mapping table, taking into account the distribution of the target operation information in the text to be processed, and eliminating the need for extracting operation information from the entire text each time to determine the target operation information, as is the case in related technologies, thus improving the accuracy and efficiency of determining the target operation information. Attached Figure Description

[0055] Figure 1 This is a flowchart illustrating an operation information determination method provided in an embodiment of this application.

[0056] Figure 2 A flowchart illustrating an operation information determination method provided in another embodiment of this application;

[0057] Figure 3 A schematic diagram of the structure of a dependency parsing tree provided in an embodiment of this application;

[0058] Figure 4 A schematic diagram of another dependency parsing tree structure provided in this application embodiment;

[0059] Figure 5 A schematic diagram of the processing flow of an operation information determination method provided in an embodiment of this application;

[0060] Figure 6 A schematic diagram of the processing flow of an operation information determination method provided in an embodiment of this application;

[0061] Figure 7 This is a schematic diagram of the structure of an operation information determination device provided in an embodiment of this application. Detailed Implementation

[0062] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0063] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0064] This application provides an operation information determination method, which is applied to an operation information determination device, such as... Figure 1As shown, the method includes the following steps:

[0065] Step 101: Receive the query information, perform word segmentation on the query information, and obtain the first word.

[0066] The information to be queried can be information entered by the user, which is a statement entered by the user.

[0067] In this embodiment of the application, the information to be queried is segmented into words to obtain the words of the information to be queried, and the words of the information to be queried are used as the first word so that the subsequent process can determine the operation information of the information to be queried based on the first word.

[0068] Step 102: Segment the operation names in the operation description mapping table to obtain the second word of each operation name.

[0069] The operation description mapping table represents the relationship between operation names and operation information in the text to be processed. The operation description mapping table includes the identifiers of the operation names and the corresponding operation information; each identifier uniquely identifies the operation information corresponding to the operation name.

[0070] In one feasible implementation, the identifier of the operation information corresponding to the operation name can represent the position of the operation information corresponding to the operation name in the text to be processed.

[0071] In this embodiment of the application, the operation names (statements) in the operation description mapping table can be segmented to obtain the second word corresponding to each operation name, so as to determine the operation information of the information to be queried based on the second word.

[0072] Step 103: Determine the target operation name based on the first word and the second word.

[0073] In this embodiment of the application, the first word of the information to be queried can be matched with the second word of each operation name in the operation description mapping table to obtain the matching result. The target word is then determined based on the matching result, and the target operation name is determined based on the target word. The matching result can be represented by the matching degree.

[0074] Specifically, the first word of the query information can be matched with the second word of each operation name in the operation description mapping table, and the second word with the highest matching degree can be determined. This second word with the highest matching degree is taken as the target word, and the operation name containing the target word is taken as the target operation name. Here, the matching degree is the number of words that the query information and the operation name have in common.

[0075] Step 104: Based on the target operation name and operation description mapping table, determine the target operation information of the information to be queried from the text to be processed, and output the target operation information.

[0076] In this embodiment, the identifier of the operation information corresponding to the target operation name can be determined from the operation description table based on the target operation name, and the target operation information can be determined from the operation description mapping table according to the identifier of the operation information corresponding to the target operation name, and then the target operation information can be output. The identifier of the operation information corresponding to the target operation name can represent the location of the operation information corresponding to the target operation name.

[0077] It should be noted that if the operation instruction mapping table contains operation information corresponding to each operation name, the operation information corresponding to the target operation name can also be directly determined from the operation instruction mapping table based on the target operation name.

[0078] Once the target operation information is determined, it can be displayed in different ways. The display methods can be to generate target text based on the target operation information and the information to be queried, and display the target text and the position of the target operation information in the text to be processed; or to mark the target operation information in the text to be processed and display the text to be processed.

[0079] In one feasible implementation, the information to be queried can be "statement 1", the target operation information can be information composed of statements 3 and 4, and the target text generated based on the information to be queried and the target operation information can be "the queried operation: statement 1, after querying, consists of the following steps: statement 3; statement 2", where statement 1, statement 2 and statement 3 all refer to the content of the statements; in another feasible implementation, the target operation information in the text to be processed can be highlighted and the highlighted area in the text to be processed can be displayed.

[0080] The operation information determination method provided in this application embodiment receives query information, performs word segmentation on the query information to obtain a first word; segments the operation names in the operation description mapping table to obtain a second word for each operation name; wherein, the operation description mapping table represents the relationship between operation names and operation information in the text to be processed; based on the first word and the second word, the target operation name is determined; based on the target operation name and the operation description mapping table, the target operation information of the query information is determined from the text to be processed, and the target operation information is output. In this way, the target operation information of the query information is determined according to the operation description mapping table, taking into account the distribution of the target operation information in the text to be processed, and eliminating the need for extracting operation information from the entire text each time to determine the target operation information, as is the case in related technologies, thus improving the accuracy and efficiency of determining the target operation information.

[0081] Based on the foregoing embodiments, this application provides a method for determining operation information, referring to... Figure 2 As shown, the method includes the following steps:

[0082] Step 201: The operation information determination device acquires the text to be processed and determines the first statement from the text to be processed.

[0083] The text to be processed can be an electronic document such as a user manual or electronic manual for the device; the text to be processed contains a large number of operation instructions; the operation instructions can refer to a sequence of actions consisting of several steps to control a certain "object" in order to reach a certain state of the object; the operation can be called the operation name, and the operation instructions can be called the operation information; the first statement is a statement that contains both a verb and a noun.

[0084] In one feasible implementation, the operation name can be "take soda from the refrigerator", and the operation description refers to the specific steps of "taking soda from the refrigerator": "The first step can be to open the refrigerator; the second step can be to take out the soda; the third step can be to close the refrigerator."

[0085] In this embodiment, words in the text to be processed can be filtered to obtain sentences containing both verbs and nouns, thus obtaining the first sentence. It should be noted that there are two ways to obtain the text to be processed: active acquisition and passive acquisition. Active acquisition refers to the operation information determining device actively downloading the text to be processed via the network; passive acquisition refers to the operation information determining device receiving a download instruction from the user and then downloading the text to be processed via the network, or the user sending the text to be processed to the operation information determining device via a terminal.

[0086] In step 201, determining the first statement from the text to be processed can be achieved through the following steps:

[0087] a1. The operation information determination device determines the statements in the text to be processed and determines the part of speech of the words in the statements in the text to be processed.

[0088] In this embodiment of the application, the operation information determining device can extract sentences from the text to be processed based on punctuation marks in the text to be processed, and perform word segmentation on the sentences to be processed to obtain the words in each sentence of the text to be processed. Then, it performs grammatical analysis on the words in each sentence of the text to be processed to determine the part of speech of each word in the text to be processed. The part of speech may include, but is not limited to, verbs or nouns. The type of punctuation marks may include Chinese punctuation marks and English punctuation marks.

[0089] In one feasible implementation, the punctuation marks can be the period in English punctuation and / or the period in English punctuation. If there are 100 Chinese punctuation marks (periods) in the text to be processed and there are no English punctuation marks (periods), then 100 sentences can be extracted from the text to be processed.

[0090] a2. The operation information determination device obtains the first statement from the statements in the text to be processed, which contains both verbs and nouns.

[0091] In this embodiment of the application, based on the part of speech of each word in the text to be processed, the statements in the text to be processed are filtered, and the first statement is obtained from the multiple statements in the text to be processed that simultaneously contain verbs and nouns.

[0092] Step 202: The operation information determination device obtains the part-of-speech association parameters of the first statement.

[0093] The part-of-speech (POS) parameters of the first statement represent the dependency relationship between the words in the first statement, which can also be called the association relationship. In a statement, if one word modifies another word, the modifier is called the subordinate word, and the modified word is called the dominant word. The relationship between the two is the dependency relationship. The POS parameters include, but are not limited to, the verb-object relationship or subject-predicate relationship between words.

[0094] In this embodiment of the application, the operation information determining device can perform word segmentation on the first statement to obtain the words of the first statement, and then analyze the part of speech of the words in the first statement to determine the part of speech of the words in the first statement and the dependency relationship between the words in the first statement.

[0095] It should be noted that step 202 can be achieved through the following steps:

[0096] b1. The operation information determination device obtains the words in the first statement and constructs a dependency parsing tree based on the words in the first statement.

[0097] In this embodiment, the first sentence can be segmented to obtain the words in the first sentence, and generative syntactic analysis can be performed on the words in the first sentence to obtain the dependency parsing tree corresponding to the first sentence. It should be noted that generative syntactic analysis is an important task in natural language processing, and its goal is to analyze the grammatical structure of a sentence and represent it as an easily understandable structure; this structure can be a tree structure. The dependency parsing tree represents the grammatical relationships between words in the sentence.

[0098] In one feasible implementation, if the statement is "open the refrigerator", the generated dependency parsing tree for that statement is as follows: Figure 3 As shown, "open" is the root word in the dependency parsing tree (denoted by Root), and it is also the core word of the entire sentence. HED represents the core relation, that is, "open" is the core of the entire sentence; the relationship between "open" and "refrigerator" is a direct object relation (verb-object, VOB); "open" is a verb and is represented by "v", and "refrigerator" is a noun and is represented by "n".

[0099] b2. The operation information determining device determines the词性 association parameter of the first statement based on the dependency syntactic analysis tree.

[0100] Among them, the词性 association parameter of the first statement characterizes the dependency relationship between the words in the first statement. The词性 association parameter includes but is not limited to the verb-object relationship or the subject-predicate relationship. The词性 association parameter of the first statement can be obtained by analyzing the dependency syntactic analysis tree.

[0101] In a feasible implementation manner, if the statement is "Take soda from the refrigerator", the corresponding dependency syntactic analysis tree is as Figure 4 shown. It can be obtained from the syntactic analysis tree that the relationship between "from" and "refrigerator" is a preposition-object (POB) relationship; "take" and "from" can form an adverbial-middle structure; the relationship between "take" and "soda" is a verb-object relationship.

[0102] It should be noted that the词性 of each word is also marked in the dependency syntactic analysis tree. For example, Figure 4 shown, in the dependency syntactic analysis tree of "Take soda from the refrigerator", "p" is used to mark that "from" is a preposition, "n" is used to mark that the refrigerator is a noun, "v" is used to mark that "take" is a verb, and "n" is used to mark that "soda" is a noun.

[0103] Step 203. The operation information determining device filters the first statement based on the词性 association parameter of the first statement to obtain a set of target statements.

[0104] Among them, the set of target statements includes multiple second statements; the second statements are obtained by filtering multiple first statements.

[0105] In the embodiments of the present application, the operation information determining device can filter the words of the first statement based on the词性 association parameter of the first statement, and determine the set of target statements based on the statements where the selected words are located.

[0106] It should be noted that step 203 can also be implemented through the following steps:

[0107] c1. The operation information determining device determines a third word from the words of the first statement based on the词性 association parameter.

[0108] Among them, the词性 of the third word is a verb, and there is no词性 association relationship pointing to the third word in the first statement; there is a word in the first statement that has a verb-object relationship with the third word, and there is no word that has a subject-predicate relationship with the third word.

[0109] It should be noted that the third word is a verb and there is no dependency relationship pointing to the third word in the first sentence, which means that the third word is a verb independent of other words, and can also be called the third word is the root (dummy root) word in the dependency syntax analysis tree.

[0110] In the embodiment of the present application, based on the词性关联参数 (it seems there is a misspelling here, assuming it should be "dependency relationship parameter"), the root words that do not depend on other words can be determined from each first sentence first. Then, it is determined whether there is a word in the first sentence where the root word is located that has an object-predicate relationship with the root word. If so, it is determined whether there is a word in the first sentence where the root word is located that has a subject-predicate relationship with the root word. If not, the root word is determined as the third word. Finally, multiple third words can be determined from the words in multiple first sentences.

[0111] In a feasible implementation, as Figure 4 shown, "take" is a verb and there is no word pointing to "take", and the word that has an object-predicate relationship with "take" is "soda", and there is no word that forms a subject-predicate relationship with "take". Therefore, "take" can be used as the "third word".

[0112] c2. The operation information determining device determines the third sentence from the first sentences based on the sentence corresponding to the third word.

[0113] In the embodiment of the present application, the sentence corresponding to the third word can be determined from the first sentences, and the sentences other than the sentence corresponding to the third word in the first sentences are filtered out to obtain the third sentence. Here, the sentence corresponding to the third word refers to the sentence where the third word is located.

[0114] c3. The operation information determining device determines the target sentence set from the third sentence based on the position information of the third sentence in the text to be processed.

[0115] Among them, the position information of the third sentence in the text to be processed can refer to the line number of the third sentence in the text to be processed and the first-line indentation distance of the paragraph where the third sentence is located. In the embodiment of the present application, the third sentence can be screened based on the line number of the third sentence in the text to be processed and the first-line indentation distance of the paragraph where the third sentence is located, and the target sentence set is determined based on the screened sentences.

[0116] It should be noted that step c3 can be implemented through the following steps:

[0117] d1. The operation information determining device obtains the line number of each third sentence in the text to be processed, the first-line indentation distance of the paragraph where each third sentence is located, and the paragraph number of each third sentence.

[0118] In this embodiment of the application, the line and paragraph of the statement in the text to be processed can be numbered to obtain the line number of each statement in the text to be processed and the paragraph number of the paragraph of each statement. Then, the line number of the third statement can be determined from the line numbers of the statements in the text to be processed, and the paragraph number of the third statement can be determined from the paragraph numbers of the text to be processed.

[0119] It should be noted that if a statement occupies multiple lines in any paragraph of the text to be processed, the line number of the first line containing the statement will be used as the line number of the statement.

[0120] To obtain the first-line indentation distance of the paragraph containing the third statement, the text to be processed can be converted into an image. Based on the paragraph number of the third statement, the image of the paragraph containing the third statement can be determined from the image. Then, text recognition processing can be performed on the image of the paragraph containing the third statement, and the coordinates of the first character of the recognized text can be determined as the first-line indentation distance of the paragraph containing the third statement. The first-line indentation distance can also be called the horizontal indentation distance.

[0121] d2. The operation information determines the relationship between the fourth statement and the third statement based on the first-line indentation distance, line number, and paragraph number.

[0122] The fourth statement is selected from the third statements based on the first-line indentation distance, line number, and paragraph number of the third statement. The directed edges between the fourth statements can be represented by the lines from statement a to statement b. The line number of statement a is less than the line number of statement b, and the first-line indentation distance of statement a is less than the first-line indentation distance of statement b. If the number of lines in statement a is greater than the number of lines in statement b, or the first-line indentation distance of statement a is greater than the first-line indentation distance of statement b, then the construction of the directed edges from statement a to statement b is stopped, and statement a is deleted.

[0123] In this embodiment of the application, the third statement can be sorted according to the line number from largest to smallest or smallest to largest. Based on the sorted third statement and the paragraph number of the third statement, the third statement can be filtered to construct a directed edge between the statements of two adjacent paragraph numbers in the text to be processed. Based on the statements corresponding to the directed edge, the fourth statement and the pointing relationship between the fourth statements can be obtained.

[0124] In one feasible implementation, taking paragraph numbers 1 and 2 as examples (the horizontal indentation of statements in paragraph 1 is the same; the horizontal indentation of statements in paragraph 2 is also the same), the statements in paragraphs 1 and 2 are first sorted. If the statements in paragraph 1 are statement 1, statement 2, and statement 3, with line number 1 for statement 1, line number 2 for statement 2, and line number 3 for statement 3, and the statements in paragraph 2 are statement 4, statement 5, and statement 6, with line number 4 for statement 4, line number 5 for statement 5, and line number 6 for statement 6, it is clear that the line numbers of all statements in paragraph 2 are greater than those in paragraph 1. Given that the first-line indentation of paragraph 1 is less than that of paragraph 2, a directed edge can be constructed between paragraph 1 and paragraph 2, pointing from statement 3 to statement 4, and statements 1, 2, 5, and 6 can be deleted. Statements 3 and 4 are the fourth statements.

[0125] In another feasible implementation, if both the first and second paragraphs have only one line of statements, where statements 1, 2, and 3 are statements on the same line in the first paragraph, and statements 4, 5, and 6 are statements on the same line in the second paragraph, and if the indentation of the first line of the first paragraph is less than that of the first line of the second paragraph, then directed edges can be constructed for statements 1 pointing to statements 4, 5, and 6 respectively, statements 2 pointing to statements 4, 5, and 6 respectively, and statements 3 pointing to statements 4, 5, and 6 respectively.

[0126] d3. Based on the pointing relationship between the fourth statements, the device determines the operation information and constructs a directed tree of the fourth statements.

[0127] The pointing relationships between nodes in the directed tree are determined by the pointing relationships between the fourth statements.

[0128] In this embodiment of the application, the pointing relationship between nodes in the directed tree can be generated based on the pointing relationship between the fourth statements, and the directed tree of the fourth statements can be constructed based on the pointing relationship between the nodes.

[0129] It should be noted that there can be multiple directed trees, and multiple directed trees can form an operation name hierarchy topology graph; the directed trees can be constructed by inserting directed edges into nodes in sequence.

[0130] In one feasible implementation, the pointing relationship between nodes a and b is determined based on the directed edge between statement 'a' and statement 'b'. Then, the directed tree can be determined sequentially based on the pointing relationships between each node (i.e., the directed tree between nodes). Here, the statement corresponding to node a is statement a, the statement corresponding to node b is statement b, and the directed tree node a points to node b. Before inserting the directed edge between nodes a and b, it is also necessary to ensure that the statements corresponding to the nodes in the directed tree constructed from the previous directed edges do not contain a directed edge between statement b and statement a.

[0131] In another feasible implementation, if the fourth statement includes statement a, statement b, statement c, and statement d, and if statement a refers to statement b, and statement b refers to statements c and d respectively, then when constructing the directed tree, statement a can be set as the root node, statement b as a child node of statement a, and statements c and d as child nodes of statement b.

[0132] d4. The operation information determines the device based on a directed tree, and determines the hierarchical relationship between the fourth statement.

[0133] In this context, the hierarchical relationship between nodes in a directed tree can be used as the hierarchical relationship between the fourth statements corresponding to the nodes.

[0134] In this embodiment of the application, the hierarchical relationship between the fourth statements can be determined based on the statements corresponding to the directed tree.

[0135] d5. Based on the hierarchical relationship and the fourth statement, determine the target statement set for the operation information.

[0136] In this embodiment of the application, the fourth statements can be filtered based on the hierarchical relationship between the fourth statements and the fourth statements themselves, and the target statement set can be determined based on the filtered statements.

[0137] d5 can be achieved through the following steps:

[0138] e1. Operation information determines that the device will mark each node in the directed tree as the first label.

[0139] The first label is the initial label of each node in the directed tree, indicating that the statement corresponding to each node in the directed tree has not yet been processed.

[0140] In this embodiment of the application, each node in the directed tree is marked to facilitate subsequent processing of the statements corresponding to the first marked nodes and to avoid missing unprocessed statements; in one feasible implementation, each node in the directed tree can be marked as "false", that is, the first mark is "false".

[0141] e2. Operation information determination device determines the i-th node with the first label, the m-th node with the first label, and the n-th node with the first label for each directed tree based on the hierarchical relationship.

[0142] In this context, the level of node m is higher than that of node i; the level of node n is the same as that of node i; and i, m, and n are all positive integers. Node m is the ancestor of node i, and node n is the sibling of node i.

[0143] In the embodiments of this application, the i-th node can be any node other than the root node in the directed tree; for each directed tree, the traversal can be performed from the lowest leaf node to the root node to determine the ancestor node of the i-th node and the sibling node of the i-th node.

[0144] e3. Operation Information Determination: For each directed tree, the device updates the nodes in each directed tree based on the statements corresponding to the i-th node, the m-th node, and the n-th node to determine multiple target directed trees.

[0145] In this embodiment of the application, for any directed tree, it is possible to determine whether the parent node of the i-th node needs to be updated based on the statement corresponding to the i-th node, the statement corresponding to the m-th node, and the statement corresponding to the n-th node in the directed tree, and update the directed tree based on the determination result.

[0146] Step e3 can also be achieved through the following steps:

[0147] f1. The operation information determination device determines the word of the statement corresponding to the i-th node and the word of the statement corresponding to the m-th node, and the first word commonity degree.

[0148] Here, the first lexical commonality refers to the number of shared words between the statement corresponding to node i and the statement corresponding to node m. Node m is an ancestor node of node i, and there can be one or more ancestor nodes.

[0149] In one feasible implementation, if the ancestor nodes of the i-th node are three, namely m1, m2 and m3, then the lexical common degree w(m1,i) between the statement corresponding to m1 and the statement corresponding to the i-th node, the lexical common degree w(m2,i) between the statement corresponding to m2 and the statement corresponding to the i-th node, and the lexical common degree w(m3,i) between the statement corresponding to m3 and the statement corresponding to the i-th node can be calculated respectively; wherein, the first lexical common degree includes w(m1,i), w(m2,i) and w(m3,i).

[0150] f2. The operation information determines the word of the statement corresponding to the nth node and the word of the statement corresponding to the mth node, and the degree of second vocabulary commonality.

[0151] The second word commonality refers to the number of words shared between the statement corresponding to node i and the statement corresponding to node n; node n is a sibling node at the same level as node i; and the number of sibling nodes can be one or more.

[0152] In one feasible implementation, if the sibling nodes of the i-th node are i1 and i2, and the m-th node includes m1, m2 and m3, then the word commonality degree between the statement corresponding to i1 and m1, m2 and m3, and the word commonality degree between the statement corresponding to i2 and m1, m2 and m3 can be calculated respectively. That is, the second word commonality degree can include: w(m1,i1), w(m1,i2), w(m2,i1), w(m2,i2), w(m3,i1) and w(m3,i2).

[0153] f3. The operation information determines the third word co-occurrence based on the first word co-occurrence and the second word co-occurrence.

[0154] Among them, the third word commonality refers to the maximum word commonality between the i-th node and its ancestor node (the m-th node).

[0155] In one feasible implementation, if the sibling nodes of the i-th node include i1 and i2, and the ancestor nodes of the i-th node include m1, m2, and m3, then the first value can be determined based on w(m1,i), w(m1,i1), and w(m1,i2), where the first value can be represented by W1, W1 = w(m1,i) + w(m1,i1) + w(m1,i2); similarly, the second value can be determined, represented by W2, W2 = w(m2,i) + w(m2,i1) + w(m2,i2); the third value can be represented by W3, W3 = w(m3,i) + w(m3,i1) + w(m3,i2). Then, the maximum value is determined from the first, second, and third values, and the maximum value is taken as the third word commonity degree.

[0156] f4. The operation information determines the degree of commonality of the fourth word in the word of the statement corresponding to the i-th node and the word of the statement corresponding to the parent node of the i-th node.

[0157] The fourth word commonality is the sum of the commonality of the words in the statement corresponding to the i-th node and the words in the statement corresponding to the parent node of the i-th node, and the commonality of the words in the statement corresponding to the sibling node (n-th node) of the i-th node.

[0158] In one feasible implementation, if the sibling nodes of the i-th node include i1 and i2, and the parent node of the i-th node is denoted as p, then the fourth word commonality degree = w(p,i) + w(p,i1) + w(p,i2); where w(p,i) represents the number of words in common between the statement corresponding to the p node and the statement corresponding to the i-th node, w(p,i1) represents the number of words in common between the statement corresponding to the p node and the statement corresponding to the i1-th node, and w(p,i2) represents the number of words in common between the statement corresponding to the p node and the statement corresponding to the i2-th node.

[0159] f5. The operation information determination device updates the nodes in the directed tree based on the third and fourth word commonness to determine the target directed tree.

[0160] In this embodiment of the application, it can be determined whether the parent node of the i-th node needs to be updated based on the third word commonality and the fourth word commonality, and the nodes in the directed tree are updated based on the determined result, and the updated directed tree is used as the target directed tree.

[0161] Step f5 can be achieved through the following steps:

[0162] g1. When the operation information determines that the third word commonality is greater than the fourth word commonality, the operation information determines that the device deletes the parent node of the i-th node, modifies the parent node of the i-th node to the m-th node corresponding to the third word commonality, and modifies the first tag of the i-th node and its sibling nodes to the second tag.

[0163] In this embodiment of the application, if the common degree of the third word is greater than the common degree of the fourth word, it indicates that the parent node of the current i-th node in the directed tree is not the true parent node of the i-th node. Then, the ancestor node of the i-th node corresponding to the common degree of the third word can be taken as the parent node of the i-th node, and the original parent node of the i-th node can be deleted. The first label of the i-th node and the sibling node of the i-th node can be modified to the second label, so that the nodes marked with the second label will not be processed in the future. For example, the second label can be "true".

[0164] In one feasible implementation, if the common degree of the third word is greater than that of the fourth word, the parent node of the i-th node is p, and the common degree of the third word is W2, where W2 = w(m2,i) + w(m2,i1) + w(m2,i2), that is, the node corresponding to the common degree of the third word is m2, then the parent node p of the i-th node in the directed tree can be modified to m2. Specifically, this can be done by adding a directed edge from m2 to the i-th node, deleting the original parent node P of the i-th node, and modifying the first label of the i-th node and its sibling nodes to the second label.

[0165] like Figure 5As shown, in the directed tree corresponding to the document, statement S2 points to S3, S4, and S5 respectively; for example... Figure 6 As shown, after updating the directed tree, the target directed tree is obtained. It is clear that statement S2 has been deleted, and directed edges S1 has been added pointing to S3, S4 and S5 respectively, thus realizing the filtering of statements corresponding to nodes in the directed tree.

[0166] g2. For each directed tree, the operation information determination device determines the target directed tree based on the parent node of the modified i-th node, provided that all nodes in the directed tree are labeled with the second label.

[0167] In this context, the statement corresponding to the node in the target directed tree is the second statement; the target directed tree does not have the original parent node of the i-th node.

[0168] In this embodiment of the application, for a directed tree, a new directed tree can be obtained based on the modified parent node of the i-th node in the directed tree, and the new directed tree can be used as the target directed tree. The number of target directed trees corresponds to the number of directed trees.

[0169] It should be noted that when all nodes in the directed tree are labeled with the second label, it means that all nodes in the directed tree have been processed, and the target directed tree can be re-determined based on the parent node of the modified i-th node.

[0170] e4. Operation information determination device determines the target statement set based on the statements corresponding to the nodes of multiple target directed trees.

[0171] In this embodiment of the application, the set of statements corresponding to the nodes of multiple target directed trees can be used as the target statement set.

[0172] Step 204: The operation information determination device determines the operation instruction mapping table of the text to be processed based on the second statement in the target statement set.

[0173] The operation description mapping table represents the correspondence between operation names and operation information in the text to be processed; the operation description mapping table includes the operation name and the identifier of the operation information corresponding to the operation name.

[0174] In this embodiment of the application, the hierarchical relationship between the second statements can be determined based on the second statements in the target statement set. Then, based on the hierarchical relationship between the second statements, the level of the same statements in the target statement set can be determined. And based on the level of the same statements and the second statements, the operation instruction mapping table of the text to be processed can be determined.

[0175] Step 204 can be achieved through the following steps:

[0176] h1. Operation information determination device determines candidate nodes with the same statement from multiple target directed trees, and determines the number of descendant nodes of the candidate nodes.

[0177] Among them, candidate nodes refer to nodes with the same statement content; there are multiple candidate nodes; the same statement refers to the content of the statement; multiple candidate nodes can be nodes on a directed tree with the same target, or nodes on directed trees with different targets.

[0178] In this embodiment of the application, nodes with the same statement in the target directed tree can be determined based on the statement corresponding to the node in the target directed tree, and nodes with the same statement can be selected as candidate nodes. The number of descendant nodes of each candidate node can be determined based on the directed tree.

[0179] In one feasible implementation, if statement A appears simultaneously in nodes e1, e2, e3, and e4 of the target directed tree, then nodes e1, e2, e3, and e4 can be selected as candidate nodes, and the number of descendant nodes of nodes e1, e2, e3, and e4 can be determined respectively.

[0180] h2. Operation information determines the target node from the candidate nodes that has the most descendant nodes.

[0181] In this embodiment, the target node is determined by the number of descendant nodes of each of the multiple candidate nodes, which means that the location of the operation information is determined for the statements corresponding to the multiple candidate nodes.

[0182] In one feasible implementation, if statement A appears simultaneously in nodes e1, e2, e3, and e4 of the target directed tree, and node e3 has the most descendant nodes, then node e3 can be used as the target node, the statement corresponding to node e3 can be used as operation name A, and the statements of the descendant nodes corresponding to node e3 can be used as operation information for operation name A.

[0183] h3. The operation information determines the correspondence between the statements corresponding to the target node of the device construction and the identifiers of the statements corresponding to the descendant nodes of the target node, and obtains the operation instruction mapping table.

[0184] In the operation description mapping table, the statement corresponding to the target node represents the operation name; the identifier in the operation description mapping table can represent the operation information corresponding to the operation name.

[0185] In this embodiment, the statements corresponding to the descendant nodes of the target node can be identified to obtain the identifiers of the statements corresponding to the descendant nodes of the target node, thus establishing a correspondence between the statements of the target node and the identifiers of the statements corresponding to the descendant nodes of the target node. Here, the statement of the target node is the operation name.

[0186] It should be noted that the operation description mapping table includes multiple operation names and identifiers for the operation information corresponding to each operation name. Determining the identifiers of the statements corresponding to the descendant nodes of the target node can be achieved by sorting the statements corresponding to the descendant nodes of the target node by line number, specifically in ascending order, and then identifying the statements corresponding to the sorted descendant nodes of the target node. The operation description mapping table may also include operation information corresponding to the operation names.

[0187] In longer documents, an operation name may appear in multiple places. The method provided in this application can identify the operation information corresponding to the operation name, avoid misjudging other text as operation information of the operation name, and further improve the accuracy of determining the operation information corresponding to the operation name.

[0188] Step 205: Operation Information Determination. The device receives the query information, performs word segmentation on the query information, and obtains the first word.

[0189] Step 206: The operation information determination device segments the operation names in the operation instruction mapping table to obtain the second word of each operation name.

[0190] The operation description mapping table represents the relationship between the operation name and operation information in the text to be processed.

[0191] Step 207: Operation Information Determination. The device determines the target operation name based on the first and second words.

[0192] Step 208: Operation Information Determination. Based on the target operation name and operation description mapping table, the device determines the target operation information to be queried from the text to be processed and outputs the target operation information.

[0193] It should be noted that the descriptions of the same steps and contents as in other embodiments in this embodiment can be found in the descriptions in other embodiments, and will not be repeated here.

[0194] The operation information determination method provided in this application determines the target operation information of the query information based on an operation instruction mapping table. It considers the distribution of the target operation information in the text to be processed, eliminating the need for extracting operation information from entire paragraphs each time, as is common in related technologies. This improves the accuracy and efficiency of determining the target operation information. The method can pinpoint the location of operation information in long documents where operation names appear in multiple places, avoiding misinterpreting quoted text as operation information, thus achieving effective extraction of operation information. By constructing a directed tree based on the visual features of sentences in the document (line number, first-line indentation, paragraph), the hierarchical relationship between operation names can be determined. This method can handle document sources where paragraph structure logic cannot be parsed, such as portable document formats and scanned image documents, expanding the document range from which operation knowledge can be extracted.

[0195] Based on the foregoing embodiments, embodiments of this application provide an operation information determining device, which can be applied to... Figure 1-2 In the corresponding embodiment, the method for determining operation information is referenced. Figure 7 The operation information determines that device 3 may include: a processor 31, a memory 32, and a communication bus 33, wherein:

[0196] Communication bus 33 is used to realize the communication connection between processor 31 and memory 32;

[0197] The processor 31 is used to execute the operation information determination program in the memory 32 to perform the following steps:

[0198] Receive the query information, perform word segmentation on the query information, and obtain the first word;

[0199] The operation names in the operation description mapping table are segmented to obtain the second word of each operation name; the operation description mapping table represents the relationship between the operation names and operation information in the text to be processed.

[0200] Based on the first and second words, determine the target operation name;

[0201] Based on the target operation name and operation description mapping table, the target operation information to be queried is determined from the text to be processed, and the target operation information is output.

[0202] In other embodiments of this application, the processor 31 is used to execute an operation information determination program in the memory 32 to perform the following steps:

[0203] Obtain the text to be processed and determine the first statement from the text to be processed;

[0204] Obtain the part-of-speech tagging parameters for the first statement;

[0205] Based on the part-of-speech tagging parameters of the first statement, the first statement is filtered to obtain the target statement set;

[0206] Based on the second statement in the target statement set, determine the operation instruction mapping table for the text to be processed.

[0207] In other embodiments of this application, the processor 31 is configured to execute the operation information determining program in the memory 32 to determine a first statement from the text to be processed, in order to implement the following steps:

[0208] Identify the statements in the text to be processed, and determine the part of speech of the words in the statements;

[0209] Extract sentences containing both verbs and nouns from the text to be processed to obtain the first sentence.

[0210] In other embodiments of this application, the processor 31 is used to execute the operation information determination program in the memory 32 to obtain the part-of-speech association parameters of the first statement, in order to implement the following steps:

[0211] Extract the words from the first sentence and construct a dependency parsing tree based on the words in the first sentence;

[0212] Based on the dependency parsing tree, the part-of-speech parameters of the first statement are determined.

[0213] In other embodiments of this application, the processor 31 is used to execute the operation information determination program in the memory 32 based on the part-of-speech association parameters of the first statement, and to filter the first statement to obtain a target statement set, so as to implement the following steps:

[0214] Based on part-of-speech (POS) parameters, the third word is determined from the words in the first sentence; wherein the part of speech of the third word is a verb, and there is no POS relationship pointing to the third word in the first sentence; there are words in the first sentence that have a verb-object relationship with the third word, but there are no words that have a subject-predicate relationship with the third word;

[0215] Based on the statement corresponding to the third word, determine the third statement from the first statement;

[0216] Based on the position information of the third statement in the text to be processed, the target statement set is determined from the third statement.

[0217] In other embodiments of this application, the processor 31 is configured to execute the operation information determination program in the memory 32 to determine the target statement set from the third statement based on the position information of the third statement in the text to be processed, in order to implement the following steps:

[0218] Get the line number of each third statement in the text to be processed, the first-line indentation distance of the paragraph containing each third statement, and the paragraph number containing each third statement;

[0219] Based on the first-line indentation distance, line number, and paragraph number, determine the pointing relationship between the fourth statement and the third statement;

[0220] Based on the pointing relationships between the fourth statements, construct a directed tree for the fourth statements;

[0221] Based on the directed tree, determine the hierarchical relationship between the fourth statements;

[0222] Based on the hierarchical relationship and the fourth statement, determine the set of target statements.

[0223] In other embodiments of this application, processor 31 is used to execute the operation information determination program in memory 32 based on hierarchical relationships and the fourth statement to determine the target statement set to implement the following steps:

[0224] Mark each node in the directed tree as the first label;

[0225] For each directed tree, determine the i-th node with the first label, the m-th node with the first label, and the n-th node with the first label based on the hierarchical relationship; wherein the level of the m-th node is greater than the level of the i-th node; the level of the n-th node is the same as the level of the i-th node; wherein i, m, and n are all positive integers.

[0226] For each directed tree, based on the statement corresponding to the i-th node, the statement corresponding to the m-th node, and the statement corresponding to the n-th node, the nodes in each directed tree are updated to determine multiple target directed trees;

[0227] The set of target statements is determined based on the statements corresponding to the nodes of multiple target directed trees.

[0228] In other embodiments of this application, the processor 31 is configured to execute the operation information determination program in the memory 32 to update the nodes in each directed tree based on the statement corresponding to the i-th node, the statement corresponding to the m-th node, and the statement corresponding to the n-th node, to determine multiple target directed trees, including:

[0229] Determine the word commonality between the words of the statement corresponding to the i-th node and the words of the statement corresponding to the m-th node;

[0230] Determine the word commonality between the word in the statement corresponding to node n and the word in the statement corresponding to node m;

[0231] The third word share is determined based on the first word share and the second word share.

[0232] Determine the fourth lexical commonity between the words in the statement corresponding to the i-th node and the words in the statement corresponding to the parent node of the i-th node;

[0233] Based on the third and fourth word commonness, the nodes in the directed tree are updated to determine the target directed tree; where the statement corresponding to the node in the target directed tree is the second statement.

[0234] In other embodiments of this application, processor 31 is used to execute the second statement in the target statement set of the operation information determination program in memory 32 to determine the operation instruction mapping table of the text to be processed, so as to implement the following steps:

[0235] Identify candidate nodes with the same statement from multiple directed trees and determine the number of descendant nodes of each candidate node.

[0236] Identify the target node from the candidate nodes that has the largest number of descendant nodes;

[0237] Construct a mapping relationship between the statement corresponding to the target node and the identifiers of the statements corresponding to the descendant nodes of the target node to obtain an operation description mapping table; wherein, the statement corresponding to the target node in the operation description mapping table represents the operation name; the identifier in the operation description mapping table represents the position of the operation information corresponding to the operation name.

[0238] In other embodiments of this application, the processor 31 is used to execute an operation information determination program in the memory 32 based on an operation description mapping table to determine the operation information of the information to be queried from the text to be processed, so as to implement the following steps:

[0239] Receive the query information and perform word segmentation on the query information to obtain the second word;

[0240] The operation names in the operation description mapping table are segmented to obtain the third word of each operation name;

[0241] From the third word, identify the word with the highest matching degree to the second word, and determine the target operation name corresponding to the word with the highest matching degree;

[0242] Based on the target operation name and operation description mapping table, the target operation information is obtained from the text to be processed.

[0243] It should be noted that the specific implementation process of the steps executed by the processor in this embodiment can be referred to Figure 1-2 The implementation process of the operation information determination method provided in the corresponding embodiment will not be described in detail here.

[0244] The operation information determination device provided in this application embodiment determines the target operation information of the information to be queried based on the operation instruction mapping table. It takes into account the distribution of the target operation information in the text to be processed, and does not require that the operation information can only be extracted from the whole text each time to determine the target operation information, as is the case in related technologies. This improves the accuracy and efficiency of determining the target operation information.

[0245] Based on the foregoing embodiments, embodiments of this application provide a computer-readable storage medium storing one or more programs, which can be executed by one or more processors to implement... Figure 1-2 The corresponding embodiments provide the steps of the operation information determination method.

[0246] It should be noted that the aforementioned computer-readable storage media can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM), etc.; or it can be various electronic devices that include one or any combination of the above-mentioned memories, such as mobile phones, computers, tablet devices, personal digital assistants, etc.

[0247] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0248] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0249] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0250] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0251] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0252] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0253] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for determining operational information, characterized in that, The method includes: Receive the query information, perform word segmentation on the query information, and obtain the first word; The operation names in the operation description mapping table are segmented to obtain the second word of each operation name; wherein, the operation description mapping table represents the relationship between the operation names and operation information in the text to be processed; The first word is matched with the second word of each operation name, and the second word with the highest matching degree is determined. The second word with the highest matching degree is taken as the target word, and the operation name containing the target word is taken as the target operation name; wherein, the matching degree is the number of words coexisting in the query information and the operation name; Based on the target operation name and the operation description mapping table, the target operation information of the query information is determined from the text to be processed, and the target operation information is output. The method further includes: Obtain the text to be processed, identify the statements in the text to be processed, and determine the part of speech of the words in the statements in the text to be processed; The first statement is obtained by extracting statements containing both verbs and nouns from the text to be processed. Obtain the part-of-speech tagging parameters of the first statement; Based on the part-of-speech tagging parameters of the first statement, the first statement is filtered to obtain a set of target statements; Based on the second statement in the target statement set, determine the operation instruction mapping table for the text to be processed.

2. The method according to claim 1, characterized in that, The step of obtaining the part-of-speech tagging parameters of the first statement includes: Extract the words from the first statement and construct a dependency parsing tree based on the words in the first statement; Based on the dependency parsing tree, the part-of-speech parameters of the first statement are determined.

3. The method according to claim 1, characterized in that, The step of filtering the first statement based on the part-of-speech tagging parameters of the first statement to obtain a target statement set includes: Based on the part-of-speech association parameters, a third word is determined from the words in the first statement; wherein the part of speech of the third word is a verb, and there is no part-of-speech association relationship pointing to the third word in the first statement; there are words in the first statement that have a verb-object relationship with the third word, but there are no words that have a subject-predicate relationship with the third word; Based on the statement corresponding to the third word, the third statement is determined from the first statement; Based on the position information of the third statement in the text to be processed, the target statement set is determined from the third statement.

4. The method according to claim 3, characterized in that, The step of determining the target statement set from the third statement based on the position information of the third statement in the text to be processed includes: Obtain the line number of each third statement in the text to be processed, the first-line indentation distance of the paragraph containing each third statement, and the paragraph number containing each third statement. Based on the first-line indentation distance, the line number, and the paragraph number, determine the pointing relationship between the fourth statement and the third statement; Based on the pointing relationships between the fourth statements, construct a directed tree of the fourth statements; Based on the directed tree, determine the hierarchical relationship between the fourth statements; Based on the hierarchical relationship and the fourth statement, the target statement set is determined.

5. The method according to claim 4, characterized in that, The determination of the target statement set based on the hierarchical relationship and the fourth statement includes: Each node in the directed tree is labeled with the first label; For each directed tree, based on the hierarchy, determine the i-th node with the first label, the m-th node with the first label, and the n-th node with the first label; wherein the level of the m-th node is greater than the level of the i-th node; the level of the n-th node is the same as the level of the i-th node; wherein i, m, and n are all positive integers; For each directed tree, based on the statement corresponding to the i-th node, the statement corresponding to the m-th node, and the statement corresponding to the n-th node, the nodes in each directed tree are updated to determine multiple target directed trees; Based on the statements corresponding to the nodes of the multiple target directed trees, the target statement set is determined.

6. The method according to claim 5, characterized in that, For each directed tree, based on the statements corresponding to the i-th node, the m-th node, and the n-th node, the nodes in each directed tree are updated to determine multiple target directed trees, including: Determine the first lexical commonality between the words of the statement corresponding to the i-th node and the words of the statement corresponding to the m-th node; Determine the second lexical commonality between the words of the statement corresponding to the nth node and the words of the statement corresponding to the mth node; The third word share is determined based on the first word share and the second word share. Determine the fourth lexical commonality degree between the words of the statement corresponding to the i-th node and the words of the statement corresponding to the parent node of the i-th node; Based on the third and fourth word commonness, the nodes in the directed tree are updated to determine the target directed tree; wherein, the statement corresponding to the node of the target directed tree is the second statement.

7. The method according to claim 6, characterized in that, The step of determining the operation instruction mapping table for the text to be processed based on the second statement in the target statement set includes: From multiple target directed trees, determine candidate nodes with the same statement, and determine the number of descendant nodes of the candidate nodes; From the candidate nodes, determine the target node that has the largest number of descendant nodes; A correspondence is established between the statement corresponding to the target node and the identifiers of the statements corresponding to the descendant nodes of the target node to obtain an operation description mapping table; wherein, the statement corresponding to the target node in the operation description mapping table represents the operation name; and the identifier in the operation description mapping table represents the operation information corresponding to the operation name.

8. An operation information determining device, characterized in that, The device includes: a processor, a memory, and a communication bus; The communication bus is used to realize the communication connection between the processor and the memory; The processor is used to execute a program for determining operation information in memory to perform the following steps: Receive the query information, perform word segmentation on the query information, and obtain the first word; The operation names in the operation description mapping table are segmented to obtain the second word of each operation name; wherein, the operation description mapping table represents the relationship between the operation names and operation information in the text to be processed; The first word is matched with the second word of each operation name, and the second word with the highest matching degree is determined. The second word with the highest matching degree is taken as the target word, and the operation name containing the target word is taken as the target operation name; wherein, the matching degree is the number of words coexisting in the query information and the operation name; Based on the target operation name and the operation description mapping table, the target operation information of the query information is determined from the text to be processed, and the target operation information is output. The processor, used to execute the operation information determination program in the memory, further includes the following steps: Obtain the text to be processed, identify the statements in the text to be processed, and determine the part of speech of the words in the statements in the text to be processed; The first statement is obtained by extracting statements containing both verbs and nouns from the text to be processed. Obtain the part-of-speech tagging parameters of the first statement; Based on the part-of-speech tagging parameters of the first statement, the first statement is filtered to obtain a set of target statements; Based on the second statement in the target statement set, determine the operation instruction mapping table for the text to be processed.

Images