CN112328780A - Natural language conversion processing method and device, electronic equipment and storage medium - Google Patents
Natural language conversion processing method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112328780A CN112328780A CN202011275097.9A CN202011275097A CN112328780A CN 112328780 A CN112328780 A CN 112328780A CN 202011275097 A CN202011275097 A CN 202011275097A CN 112328780 A CN112328780 A CN 112328780A
- Authority
- CN
- China
- Prior art keywords
- natural language
- keywords
- processed
- language
- keyword
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000006243 chemical reaction Methods 0.000 title claims abstract description 38
- 238000003672 processing method Methods 0.000 title claims abstract description 23
- 238000000034 method Methods 0.000 claims abstract description 34
- 238000012545 processing Methods 0.000 claims abstract description 17
- 238000012937 correction Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 210000004556 brain Anatomy 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000011835 investigation Methods 0.000 description 3
- 239000003607 modifier Substances 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000007480 spreading Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000007800 oxidant agent Substances 0.000 description 1
- 230000001590 oxidative effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3343—Query execution using phonetics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
Abstract
The application provides a natural language conversion processing method and device, electronic equipment and a storage medium, and relates to the technical field of text processing. The natural language conversion processing method comprises the following steps: acquiring a natural language to be processed; acquiring a plurality of keywords in the natural language to be processed according to a preset database, and acquiring categories corresponding to the keywords; judging the logic attribute of each language segment in the natural language to be processed according to the key words; and generating a program flow corresponding to the natural language to be processed according to the logic attribute of each language segment and the category corresponding to each keyword. By extracting the keywords in the natural language to be processed and acquiring the logic attributes of the natural language to be processed by using the keywords, the program flow corresponding to the natural language to be processed is finally obtained, and the accuracy of text conversion is improved. In addition, by using the method provided by the embodiment of the application, the program flow corresponding to the natural language to be processed can be directly obtained, and the execution efficiency of the text is improved.
Description
Technical Field
The present application relates to the field of text processing technologies, and in particular, to a natural language conversion processing method and apparatus, an electronic device, and a storage medium.
Background
In the real world, many industry knowledge is stored in the brain of an industry expert, and in order to facilitate the sharing and spreading of the knowledge, the implicit knowledge in the brain needs to be made explicit.
At present, the most common method is to make the expert express the knowledge in natural language and store the knowledge in the record and document. Because natural language has ambiguity to a certain extent, other people can have inconsistent understanding when reading documents, and simultaneously can filter some information unconsciously, so that all knowledge expressed by an author cannot be mastered comprehensively; on the other hand, this approach is still a biographical one, and knowledge in the document cannot be directly understood and executed by a computer.
The existing text conversion method is not efficient to execute.
Disclosure of Invention
In order to solve the problems in the prior art, the application provides a natural language conversion processing method, a natural language conversion processing device, an electronic device and a storage medium.
A first aspect of the present application provides a natural language conversion processing method, including:
acquiring a natural language to be processed;
acquiring a plurality of keywords in the natural language to be processed according to a preset database, and acquiring a category corresponding to each keyword;
judging the logic attribute of each language segment in the natural language to be processed according to the keyword;
and generating a program flow corresponding to the natural language to be processed according to the logic attribute of each language segment and the category corresponding to each keyword.
Optionally, the obtaining a plurality of keywords in the natural language to be processed according to a preset database, and obtaining categories corresponding to the keywords include:
acquiring a plurality of keywords in the natural language to be processed according to a preset database;
and calling a data source, and obtaining the category corresponding to each keyword by matching the data source, wherein the data source indicates the category of the keyword.
Optionally, the determining, according to the keyword, a logical attribute of each speech segment in the natural language to be processed includes:
calling a data source;
and judging the logic attribute of each language segment in the natural language to be processed according to the keywords and a preset rule, wherein the data source indicates the logic relationship corresponding to the keywords in each language segment.
Optionally, the generating a program flow corresponding to the natural language to be processed according to the logic attribute of each language segment and the category corresponding to each keyword includes:
determining an atomic index and a derivative index of each word segment according to the category corresponding to each keyword;
determining the sequence and branch logic among the language segments according to the logic attributes of the language segments;
and generating a program flow corresponding to the natural language to be processed according to the sequence, the branch logic, the atomic indexes and the derivative indexes of the language segments.
Optionally, after acquiring a plurality of keywords from the natural language to be processed according to a preset database, the method further includes:
displaying the keywords through a display device;
and receiving correction information based on the keywords, and acquiring a plurality of corrected keywords.
Optionally, the acquiring the natural language to be processed includes:
collecting natural language audio data;
and converting the natural language audio data into an initial natural language text as the natural language to be processed.
A second aspect of the present application provides a natural language conversion processing apparatus including: an acquisition unit, a judgment unit and a generation unit;
the acquisition unit is used for acquiring the natural language to be processed;
acquiring a plurality of keywords in the natural language to be processed according to a preset database, and acquiring a category corresponding to each keyword;
the judging unit is used for judging the logic attribute of each language segment in the natural language to be processed according to the keyword;
and the generating unit is used for generating a program flow corresponding to the natural language to be processed according to the logic attribute of each language segment and the category corresponding to each keyword.
Optionally, the obtaining unit is specifically configured to obtain a plurality of keywords in the natural language to be processed according to a preset database;
and calling a data source, and obtaining the category corresponding to each keyword by matching the data source, wherein the data source indicates the category of the keyword.
Optionally, the determining unit is specifically configured to invoke a data source; and judging the logic attribute of each language segment in the natural language to be processed according to the keywords and a preset rule, wherein the data source indicates the logic relationship corresponding to the keywords in each language segment.
Optionally, the generating unit is specifically configured to determine an atomic index and a derivative index of each of the paragraphs according to a category corresponding to each of the keywords;
determining the sequence and branch logic among the language segments according to the logic attributes of the language segments;
and generating a program flow corresponding to the natural language to be processed according to the sequence, the branch logic, the atomic indexes and the derivative indexes of the language segments.
Optionally, the apparatus further comprises: a display unit;
the display unit is used for displaying the keywords through display equipment;
the acquisition unit is used for receiving correction information based on the keywords and acquiring a plurality of corrected keywords.
Optionally, the acquiring unit is specifically configured to acquire natural language audio data;
and converting the natural language audio data into an initial natural language text as the natural language to be processed.
A third aspect of the present application provides an electronic device comprising: a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is operated, the processor communicates with the storage medium through the bus, and the processor executes the machine-readable instructions to perform the steps of the method according to the first aspect.
A fourth aspect of the present application provides a storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method according to the first aspect.
The application provides a natural language conversion processing method, a natural language conversion processing device, an electronic device and a storage medium, wherein the natural language conversion processing method comprises the following steps: acquiring a natural language to be processed; acquiring a plurality of keywords in the natural language to be processed according to a preset database, and acquiring a category corresponding to each keyword; judging the logic attribute of each language segment in the natural language to be processed according to the keyword; and generating a program flow corresponding to the natural language to be processed according to the logic attribute of each language segment and the category corresponding to each keyword. In the embodiment of the application, the keywords in the natural language to be processed are extracted, the logic attributes of the natural language to be processed are obtained by using the keywords, and the program flow corresponding to the natural language to be processed is finally obtained, so that the problem that in the prior art, when the natural language is directly processed, the key information in the natural language to be processed cannot be obtained, and the text conversion accuracy is not high is solved. In addition, by using the method provided by the embodiment of the application, the program flow corresponding to the natural language to be processed can be directly obtained, and the execution efficiency of the text is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 is a schematic flowchart of a natural language conversion processing method according to an embodiment of the present application;
fig. 2 is a schematic flowchart of a natural language conversion processing method according to another embodiment of the present application;
fig. 3 is a flowchart illustrating a natural language conversion processing method according to another embodiment of the present application;
fig. 4 is a flowchart illustrating a natural language conversion processing method according to another embodiment of the present application;
fig. 5 is a flowchart illustrating a natural language conversion processing method according to another embodiment of the present application;
fig. 6 is a flowchart illustrating a natural language conversion processing method according to another embodiment of the present application;
fig. 7 is a schematic diagram of a natural language conversion processing apparatus according to an embodiment of the present application;
fig. 8 is a schematic diagram of a natural language conversion processing apparatus according to another embodiment of the present application;
fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it should be understood that the drawings in the present application are for illustrative and descriptive purposes only and are not used to limit the scope of protection of the present application. Additionally, it should be understood that the schematic drawings are not necessarily drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of the present application. It should be understood that the operations of the flow diagrams may be performed out of order, and steps without logical context may be performed in reverse order or simultaneously. One skilled in the art, under the guidance of this application, may add one or more other operations to, or remove one or more operations from, the flowchart.
In addition, the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that in the embodiments of the present application, the term "comprising" is used to indicate the presence of the features stated hereinafter, but does not exclude the addition of further features.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
Furthermore, the terms "first," "second," and the like in the description and in the claims, as well as in the drawings, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that the features of the embodiments of the present application may be combined with each other without conflict.
With the continuous development of science and technology, the functions of computers are diversified more and more, and besides the most basic internet function, the computers also have the function of text processing. For example, a search of textual information is processed by a computer, and a comparison of textual information is processed by a computer. In the real world, many industry knowledge is stored in the brain of an industry expert, and in order to facilitate the sharing and spreading of the knowledge, the implicit knowledge in the brain needs to be made explicit.
At present, the most common method is to make the expert express the knowledge in natural language and store the knowledge in the record and document. Because natural language has ambiguity to a certain extent, other people can have inconsistent understanding when reading documents, and simultaneously can filter some information unconsciously, so that all knowledge expressed by an author cannot be mastered comprehensively; on the other hand, this approach is still a biographical one, and knowledge in the document cannot be directly understood and executed by a computer. Which in turn results in a low accuracy and execution efficiency of the existing text conversion methods.
In order to solve the technical problems in the prior art, the present application provides an inventive concept: extracting keywords in the natural language to be processed, acquiring the logic attribute of the natural language to be processed by using the keywords, and finally obtaining the program flow corresponding to the natural language to be processed.
The following describes a specific technical solution provided by the present application through possible implementation manners.
Fig. 1 is a flowchart illustrating a natural language conversion processing method according to an embodiment of the present application, where an execution subject of the method may be a computer, a server, or other equipment with a processing function. As shown in fig. 1, the method includes:
and S101, acquiring the natural language to be processed.
Optionally, in this embodiment of the present application, the natural language to be processed may be any content expressed by a user through a natural language, for example, a solution generated for a certain problem according to its own language expression manner, or a personal view published for a certain academic topic.
S102, acquiring a plurality of keywords in the natural language to be processed according to a preset database, and acquiring categories corresponding to the keywords.
In the embodiment of the application, according to the preset database, whether a keyword matched with preset information in the preset database exists or not is searched in the natural language to be processed, that is, a plurality of keywords are obtained from the natural language to be processed, and categories corresponding to the keywords can be obtained according to the obtained keywords.
Optionally, in this embodiment of the present application, the preset database may include keywords in various categories, where the different categories may be divided by industry, academic field, part of speech, and the like, which is not limited herein. Examples include: the key words of the financial industry, the loan industry, the chemical industry, the food industry, the catering industry, the transportation industry and the like. The keywords corresponding to each industry have certain differences, and for example, when the natural language to be processed belongs to the loan industry, the keywords may be "identity card number", "household registration", "relatives", and the like. When the natural language to be processed belongs to the chemical industry, the keywords can be 'explosion', 'color change', 'temperature rise', 'oxidant', 'corrosiveness', 'density', and the like.
In addition, besides the above keywords unique to each industry, the keywords may also include some preset connection relation words, such as: "… … if … …", "… … if … …", etc.
S103, judging the logic attribute of each language segment in the natural language to be processed according to the key words.
Optionally, in this embodiment of the application, the logical attribute of each language segment in the natural language to be processed may be determined according to the obtained keyword information. Illustratively, the logical attribute of each language segment can be obtained according to the connection keyword in the natural language to be processed.
And S104, generating a program flow corresponding to the natural language to be processed according to the logic attribute of each language segment and the category corresponding to each keyword.
In the embodiment of the application, the logic flow corresponding to the natural language to be processed can be obtained according to the logic attribute contained in the language segment and the type corresponding to each keyword.
It should be noted that the logic flow may be a machine recognizable language such as: a code language. Illustratively, when the acquired natural language to be processed is "when a credit-assessing blacklist user exists in the relatives of the lender, then no credit is offered to the lender", the acquired plurality of keywords may be "when", "lender", "relatives", "credit-assessing", "blacklist", "then", "no credit", and the like. The generated program flow may be "if … … then … …", wherein the identity information and the relative information of the lender may be queried according to the relevant information base, and finally the program flow is generated by using the information.
In the embodiment, a natural language to be processed is obtained; acquiring a plurality of keywords in the natural language to be processed according to a preset database, and acquiring a category corresponding to each keyword; judging the logic attribute of each language segment in the natural language to be processed according to the keyword; and generating a program flow corresponding to the natural language to be processed according to the logic attribute of each language segment and the category corresponding to each keyword. In the embodiment of the application, the keywords in the natural language to be processed are extracted, the logic attributes of the natural language to be processed are obtained by using the keywords, and the program flow corresponding to the natural language to be processed is finally obtained, so that the problem that in the prior art, when the natural language is directly processed, the key information in the natural language to be processed cannot be obtained, and the text conversion accuracy is not high is solved. In addition, by using the method provided by the embodiment of the application, the program flow corresponding to the natural language to be processed can be directly obtained, and the execution efficiency of the text is improved.
Fig. 2 is a schematic flowchart of a natural language conversion processing method according to another embodiment of the present application, and as shown in fig. 2, step S102 may further include:
s201, acquiring a plurality of keywords in the natural language to be processed according to a preset database.
S202, calling a data source, and obtaining the category corresponding to each keyword through matching the data source.
In the embodiment of the application, through the preset database, keywords matched with information prestored in the preset database are searched from the natural language to be processed, and a plurality of keyword information is obtained. In addition, a data source is called, the data source indicates the category of the keyword in the embodiment of the application, the acquired information of the plurality of keywords is matched with the information in the data source, and the category corresponding to the keyword is acquired.
In addition, it should be noted that, data information related to each category keyword is also prestored in the data source, and when the logic of the natural language to be processed is executed, the related data information may also be called from the data source, so that the execution process of the natural language to be processed is more complete.
For example: when the acquired natural language to be processed is 'when the credit investigation blacklist user exists in the relatives of the lender, the loan is not given to the lender', the identity information of the relatives close to the lender and the credit investigation information of all the close relatives can be acquired from the data source, and the acquisition of the information can be realized by butting the corresponding data platform. And judging whether the loan can be given to the lender or not by searching credit investigation information of the lender's relatives in the data source.
Furthermore, because the natural language is highly flexible, the generated program flow is wrong in order to avoid inaccuracy of the acquired keyword information. In the embodiment of the application, the preset database not only prestores preset keywords of each field, but also prestores synonyms corresponding to the preset keywords. Illustratively, when the acquired natural language to be processed is "when a credit-solicited blacklist user exists in a relative of a lender, no credit is given to the lender" and the acquired keyword information is "lender", the synonym related to "lender" may also be "borrower", "lender", and the like.
It can be understood that, in the embodiment of the present application, by pre-storing the synonym information corresponding to each preset keyword, the keyword information and the logic attribute information in the natural language to be processed can be completely acquired, and then the corresponding program flow is generated according to the keyword information and the logic attribute information, so that the accuracy of generating the program flow can be improved.
Fig. 3 is a flowchart illustrating a natural language conversion processing method according to another embodiment of the present application, and as shown in fig. 3, step S103 may further include:
s301, calling a data source.
S302, judging the logic attribute of each language segment in the natural language to be processed according to the keywords and the preset rule.
It should be noted that, in the embodiment of the present application, the data source indicates a logical relationship corresponding to the keyword in each language segment.
Optionally, the logic attribute may specifically include "conditional logic" and "execution logic". Wherein the "conditional logic" is composed of one or more judgment statements. The judgment statement comprises: indicators, operators, thresholds. The index may be the result of various modifiers after their derivation. Operators include, but are not limited to: greater than, less than, equal to, inclusive, exclusive. The "execution logic" may be an execution action and may include operations such as adding, deleting, modifying, and checking.
Fig. 4 is a flowchart illustrating a natural language conversion processing method according to another embodiment of the present application, and as shown in fig. 4, step S104 may further include:
s401, determining the atomic index and the derivative index of each language segment according to the category corresponding to each keyword.
S402, determining the sequence and branch logic among the language segments according to the logic attributes of the language segments.
And S403, generating a program flow corresponding to the natural language to be processed according to the sequence, the branch logic, the atomic indexes of each language segment and the derivative indexes.
The indexes can be divided into the following according to the processing process: atomic index, derivative index. In the embodiment of the application, the atomic index is an index which cannot be split in the service definition, and from the technical point of view, the atomic index is equivalent to a column in a database table; from the service perspective, the atomic index does not need processing calculation, and the service measurement is directly obtained. Such as: number, amount, age, gender, etc.
The derived index is the result of one or more atomic indexes and various modifiers. Such as: an index is defined, the index name is 'the order quantity of the Beijing express car in nearly 7 days', the corresponding data source path is an order list in a network appointment database, the original index is an order field, the modifier is Beijing, and the time period is nearly 7 days.
Sequential logic may be logic that is executed in segments in sequence, such as: "when the person in charge receives the customer's order, the process is started", "if the task is not completed within two days, the process is terminated", etc.
The branching logic is used to control the flow of the workflow in the speech segment. The execution logic for example: the rule set A is executed if the age is less than 18 years old, the rule set B is executed if the age is greater than or equal to 18 years old and less than 60 years old, and the rule set C is executed otherwise.
And further, generating a program flow corresponding to the natural language to be processed according to the sequence, the branch logic, the atomic indexes of each language segment and the derivative indexes.
Fig. 5 is a flowchart illustrating a natural language conversion processing method according to another embodiment of the present application, and as shown in fig. 5, after acquiring a plurality of keywords from a natural language to be processed according to a preset database, the method further includes:
s501, displaying the keywords through the display equipment.
S502, receiving correction information based on the keywords, and acquiring a plurality of corrected keywords.
Due to the characteristic of high flexibility of natural language, some new industry keywords may appear after a certain period of time. In the embodiment of the application, in order to enable the generated program flow to be more accurate, a keyword correction module is further added.
Specifically, in this embodiment, the keywords may also be displayed through the display device, and when the professional finds that the obtained keyword information is incorrect, the obtaining module may receive the correction information of the professional for the keywords, and obtain the plurality of keywords by using the corrected keyword information.
In addition, on the basis of receiving the correction information of the professional, the acquisition module can also add the correction keywords into a preset database, so that the next use is facilitated.
Fig. 6 is a flowchart illustrating a natural language conversion processing method according to another embodiment of the present application, and as shown in fig. 6, step S101 may further include:
s601, collecting natural language audio data.
S602, converting the natural language audio data into an initial natural language text as a natural language to be processed.
In a possible implementation manner, the user may also directly input the text data, and then the text data may be directly used as the natural language to be processed.
In another possible implementation manner, if the user inputs voice data, in order to facilitate subsequent information extraction, in this embodiment of the application, after the natural language audio data is acquired, the natural language audio data may be further converted into an initial natural language text by using a voice conversion processing technology, and the initial natural language text is used as the natural language to be processed.
The following describes a device and a storage medium for executing the natural language conversion processing method provided by the present application, and specific implementation procedures and technical effects thereof are referred to above, and will not be described again below.
Fig. 7 is a schematic diagram of a natural language conversion processing apparatus according to an embodiment of the present application, and as shown in fig. 7, the apparatus may include: an acquisition unit 701, a judgment unit 702, and a generation unit 703;
an obtaining unit 701, configured to obtain a natural language to be processed;
acquiring a plurality of keywords in the natural language to be processed according to a preset database, and acquiring categories corresponding to the keywords;
a determining unit 702, configured to determine a logical attribute of each language segment in the natural language to be processed according to the keyword;
the generating unit 703 is configured to generate a program flow corresponding to the natural language to be processed according to the logic attribute of each language segment and the category corresponding to each keyword.
Optionally, the obtaining unit 701 is specifically configured to obtain a plurality of keywords in the natural language to be processed according to a preset database;
and calling a data source, and acquiring the category corresponding to each keyword by matching the data source, wherein the data source indicates the category of the keyword.
Optionally, the determining unit 702 is specifically configured to invoke a data source; and judging the logic attribute of each language segment in the natural language to be processed according to the keywords and a preset rule, wherein the data source indicates the logic relationship corresponding to the keywords in each language segment.
Optionally, the generating unit 703 is specifically configured to determine an atomic index and a derivative index of each speech segment according to the category corresponding to each keyword;
determining the sequence and branch logic among the language segments according to the logic attributes of the language segments;
and generating a program flow corresponding to the natural language to be processed according to the sequence, the branch logic, the atomic indexes of each language segment and the derivative indexes.
Fig. 8 is a schematic diagram of a natural language conversion processing apparatus according to another embodiment of the present application, and as shown in fig. 8, the apparatus further includes: a display unit 704;
a display unit 704 for displaying the keywords through a display device;
an obtaining unit 701 is configured to receive correction information based on the keywords, and obtain a plurality of corrected keywords.
Optionally, the obtaining unit 701 is specifically configured to collect natural language audio data;
and converting the natural language audio data into an initial natural language text as the natural language to be processed.
Fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application, including: a processor 710, a storage medium 720 and a bus 730, wherein the storage medium 720 stores machine-readable instructions executable by the processor 710, when the electronic device is operated, the processor 710 communicates with the storage medium 720 through the bus 730, and the processor 710 executes the machine-readable instructions to perform the steps of the above-mentioned method embodiments. The specific implementation and technical effects are similar, and are not described herein again.
The embodiment of the application provides a storage medium, wherein a computer program is stored on the storage medium, and the computer program is executed by a processor to execute the method.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to perform some steps of the methods according to the embodiments of the present application. And the aforementioned storage medium includes: a U disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A natural language conversion processing method, comprising:
acquiring a natural language to be processed;
acquiring a plurality of keywords in the natural language to be processed according to a preset database, and acquiring a category corresponding to each keyword;
judging the logic attribute of each language segment in the natural language to be processed according to the keyword;
and generating a program flow corresponding to the natural language to be processed according to the logic attribute of each language segment and the category corresponding to each keyword.
2. The method of claim 1, wherein the obtaining a plurality of keywords from the natural language to be processed according to a preset database, and obtaining a category corresponding to each keyword comprises:
acquiring a plurality of keywords in the natural language to be processed according to a preset database;
and calling a data source, and obtaining the category corresponding to each keyword by matching the data source, wherein the data source indicates the category of the keyword.
3. The method according to claim 1, wherein the determining the logical attribute of each segment in the natural language to be processed according to the keyword includes:
calling a data source;
and judging the logic attribute of each language segment in the natural language to be processed according to the keywords and a preset rule, wherein the data source indicates the logic relationship corresponding to the keywords in each language segment.
4. The method according to any one of claims 1 to 3, wherein the generating a program flow corresponding to the natural language to be processed according to the logical attribute of each language segment and the category corresponding to each keyword includes:
determining an atomic index and a derivative index of each word segment according to the category corresponding to each keyword;
determining the sequence and branch logic among the language segments according to the logic attributes of the language segments;
and generating a program flow corresponding to the natural language to be processed according to the sequence, the branch logic, the atomic indexes and the derivative indexes of the language segments.
5. The method for natural language conversion processing according to claim 1, wherein the method further comprises, after obtaining a plurality of keywords from the natural language to be processed according to a preset database:
displaying the keywords through a display device;
and receiving correction information based on the keywords, and acquiring a plurality of corrected keywords.
6. The method according to claim 1, wherein the obtaining the natural language to be processed includes:
collecting natural language audio data;
and converting the natural language audio data into an initial natural language text as the natural language to be processed.
7. A natural language conversion processing apparatus, comprising: an acquisition unit, a judgment unit and a generation unit;
the acquisition unit is used for acquiring the natural language to be processed;
acquiring a plurality of keywords in the natural language to be processed according to a preset database, and acquiring a category corresponding to each keyword;
the judging unit is used for judging the logic attribute of each language segment in the natural language to be processed according to the keyword;
and the generating unit is used for generating a program flow corresponding to the natural language to be processed according to the logic attribute of each language segment and the category corresponding to each keyword.
8. The apparatus according to claim 7, wherein the acquiring unit is specifically configured to acquire a plurality of keywords from the natural language to be processed according to a preset database;
and calling a data source, and obtaining the category corresponding to each keyword by matching the data source, wherein the data source indicates the category of the keyword.
9. An electronic device, comprising: a processor, a storage medium and a bus, the storage medium storing machine-readable instructions executable by the processor, the processor and the storage medium communicating via the bus when the electronic device is operating, the processor executing the machine-readable instructions to perform the steps of the method according to any one of claims 1-6.
10. A storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011275097.9A CN112328780A (en) | 2020-11-13 | 2020-11-13 | Natural language conversion processing method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011275097.9A CN112328780A (en) | 2020-11-13 | 2020-11-13 | Natural language conversion processing method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112328780A true CN112328780A (en) | 2021-02-05 |
Family
ID=74317619
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011275097.9A Pending CN112328780A (en) | 2020-11-13 | 2020-11-13 | Natural language conversion processing method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112328780A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101930428A (en) * | 2009-06-18 | 2010-12-29 | 万继华 | System and method for ensuring computer to understand natural languages |
| KR20160007017A (en) * | 2014-07-10 | 2016-01-20 | 네이버 주식회사 | Method and system for searching by using natural language query |
| CN106033466A (en) * | 2015-03-20 | 2016-10-19 | 华为技术有限公司 | Database query method and device |
| CN111177184A (en) * | 2019-12-24 | 2020-05-19 | 深圳壹账通智能科技有限公司 | Structured query language conversion method based on natural language and related equipment thereof |
-
2020
- 2020-11-13 CN CN202011275097.9A patent/CN112328780A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101930428A (en) * | 2009-06-18 | 2010-12-29 | 万继华 | System and method for ensuring computer to understand natural languages |
| KR20160007017A (en) * | 2014-07-10 | 2016-01-20 | 네이버 주식회사 | Method and system for searching by using natural language query |
| CN106033466A (en) * | 2015-03-20 | 2016-10-19 | 华为技术有限公司 | Database query method and device |
| CN111177184A (en) * | 2019-12-24 | 2020-05-19 | 深圳壹账通智能科技有限公司 | Structured query language conversion method based on natural language and related equipment thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101566997B (en) | Determining words related to given set of words | |
| US9524291B2 (en) | Visual display of semantic information | |
| JP5111423B2 (en) | Document examination support apparatus, document examination support method and program | |
| US6496838B1 (en) | Database reconciliation method and system | |
| CN112667794A (en) | Intelligent question-answer matching method and system based on twin network BERT model | |
| CN105408890A (en) | Performing an operation relative to tabular data based upon voice input | |
| WO2019024692A1 (en) | Speech input method and device, computer equipment and storage medium | |
| US10599760B2 (en) | Intelligent form creation | |
| CN106557463A (en) | Sentiment analysis method and device | |
| WO2023024975A1 (en) | Text processing method and apparatus, and electronic device | |
| JP2011233162A (en) | System, method, and software for assessing ambiguity of medical terms | |
| CN111626813A (en) | Product recommendation method and system | |
| CN112069783A (en) | Medical record input method and input system thereof | |
| EP2673687A2 (en) | Visual display of semantic information | |
| CN109299238B (en) | Data query method and device | |
| US20220129491A1 (en) | Method for supporting agent and computing device thereof | |
| CN116662495A (en) | Question-answering processing method, and method and device for training question-answering processing model | |
| JP2006023968A (en) | Unique expression extracting method and device and program to be used for the same | |
| CN112328780A (en) | Natural language conversion processing method and device, electronic equipment and storage medium | |
| JP2019145102A (en) | Dialog management server, dialog management method, and program | |
| CN112989003B (en) | Intention recognition method, device, processing equipment and medium | |
| JP5679400B2 (en) | Category theme phrase extracting device, hierarchical tagging device and method, program, and computer-readable recording medium | |
| Teixeira Lopes et al. | Assisting health consumers while searching the web through medical annotations | |
| CN113434653A (en) | Method, device and equipment for processing query statement and storage medium | |
| KR20190084370A (en) | A Intelligent Method for Searching Legal Information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |