Detailed Description
In order to better understand the solution of the present application, the following description will clearly and completely describe the solution of the embodiment of the present application with reference to the accompanying drawings in the embodiment of the present application, and it is obvious that the described embodiment is only a part of the embodiment of the present application, not all the embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure. In addition, the technical scheme of the application is used for acquiring, storing, using, processing and the like of the data, and the data accords with relevant regulations of national laws and regulations.
The principles and spirit of the present application are explained in detail below with reference to several representative embodiments thereof.
In operation, service personnel often do not know how to draw the flow chart, and only the simple language is used for directly drawing the working process, so that the demand analysis personnel understand the flow chart in error and easily miss key control points, and the software for drawing the flow chart is incomplete. Secondly, due to the professionality of the drawing of the flow chart and the current multiple sets of standards of the drawing of the flow chart, and all standards have no official Chinese translation version, the problem of inconsistent understanding caused by non-uniform concepts exists in use. Moreover, the Chinese semantics have larger ambiguity, and the logic uncovered points are very difficult to realize in the process carding stage, so that the process is frequently reworked. Finally, the traditional flow chart software does not have an artificial intelligent module and lacks history data, so that the software does not have a self-iteration function and cannot progress with time.
Existing flow chart drawing tools require users to be very familiar with the flow design specifications to be able to use them smoothly, and new users often have no assistance in facing numerous symbols. Even if it can be used by hand, it takes a long time to increase the drawing speed. Furthermore, the existing flow chart drawing tool requires users to refine logic words according to service description, then sort and draw flow chart drafts according to logic relations, and finally use the drawing tool to fix the drafts according to the drafts. In the whole process, the tool is only used as a recording tool, and the overall value is not outstanding. In addition, the existing flow chart drawing tool has complex use interface, and advanced functions need user definition, so that the use experience is poor. Further, the existing flow chart drawing tool cannot accumulate historical analysis results and construct an asset library to form stackable progress, so that software iteration is slow and is easy to replace by other similar software.
Based on the above problems, the present application provides a method for drawing a flowchart, by restoring the problems to the original scene, from the service perspective, adopting a manner of directly analyzing voice, disassembling a main text and a branch text from the main text and the branch text, and finally drawing the flowchart. The application mainly adopts a voice recognition technology, a natural language processing technology, a flow drawing technology and an artificial intelligence technology. The voice recognition technology is used for collecting user voice and analyzing to obtain structured data for subsequent processing. The natural language processing technology is used for analyzing Chinese language, splitting logic keywords and sorting and archiving, and the flow drawing technology is used for drawing a flow chart according to Chinese semantics and prompting flow risk points. Artificial intelligence techniques are used to analyze historical data and iterate software logic.
Referring to fig. 1, an application scenario diagram of a drawing method of a flow chart provided in the present application is provided, where a user needs to draw its own workflow into a flow chart, the user may express its own workflow by voice, that is, input a voice to be drawn, then an electronic device processes the voice to be drawn, outputs a target flow chart corresponding to the voice to be drawn, and displays the target flow chart to the user, so that the user may efficiently obtain a high-quality target flow chart.
The following describes the technical scheme of the present application in detail through specific embodiments. It should be noted that the following embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.
Referring to fig. 2, a flowchart is provided for a step of a drawing method of a flowchart according to an embodiment of the present application, where the drawing method of the flowchart specifically includes the following steps:
s201, acquiring a recognition text obtained by performing voice recognition on voice to be drawn.
In this embodiment of the present application, before obtaining a recognition text obtained by performing speech recognition on a speech to be drawn, the method further includes: the user triggers the selection of the flowchart standard through the interface, and in the embodiment of the application, various flowchart standards can be preconfigured for the user to select, for example, different flowchart standards for different languages.
Further, after the user determines the flow chart criteria, the voice to be drawn is input. The voice to be drawn requires the user to have moderate speech speed, clear spell and standard voice as much as possible, for example, chinese uses standard mandarin.
In the embodiment of the application, the recognition text obtained by performing voice recognition on the voice to be drawn by adopting a voice recognition technology is adopted.
The method includes that a bank staff member needs to conduct a flow chart of account opening on a bank, the staff member inputs a to-be-drawn voice to conduct recognition, and a recognition text is obtained, for example, firstly, the staff member fills out an account opening application form, then checks whether the account opening application form is filled out accurately, if yes, the staff member is conducted next, if not, the staff member is enabled to modify, and then checks if the account opening application form is filled out accurately, the staff member provides an effective identification document, what the effective identification document provided by the staff member is, an identification card and a passport, then the identity information of the staff member is verified, and different authentication systems are needed to be used for verifying the different effective identification documents, if the identification card adopts an A system, and if the passport adopts a B system, the staff member adopts a B system. And then transacting account opening procedures, generating account numbers, signing related agreements by clients, and completing account opening by contracts.
S202, analyzing the identification text to obtain a plurality of key texts in the identification text.
In the embodiment of the application, the identification file is analyzed by adopting a natural language processing technology, so that a plurality of key texts are obtained. The plurality of key texts belongs to the entity text, triplet, intent or event class.
For example, for the above identified text, key text is obtained such as: "customer", "fill out", "open account application form", "check", "if accurate", "if" customer modification "," if "valid", "identification document", "identification card", "or", "passport", "verification", "identification information", "verification by authentication system", "if" system a "," system B "," transacting "," account opening procedure "," generating "," account number "," signing related agreement "," contract ".
In the embodiment of the application, an algorithm model can be trained in advance, the algorithm model comprises a word vector space model, feature characterization can be performed on each text unit, and then the characterization vector is marked, so that corresponding key texts can be obtained.
Further, after segmenting the recognition text to obtain a plurality of text units, the method further comprises: determining whether the modified text unit is explicit; if not, outputting prompt information for prompting the user to modify the text unit.
For example, in the above-mentioned identification text, "is an identification card, and the passport" indicates to the user whether the identification card and the passport "are the identification card or the passport" after outputting, so that the user inputs a voice segment again for the ambiguous meaning, the text after the re-identification replaces the ambiguous text unit, and if the voice input again by the user is identified as "being an identification card or a passport", the text unit "is an identification card or a passport" may be modified to be an identification card or a passport ".
And S203, classifying the plurality of key texts to obtain a plurality of text categories.
Wherein the plurality of text categories includes: decision making, body making and action making.
Wherein, decision-making key text such as words of "whether", "if" and the like.
Specifically, in the modeling process, each key text is classified, the classification rule includes logic (whether the key text is decision-making text), a main body, actions and the like, then word segmentation, part-of-speech tagging, proper noun tagging, morpheme tagging, verb and adjective special usage tagging and phrase tagging are performed on the key text of each text category, and the tagged key text can be stored in an asset library.
S204, determining a main text according to a plurality of text categories, at least one key text included in the text categories and the semantics of the identification text.
Finally, summarizing and analyzing semantic information of the identification text, removing nonsensical words and sentences (such as first, next, then, etc. in the above description), sorting to obtain a main text, marking decision texts in the main text, and next, sorting branch processes from the identification text to the next step, recording if contradiction points are met, and prompting a user to modify.
S205, determining branch texts according to decision-making key texts in the main texts and the semantics of the recognized texts.
In this embodiment of the present application, for example, the identification text is "first, the client fills out an account opening application form, then checks whether the account opening application form is filled out accurately, if yes, then proceeds to the next step, if no, then the client is allowed to modify, and then checks again after modification, if the account opening application form is filled out accurately, then the client is required to provide a valid identification document, checks what the valid identification document provided by the client is, is an identification card and a passport, then verifies the identity information of the client, and needs to verify by using different authentication systems for different valid identification documents, if the identity card adopts the a system, if the passport adopts the B system. And then transacting account opening procedures, generating account numbers, signing related agreements by clients, and completing account opening by contracts. The key texts are "customer", "filling", "account opening application form", "checking", "whether accurate", "if" customer modification "," if "valid", "identification document", "identification card", "or", "passport", "verification", "identity information", "verification by authentication system", "if", "a system", "B system", "transacting", "account opening procedure", "generating", "account number", "signing related agreement", "contract", the backbone texts which can be obtained are: 1) The client fills out an account opening application form; 2) Checking whether an account opening application form is accurate; 3) The client provides a valid identification document; 4) Verifying the valid certificate; 5) Handling account opening procedures and generating account numbers; 6) The client signs the relevant agreement and contract. Identifying the decision text as 2) checking if the account opening application form is accurate and 4) verifying the valid certificate. Wherein, the branch text corresponding to decision text 2) is: the account opening application form is accurate, and the step 3) is entered; the account opening application form is inaccurate; the client modifies the application form and proceeds to step 2). Decision text 4) the corresponding branch text is: if the identification card is verified by the A system, if the passport is verified by the B system.
The foregoing is merely illustrative, and the present application is not limited to a specific application scenario, and may be applied to drawing a flowchart of an arbitrary scenario. According to the method and the device, the modeling model can be trained in advance, so that the modeling model learns and processes the key text and the recognition text to obtain the corresponding trunk text and the corresponding branch text.
S206, drawing a target flow chart corresponding to the voice to be drawn according to the main text and the branch text.
The method comprises the steps of presetting business element texts in an application scene, and extracting the same business element texts from a main text and a branch text based on the preset business element texts. For example, the "account opening" may further obtain a graphic corresponding to the "account opening". The business element text and the graph are also preset corresponding relations. The graphics are graphics required for drawing the flow chart, such as rectangle, rounded rectangle, etc.
In the embodiment of the application, an interface can be used for drawing a target flow chart, and the interface acquires all the business element texts of the trunk text and the branch text, then acquires the graph defined in the flow chart standard, and establishes a mapping relation item by item.
Wherein different flow chart standards correspond to different graphics, multiple sets of flow chart standards may be configured, the configuration supporting a later update. Finally, the interface extracts all the graphics to finish the drawing of the target flow chart.
Illustratively, the target flow image drawn according to the above-described main text and branch text refers to fig. 3. The present application may draw the target flowchart in other manners according to the settings, and is not limited herein.
According to the embodiment of the application, the recognition text obtained by performing voice recognition on the voice to be drawn is obtained; analyzing the identification text to obtain a plurality of key texts in the identification text; modeling based on the semantics of the identification text and the text categories of a plurality of key texts, and determining a trunk text and a branch text; and drawing a target flow chart corresponding to the voice to be drawn according to the trunk text and the branch text, so as to realize accurate and efficient drawing of the target flow chart.
In the embodiment of the application, the generated target flow chart is editable, and the user can modify the target flow chart according to the requirement, which is not limited.
In an alternative embodiment, further comprising: analyzing the target flow chart to obtain scene data and decision data of the target flow chart; establishing a mapping relation of scene data, decision data and user identification; and storing a mapping relation, wherein the mapping relation is used for prompting a user to draw the components and the patterns of the flow chart next time.
In the embodiment of the application, the scene data includes the key text related to the scene, such as the "account opening application form", "identification document", "account opening procedure" and "account number". Decision data includes decision-making key text, such as "if", "if" as described above. The scene data represents a user work scene. The decision data represents user decision habits. And a mapping relation of scene data, decision data and user identification can be established and stored in an asset library.
In the present embodiment, the asset library is responsible for accumulating some of the key text generated in the above process, including morphemes, words, decisions, usage habits, and the like.
In addition, an artificial intelligent module can be built in the asset library, and each time a user draws a flow chart by using the method, the module records scene data, decision data and the like, analyzes the voice newly input by the user, and performs modeling analysis by combining the scene data decision data.
Further, the correlation coefficients are calculated by distinguishing different situations through machine learning, fitting function (linear/nonlinear) construction and the like. The artificial intelligence module also periodically analyzes the behavioral relevance of different users. And storing all analysis results to an asset library. When the user uses the method next time, the module prejudges the intention of the user in advance according to the analysis result of the asset library, prompts the user for the subsequent potential flow chart components and patterns after each step of execution is completed, and provides whole chart preview, thereby rapidly helping the user to complete the drawing of the flow chart.
In the embodiment of the application, the method and the device can be used by a user in work, the voice to be drawn or the original text can be directly input in work, and the target flow chart can be automatically analyzed, processed and processed by adopting the scheme of the application. For the contradiction, the user may be prompted to make a modification or confirmation. After the prompt is obtained, the user can continue to conduct deep investigation, so that the whole feedback period is greatly shortened, the feedback can be continuously conducted in the working period, and the drawing accuracy of the flow chart is improved. Meanwhile, the method and the device can help the user to process most analysis work, save the energy of the user and improve the drawing efficiency of the flow chart.
Referring to fig. 4, a flowchart is provided for a step of a drawing method of a flowchart according to an embodiment of the present application, where the drawing method of the flowchart specifically includes the following steps:
s401, acquiring a recognition text obtained by performing voice recognition on voice to be drawn.
The specific implementation process of this step refers to S201, and will not be described here again.
S402, dividing the recognition text to obtain a plurality of text units.
Wherein each text unit corresponds to a semantic meaning and a grammar.
Further, after segmenting the recognition text to obtain a plurality of text units, the method further comprises: determining whether the modified text unit is explicit; if not, outputting prompt information for prompting the user to modify the text unit.
Specifically, the recognized text is cut into a series of text units having semantics and grammar through operations such as sentence breaking, word segmentation and the like.
S403, carrying out feature characterization by adopting a word vector space model for each text unit in the plurality of text units to obtain a characterization vector of each text unit.
In the embodiment of the application, an algorithm model can be trained in advance, the algorithm model comprises a word vector space model, feature characterization can be performed on each text unit, and then the characterization vector is marked, so that corresponding key texts can be obtained.
And S404, labeling each characterization vector to obtain a plurality of key texts in the identification text.
Then, for each text unit, a word vector space model may be used to obtain a token vector, and the token vectors of the text units may form a matrix, which is a numeric representation of the identified text. And then, processing the matrix by adopting a classification algorithm, a sequence labeling and other modes, so that the key text in the identification text can be obtained.
In the embodiment of the application, the key text contains contents required for modeling such as language logic, entity information and the like, and the contents are transferred to a modeling model layer for modeling.
S405, classifying the plurality of key texts to obtain a plurality of text categories.
The specific implementation procedure of this step refers to S203, and will not be described here again.
S406, determining a main text according to a plurality of text categories, at least one key text included in the text categories and the semantics of the identification text.
The specific implementation process of this step refers to S204, and will not be described here again.
S407, determining branch texts according to decision-making key texts in the main texts and the semantics of the recognized texts.
The specific implementation procedure of this step refers to S205, and will not be described here again.
And S408, extracting service element texts in the main text and the branch text.
The method comprises the steps of presetting business element texts in an application scene, and extracting the same business element texts from a main text and a branch text based on the preset business element texts. For example, the "account opening" may further obtain a graphic corresponding to the "account opening".
S409, obtaining the graph in the flow chart standard corresponding to the business element text.
In the embodiment of the application, the text and the graph of the business element are also preset corresponding relations. The graphics are required by drawing a flow chart, such as rectangle, rounded rectangle and the like
S410, drawing a target flow chart according to the main text, the branch text and the graphics.
In the embodiment of the application, different flow chart standards correspond to different graphs, and multiple sets of flow chart standards can be configured, and the configuration supports later updating. Finally, the interface extracts all the graphics to finish the drawing of the target flow chart.
S411, determining whether semantic contradiction exists in the target flow chart;
and S412, if the semantic contradiction exists, outputting the semantic contradiction for prompting the user to modify the target flow chart.
In the embodiment of the application, the generated target flow chart is editable, and the user can modify the target flow chart according to the requirement, which is not limited.
If semantic contradiction exists, the user can modify the target flow chart, so that the flexibility of the target flow chart is improved.
In the embodiment of the application, the method and the device can be used by a user in work, the voice to be drawn or the original text can be directly input in work, and the target flow chart can be automatically analyzed, processed and processed by adopting the scheme of the application. For the contradiction, the user may be prompted to make a modification or confirmation. After the prompt is obtained, the user can continue to conduct deep investigation, so that the whole feedback period is greatly shortened, the feedback can be continuously conducted in the working period, and the drawing accuracy of the flow chart is improved. Meanwhile, the method and the device can help the user to process most analysis work, save the energy of the user and improve the drawing efficiency of the flow chart.
The following are device embodiments of the present application, which may be used to perform method embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.
Referring to fig. 5, a schematic diagram of a drawing device of a flowchart is provided in an embodiment of the present application, where a drawing device 500 of the flowchart includes: an acquisition module 501, a parsing module 502, a classification module 503, a first determination module 504, a second determination module 505 and a drawing module 506; wherein:
an obtaining module 501, configured to obtain a recognition text obtained by performing speech recognition on a speech to be drawn;
the parsing module 502 is configured to parse the recognition text to obtain a plurality of key texts in the recognition text;
the classifying module 503 is configured to classify a plurality of key texts, to obtain a plurality of text categories, where the plurality of text categories include: decision making, body and action;
a first determining module 504, configured to determine a backbone text according to a plurality of text categories, at least one key text included in the text categories, and semantics of the identified text;
a second determining module 505, configured to determine a branch text according to the decision-making key text in the main text and the semantic meaning of the identified text;
and the drawing module 506 is configured to draw a target flowchart corresponding to the voice to be drawn according to the trunk text and the branch text.
In one embodiment of the present application, the parsing module 502 is configured to segment and identify a text, so as to obtain a plurality of text units, where each text unit corresponds to a semantic meaning and a grammar; for each text unit in the plurality of text units, carrying out feature characterization by adopting a word vector space model to obtain a characterization vector of each text unit; labeling each characterization vector to obtain a plurality of key texts in the identification text.
In one embodiment of the present application, the first determining module 504 is further configured to determine whether the modified text unit is explicit after segmenting the identified text to obtain a plurality of text units; if not, outputting prompt information for prompting the user to modify the text unit.
In one embodiment of the present application, the drawing module 506 is specifically configured to extract service element texts in the trunk text and the branch text; acquiring a graph in a flow chart standard corresponding to the text of the business element; and drawing the target flow chart according to the trunk text, the branch text and the graph.
In one embodiment of the present application, the first determining module 504 is further configured to determine whether there is a semantic contradiction in the target flowchart after the target flowchart is drawn according to the main text and the branch text, and the graphics; if the semantic contradiction exists, the semantic contradiction is output and used for prompting the user to modify the target flow chart.
In one embodiment of the present application, further comprising: a saving module (not shown) for analyzing the target flow chart to obtain scene data and decision data of the target flow chart; establishing a mapping relation of scene data, decision data and user identification; and storing a mapping relation, wherein the mapping relation is used for prompting a user to draw the components and the patterns of the flow chart next time.
According to the technical scheme, the drawing device of the flow chart provided by the application obtains the recognition text obtained by performing voice recognition on the voice to be drawn; analyzing the identification text to obtain a plurality of key texts in the identification text; modeling based on the semantics of the identification text and the text categories of a plurality of key texts, and determining a trunk text and a branch text; and drawing a target flow chart corresponding to the voice to be drawn according to the trunk text and the branch text, so as to realize accurate and efficient drawing of the target flow chart. In addition, the specific implementation process refers to the above method embodiment, and is not described herein.
It should be noted that, it should be understood that the division of the modules of the above apparatus is merely a division of a logic function, and may be fully or partially integrated into a physical entity or may be physically separated. And these modules may all be implemented in software in the form of calls by the processing element; or can be realized in hardware; the method can also be realized in a form of calling software by a processing element, and the method can be realized in a form of hardware by a part of modules. For example, the processing module may be a processing element that is set up separately, may be implemented in a chip of the above-mentioned apparatus, or may be stored in a memory of the above-mentioned apparatus in the form of program codes, and the functions of the above-mentioned processing module may be called and executed by a processing element of the above-mentioned apparatus. The implementation of the other modules is similar. In addition, all or part of the modules can be integrated together or can be independently implemented. The processing element here may be an integrated circuit with signal processing capabilities. In implementation, each step of the above method or each module above may be implemented by an integrated logic circuit of hardware in a processor element or an instruction in a software form.
For example, the modules above may be one or more integrated circuits configured to implement the methods above, such as: one or more specific integrated circuits (application specific integrated circuit, ASIC), or one or more microprocessors (digital signal processor, DSP), or one or more field programmable gate arrays (field programmable gate array, FPGA), or the like. For another example, when a module above is implemented in the form of a processing element scheduler code, the processing element may be a general purpose processor, such as a central processing unit (central processing unit, CPU) or other processor that may invoke the program code. For another example, the modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions in accordance with embodiments of the present application are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by wired (e.g., coaxial cable, fiber optic, digital Subscriber Line (DSL)), or wireless (e.g., infrared, wireless, microwave, etc.) means from one website, computer, central, or data center. Computer readable storage media can be any available media that can be accessed by a computer or data storage devices such as a central office, data center, or the like, that contains an integration of one or more available media. Usable media may be magnetic media (e.g., floppy disks, hard disks, magnetic tape), optical media (e.g., DVD), or semiconductor media (e.g., solid State Disk (SSD)), among others.
Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 6, the electronic device may include: a processor 61, a memory 62, a communication interface 63 and a system bus 64. The memory 62 and the communication interface 63 are connected to the processor 61 through the system bus 64 and complete communication with each other, the memory 62 is used for storing computer execution instructions, the communication interface 63 is used for communicating with other devices, and the scheme of the above embodiment is implemented when the processor 61 executes the computer execution instructions.
The system bus referred to in fig. 6 may be a peripheral component interconnect standard (peripheral component interconnect, PCI) bus, or an extended industry standard architecture (extended industry standard architecture, EISA) bus, or the like. The system bus may be classified into an address bus, a data bus, a control bus, and the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus. The communication interface is used for realizing communication between the database access device and other devices (such as a user side, a read-write library and a read-only library). The memory may comprise random access memory (random access memory, RAM) and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The processor may be a general-purpose processor, including a Central Processing Unit (CPU), a network processor (network processor, NP), etc.; but may also be a digital signal processor DSP, an application specific integrated circuit ASIC, a field programmable gate array FPGA or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component.
Optionally, an embodiment of the present application further provides a computer readable storage medium, where a computer program is stored, where the computer program when executed by a processor causes an electronic device to perform a method according to the above embodiment.
Optionally, an embodiment of the present application further provides a computer program product, on which a computer program is stored, which when executed by a processor causes an electronic device to perform the method of the above embodiment.
In the present application, "at least one" means one or more, and "a plurality" means two or more. "and/or", describes an association relationship of an association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate: a alone, a and B together, and B alone, wherein a, B may be singular or plural. The character "/" generally indicates that the front and rear associated objects are an "or" relationship; in the formula, the character "/" indicates that the front and rear associated objects are a "division" relationship. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b, or c may represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, c may be single or plural.
It will be appreciated that the various numerical numbers referred to in the embodiments of the present application are merely for ease of description and are not intended to limit the scope of the embodiments of the present application. In the embodiments of the present application, the sequence number of each process does not mean the sequence of execution sequence, and the execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application.