CN113885825A

CN113885825A - Method and device for intelligently creating application form

Info

Publication number: CN113885825A
Application number: CN202111086298.9A
Authority: CN
Inventors: 郭鹏飞; 寸志清; 杨涛; 张伟涛; 阴亮; 陈德志
Original assignee: State Grid Business Travel Cloud Technology Co ltd; State Grid E Commerce Co Ltd; State Grid E Commerce Technology Co Ltd
Current assignee: State Grid Business Travel Cloud Technology Co ltd; State Grid E Commerce Co Ltd; State Grid E Commerce Technology Co Ltd
Priority date: 2021-09-16
Filing date: 2021-09-16
Publication date: 2022-01-04

Abstract

The application provides a method and a device for intelligently creating a request form, which add an intelligent voice input function on the basis of common business software, and acquire voice information (at least comprising one of time, place and intention) input by a user; performing character recognition and semantic reasoning on the voice information, and determining key entity information contained in the voice information and a user intention corresponding to the user; skipping to corresponding product orders (reservation orders, inquiry orders and business trip request orders) according to the user intention; and filling the key entity information contained in the voice information into a text box corresponding to the product order. The intelligent business trip software can be realized by the intelligent business trip platform, the butt joint of the business trip platform and the intelligent voice platform is realized, the purposes of systematization and intellectualization of relevant business in business trips conveniently, accurately and efficiently are achieved, the hands of a user are liberated, the efficiency of creating an application form is improved, and the user experience is improved.

Description

Method and device for intelligently creating application form

Technical Field

The present application relates to the field of data processing technologies, and in particular, to a method and an apparatus for intelligently creating a request form.

Background

At present, the business trip software is mainly intelligent terminal software for business trip, supports booking of air tickets, trains and hotels, inquires about the condition of relatively new related navigation in real time, supports functions of collective mobile phone online reservation and the like, and has a function of not being powerful. However, the intelligent terminal software needs to manually input or select the time, the place, the intention and other related information to realize the application process, and cannot liberate the hands of the user, so that the efficiency of creating the business application form is low, and the user experience is poor.

Disclosure of Invention

In view of the above problems, the present application provides a method and an apparatus for intelligently creating a request form, so as to intelligently input or select related information such as time, location, intention, etc., liberate both hands of a user, improve the efficiency of creating a request form, and improve user experience.

In order to achieve the above object, the present application provides the following technical solutions:

a method of intelligently creating an application form, comprising:

acquiring voice information input by a user, wherein the voice information at least comprises one of time, place and intention;

performing character recognition and semantic reasoning on the voice information, and determining key entity information contained in the voice information and a user intention corresponding to the user;

skipping to a corresponding product order according to the user intention, wherein the product order comprises: booking orders, inquiring orders and going-on-business application orders;

and filling the key entity information contained in the voice information into a text box corresponding to the product order.

Further, the performing text recognition and semantic reasoning on the voice information to determine key entity information contained in the voice information and the corresponding intention of the user includes:

performing character recognition on the voice information through a voice recognition technology, and converting the voice information into corresponding text information;

identifying the text information through a natural language processing technology, and extracting the key entity information from the text information;

and semantically reasoning the voice information through a multi-turn dialogue technology and a semantic reasoning technology, and determining the user intention corresponding to the user.

Further, the skipping to the corresponding product order according to the user intention includes:

when the user intention is recognized as a voice new application form, skipping to the voice new application form according to the user intention;

when the user intention is identified as the application form associated with the reason for public line, jumping to the application form associated with the reason for public line according to the user intention;

when the user intention is identified as specific service subscription, jumping to the specific service subscription application form according to the user intention;

when the user intention is identified as an unassociated application form, jumping to the unassociated application form according to the user intention;

when the user intention is recognized as the inquiry-only application form, jumping to the inquiry-only application form according to the user intention;

and when the user intention is recognized as the private reason outgoing application form, jumping to the private reason outgoing application form according to the user intention.

An apparatus for intelligently creating a request form, comprising:

the first processing unit is used for acquiring voice information input by a user, wherein the voice information at least comprises one of time, place and intention;

the second processing unit is used for performing character recognition and semantic reasoning on the voice information and determining key entity information contained in the voice information and user intention corresponding to the user;

a third processing unit, configured to jump to a corresponding product order according to the user intention, where the product order includes: booking orders, inquiring orders and going-on-business application orders;

and the fourth processing unit is used for filling the key entity information contained in the voice information into a text box corresponding to the product order.

Further, the second processing unit is specifically configured to:

Further, the third processing unit is specifically configured to:

A storage medium comprising a stored program, wherein a device on which the storage medium is located is controlled to perform a method of intelligently creating a request form as described above when the program is run.

An electronic device comprising at least one processor, and at least one memory, bus connected with the processor; the processor and the memory complete mutual communication through the bus; the processor is configured to invoke program instructions in the memory to perform the method of intelligently creating a request form as described above.

According to the method and the device for intelligently creating the application form, an intelligent voice input function is added on the basis of common business software, and voice information (at least comprising one of time, place and intention) input by a user is obtained; performing character recognition and semantic reasoning on the voice information, and determining key entity information contained in the voice information and a user intention corresponding to the user; skipping to corresponding product orders (reservation orders, inquiry orders and business trip request orders) according to the user intention; and filling the key entity information contained in the voice information into a text box corresponding to the product order. The intelligent business trip software can be realized by the intelligent business trip platform, the butt joint of the business trip platform and the intelligent voice platform is realized, the purposes of systematization and intellectualization of relevant business in business trips conveniently, accurately and efficiently are achieved, the hands of a user are liberated, the efficiency of creating an application form is improved, and the user experience is improved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

Fig. 1 is a schematic flowchart of a method for intelligently creating an application form according to an embodiment of the present application;

fig. 2 is a schematic view of a business process after a voice recognition function is added to business travel software disclosed in the embodiment of the present application;

FIG. 3 is a schematic diagram of a voice small assistant access scheme disclosed in an embodiment of the present application;

FIG. 4 is a schematic diagram illustrating an implementation of a small voice helper processing transaction disclosed in an embodiment of the present application;

FIG. 5 is a schematic diagram of a help function of a small voice assistant disclosed in an embodiment of the present application;

fig. 6 is a schematic flow chart illustrating the process of performing text recognition and semantic reasoning on the voice information to determine key entity information included in the voice information and an intention corresponding to the user, which is disclosed in the embodiment of the present application;

FIG. 7 is a schematic diagram of semantic reasoning analysis logic disclosed in an embodiment of the present application;

FIG. 8 is a diagram of a Long Short Term Memory (LSTM) algorithm and a gated round robin unit (GRU) algorithm disclosed in an embodiment of the present application;

FIG. 9 is a diagrammatic interface view of an implementation of creating an application form as disclosed in an embodiment of the present application;

FIGS. 10-13 are schematic diagrams illustrating a service flow of an intelligent voice service subscription disclosed in an embodiment of the present application;

FIG. 14 is a pictorial interface diagram illustrating an implementation of a request form associated with a line of interest disclosed in an embodiment of the present application;

FIGS. 15-17 are pictorial interface diagrams illustrating an implementation of a specific service subscription application form as disclosed in an embodiment of the present application;

FIG. 18 is an interface diagram illustrating an implementation of an unassociated application form as disclosed in an embodiment of the present application;

FIG. 19 is an illustrative interface diagram of an implementation of a query-only application form as disclosed in an embodiment of the present application;

FIGS. 20-21 are pictorial interface diagrams illustrating an implementation of a private release application form disclosed in an embodiment of the present application;

fig. 22 is a schematic structural diagram of an apparatus for intelligently creating a request form according to an embodiment of the present application;

fig. 23 is a schematic structural diagram of an electronic device disclosed in an embodiment of the present application.

Detailed Description

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 is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

Referring to fig. 1, a schematic flow chart of a method for intelligently creating a request form according to an embodiment of the present application is provided. As shown in fig. 1, an embodiment of the present application provides a method for intelligently creating a request form, where the method includes the following steps:

s101: acquiring voice information input by a user, wherein the voice information at least comprises one of time, place and intention.

In the embodiment of the application, an intelligent voice input function needs to be added on the basis of common business travel software, and the input voice is subjected to character recognition through the intelligent voice platform and is fed back to the business travel software. The intelligent business travel software is realized through an intelligent voice technology, the butt joint of the business travel platform and the intelligent voice platform is realized, and the purposes of systematizing and intelligentizing relevant business in business travel conveniently, accurately and efficiently are achieved.

It should be noted that, need to realize the butt joint of business trip platform and intelligent voice platform, let the user know this function tentatively, use this function, tentatively form the more convenient cognition of intelligent pronunciation, tentatively realize the pronunciation of business trip and speech recognition platform butt joint and application form and establish the function, business trip software increases the speech input function, carry out text recognition to input voice through intelligent voice platform, and feed back to the business trip, the business trip is filled in the mandatory information of establishing the business application form with the text information who gathers, as shown in fig. 2, reduce user's text input and cost of selection, raise the efficiency.

In this step, the implementation can be accessed through the small voice assistant, and specifically, the implementation of the small voice assistant and the demonstration of the small voice assistant help center are performed in three aspects:

firstly, the voice small assistant access diagram is shown in FIG. 3, 1) clicking the "+" button on the business trip application list page to pop out two selection buttons of "voice" and "manual"; 2) after the intelligent voice small assistant gets on line, a prompt is given after clicking '+' for the first time: "trial voice creation bar"; 3) clicking the "voice" button enters the voice creation page.

Second, the voice small helper handles the transaction implementation, as shown in FIG. 4, 1) chat default page prompt document: "I listen to, can try to say" I take the plane to go to Shanghai on tomorrow "; 2) long-press of a microphone starts voice input, and the shortest voice time is 1 second, and the longest voice time is 20 seconds; 3) below 1 second, toast prompt is given: "sorry, too short speaking duration"; 4) the long-press state is kept in the voice input process, the sound wave effect action is displayed, and the voice input is cut off after the voice input is lifted; 5) giving a countdown second reading prompt when the recording duration reaches 15 seconds: 5(4321) stopping recording after seconds, and locating below the sound wave effect; 6) when the time reaches 20 seconds, the voice is automatically uploaded, and the interaction is stopped; 7) after the voice input is finished, displaying the recognized case, adopting a business travel default head portrait at the head portrait of the user, simultaneously giving a prompt case by the small voice assistant, and giving a prompt of 'voice recognition' when waiting time appears in the voice uploading process; 8) the chat page is used for specially marking the time (departure date and return date), city (business trip city) and four traffic modes (plane, train, automobile and other) appearing in the voice recognition file of the user; 9) click "help" to go to the help page; clicking X to close the chat page; 10) clicking 'direct filling in' in a dialog box of the small assistant, jumping to a business trip application form establishing page, returning to the small assistant, storing the recorded information, and displaying a default page; 11) when the user still does not receive the feedback of the AI platform after the voice is recorded for 2 seconds, giving an error reporting prompt: "current network is unusual, please try to establish the application form again", increase the loading effect in the latency, the loading icon adopts the default style of business travel, the suggestion case: "in speech recognition"; 12) no matter what the user's speech relates to, the small assistant interacts with the user only once, and the small assistant gives the prompt: "you have generated a business application form without identifying the manual completion of the message acquisition request", specifically includes: departure place, destination, departure time, return time, transportation, business trip, etc.; 13) when the scene recognition fails and the voice is not recognized, giving a prompt: "sorry, i do not know very clearly what you want to do, please create a business application form manually", the follow-up intelligent voice will realize the whole scene operation access of inquiry, examination and approval, reservation and reimbursement, really realize the convenient service of the user, greatly improve the user experience, create a brand-new intelligent tour, and serve the tour platform.

Finally, the help function, if in question or improper operation during the use process, can be used to help solve the problem, as shown in fig. 5: 1) statically displaying a page without functional operation; 2) clicking "<" to return to the chat page; 3) clicking the closing page of 'knowing' and returning to the chat page; 4) and when the chat page is returned, the existing chat records are reserved.

S102: and performing character recognition and semantic reasoning on the voice information, and determining key entity information contained in the voice information and the user intention corresponding to the user.

In the embodiment of the application, the intelligent business trip voice assistant can replace traditional clicking and input operations through deep learning, voice recognition, natural language processing and multi-turn conversation technologies, accurately recognize user intentions and extract key entity information, and guide a user to complete page skipping, information query, event handling and business handling.

It should be noted that, as shown in fig. 6, the performing text recognition and semantic reasoning on the voice information to determine the key entity information included in the voice information and the corresponding intention of the user specifically includes the following steps:

s601: and performing character recognition on the voice information through a voice recognition technology, and converting the voice information into corresponding text information.

To illustrate further, Speech Recognition technology (ASR): also known as automatic speech recognition, the goal is to convert the lexical content of human speech into computer-readable input, such as keystrokes, binary codes or character sequences. Unlike speaker recognition and speaker verification, the latter attempts to recognize or verify the speaker who uttered the speech rather than the vocabulary content contained therein.

It should be noted that the speech recognition technology is based on a front-edge algorithm in deep learning, performs customized training on a recognition model according to corpora of business trip business, and converts audio streams or audio files sent by different audio sources not exceeding one minute into texts through API (application programming interface) calling. The speech recognition technology adopted in the intelligent speech assistant can dynamically detect whether boundaries exist on speech or not by using a model, so that the boundaries of different words are distinguished, and the relation and the basic semantics between words and sentences are fully reflected. The model firstly adopts a method based on a decision tree to carry out clustering analysis on the three-phonon model, then each clustered model is independently trained, and simultaneously, the training data and the algorithm parameters can be shared by each model. Certain phonetic knowledge base is input in the process of splitting the algorithm up and down, on one hand, the knowledge base can be enriched by outputting unused three-tone models, on the other hand, the operation efficiency can be improved in a doubling mode, and the speech recognition speed is further improved. At present, the recognition rate of the intelligent voice assistant to Mandarin is far over 90 percent, and the intelligent voice assistant is in the leading level in the industry.

S602: and identifying the text information through a natural language processing technology, and extracting the key entity information from the text information.

Natural Language Processing (NLP): also called Natural Language Understanding (NLU), also called Computational Linguistics (Computational Linguistics), is one of the branches of linguistic information processing on the one hand and one of the core topics of Artificial Intelligence (AI) on the other hand.

S603: and semantically reasoning the voice information through a multi-turn dialogue technology and a semantic reasoning technology, and determining the user intention corresponding to the user.

It should be noted that Semantic reasoning technology (Semantic Inference, SI): refers to reasoning that is done in terms of semantic relationships between terms. There are three main categories: 1) reasoning synonymy relation; 2) reasoning hyponymy relation; 3) the antisense relationship is inferred.

It should be further noted that the semantic reasoning technology is based on a natural language processing technology, and performs semantic reasoning on the sentence converted into the text, so as to accurately recognize the will of the user, and thus, the operation that the user wants to perform is positioned. For example: the intelligent voice assistant can accurately position the corresponding function as long as the user speaks a sentence with the keyword, and a complicated search input process is omitted. In order to further improve the accuracy of semantic recognition, the project adopts an optimized convolutional neural network model, and a cycle layer is added on the basis of a commonly used convolutional neural network model, and the structure of the model comprises the following steps: input layer-hidden layer-output layer-cyclic layer. The added circulating neural network is different from the traditional neural network in that the previous output result is brought to the next hidden layer each time for training. The analysis logic is shown in fig. 7, and the test result shows that the text feature result extracted by the loop layer is further optimized through the convolution layer, and the classification performance of the text is further improved compared with that of the traditional convolution neural network. The convolutional neural network algorithms currently used for solving the problem of the cyclic convolutional neural network question-answer mainly include two types, one is a Long Short-term memory network (LSTM) algorithm, and the other is a Gated cyclic Unit (Gated Recurrent Unit) algorithm, as shown in fig. 8. In the embodiment of the application, the question-answer matching is realized by using a GRU algorithm, the GRU is a variant with a good effect of the LSTM network, the structure of the GRU is simpler than that of the LSTM network, and much time can be saved under the condition that a training data set is larger.

Multi-round Conversation technology (MCT): also called context-based dialogue, single round and multi-round application are the same, and a single round can be solved by one sentence, and a plurality of rounds can be realized by repeating the above steps for several times. Namely: the user's needs are complex and variable, and may need to be set out in multiple rounds, or the user may modify and refine his or her needs during the dialog process, which requires the system to be able to recognize and track the user's entire dialog intention. In addition, the machine may also help the user find a satisfactory result by asking, clarifying or confirming when the user stated a need not be clear enough. Compared with chatting, task-oriented dialog is very clear in purpose, and the key is to obtain the tracking of intention and constraint conditions (slot positions) and dialog states. The intelligent voice assistant generates a single, definite and specific answer or a plurality of answers with high relevance but uncertain according to the content input by the user and the knowledge matching condition, and the answers need to be selected by the user. If the user's needs are met, the session may be terminated; if the user's needs are not met, a new session may be run and the above process will be repeated. The project uses GRU algorithm to realize multiple rounds of question-answer matching.

S103: skipping to a corresponding product order according to the user intention, wherein the product order comprises: booking orders, polling orders, and business return request orders.

S104: and filling the key entity information contained in the voice information into a text box corresponding to the product order.

In an embodiment of the present application, the skipping to the corresponding product order according to the user intention includes:

when the user intention is recognized as a voice new application form, skipping to the voice new application form according to the user intention; when the user intention is identified as the application form associated with the reason for public line, jumping to the application form associated with the reason for public line according to the user intention; when the user intention is identified as specific service subscription, jumping to the specific service subscription application form according to the user intention; when the user intention is identified as an unassociated application form, jumping to the unassociated application form according to the user intention; when the user intention is recognized as the inquiry-only application form, jumping to the inquiry-only application form according to the user intention; and when the user intention is recognized as the private reason outgoing application form, jumping to the private reason outgoing application form according to the user intention.

Specifically, as shown in fig. 9, after the user performs voice recognition, when "business trip and application form" is recognized, it is determined that a new application form is created, and if the recognition is successful, it is prompted that "business trip application form is generated for you, and the information is not obtained to ask for manual filling", and the application form is clicked to enter the application form filling interface; and (4) identifying failure prompt: i did not hear clearly, trying to say "I go to Shanghai and go from Beijing tomorrow" or "I book an air ticket to Shanghai before Beijing tomorrow". The subscription of the intelligent voice service to a particular service is accomplished through the process illustrated in fig. 10-13.

Specifically, as shown in fig. 14, the implementation diagram interface of the application form for associating with the public line is described in function: 1) after the user selects the line for public, the related application forms are screened out according to time, place and products. The small assistant prompts that the following application form has been queried for you, speaking the number or clicking on the card to associate the application form. 2) The application forms are displayed in a card form, a serial number is given to each application form, and the subsequent cards are checked in a sliding mode. 3) The user can select by speaking the serial number of the application form or clicking the corresponding application form. 4) Clicking or speaking "query only" jumps to the cause public query interface.

Specifically, the implementation diagram interfaces of the specific service subscription request form are shown in fig. 15 to 17, and the functions are described as follows: 1) and after the user successfully associates the application form, the user enters into the reservation of the public products. 2) The query interface is jumped to prompt "query in progress, please wait … …". After the verification is finished, the query list is automatically jumped, and manual click search is not needed. 3) The list interface click back may return to the query interface. The click return of the query interface can return a voice chat interface, and past records are not reserved.

Specifically, the implementation illustration interface of the unassociated application form is shown in fig. 18, and the functions are described as follows: 1) after the user selects the public trip, if the matched application form is not found, the user is fed back 'please select only to inquire or input the voice again if the matched application form is not found at present'. 2) The user may manually click "query only" or voice reply "query only". The voice input can be carried out again, and the voice content is not covered.

Specifically, the implementation illustration interface of the query-only application form is shown in fig. 19, and the functions are described as follows: 1) after the user selects or only queries by voice input, the query of the products due to public reasons is carried out according to the voice content of the user. The query interface is jumped to prompt "query in progress, please wait … …". After the verification is finished, the query list is automatically jumped, and manual click search is not needed. 2) The list interface click back may return to the query interface. The click return of the query interface can return a voice chat interface, and past records are not reserved.

Specifically, as shown in fig. 20 to 21, the implementation diagram interface of the private application form describes the functions: 1) and after the user selects private trip, the private product query is carried out according to the voice content of the user. The query interface is jumped to prompt "query in progress, please wait … …". After the verification is finished, the query list is automatically jumped, and manual click search is not needed. 2) The list interface click back may return to the query interface. The click return of the query interface can return a voice chat interface, and past records are not reserved.

The embodiment of the application provides a method for intelligently creating an application form, which is characterized in that an intelligent voice input function is added on the basis of common business software, and voice information (at least comprising one of time, place and intention) input by a user is acquired; performing character recognition and semantic reasoning on the voice information, and determining key entity information contained in the voice information and a user intention corresponding to the user; skipping to corresponding product orders (reservation orders, inquiry orders and business trip request orders) according to the user intention; and filling the key entity information contained in the voice information into a text box corresponding to the product order. The embodiment of the application can realize the intellectualization of business travel software, realizes the butt joint of the business travel platform and the intelligent voice platform, achieves the purposes of systematization and intellectualization of relevant affairs in business travel conveniently, accurately and efficiently, liberates both hands of users, improves the efficiency of establishing an application form, and improves user experience.

Referring to fig. 22, based on the method for intelligently creating a request form disclosed in the foregoing embodiment, this embodiment correspondingly discloses an apparatus for intelligently creating a request form, where the apparatus includes:

a first processing unit 221, configured to acquire voice information input by a user, where the voice information at least includes one of time, place, and intention;

the second processing unit 222 is configured to perform character recognition and semantic reasoning on the voice information, and determine key entity information included in the voice information and a user intention corresponding to the user;

a third processing unit 223, configured to jump to a corresponding product order according to the user intention, where the product order includes: booking orders, inquiring orders and going-on-business application orders;

the fourth processing unit 334 is configured to fill the key entity information included in the voice information into a text box corresponding to the product order.

Further, the second processing unit 222 is specifically configured to:

Further, the third processing unit 223 is specifically configured to:

The device for intelligently creating the application form comprises a processor and a memory, wherein the first processing unit, the second processing unit, the third processing unit, the fourth processing unit and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.

The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. The kernel can be set to be one or more than one, and the purposes of liberating the hands of the user, improving the efficiency of creating the application form and improving the user experience are achieved by adjusting the kernel parameters.

An embodiment of the present application provides a storage medium on which a program is stored, which, when executed by a processor, implements the method for intelligently creating a request form.

The embodiment of the application provides a processor, wherein the processor is used for running a program, and the program runs to execute the method for intelligently creating the application form.

An electronic device 230 includes at least one processor 2301, and at least one memory 2302, a bus 2303 connected with the processor; the processor 2301 and the memory 2302 are communicated with each other through the bus 2303; the processor 2301 is configured to call the program instructions in the memory 2302 to execute the method for intelligently creating a request form as described above.

The electronic device herein may be a server, a PC, a PAD, a mobile phone, etc.

The present application further provides a computer program product adapted to perform a program for initializing the following method steps when executed on a data processing device:

The present application is described in terms of flowcharts and/or block diagrams of methods, apparatus (systems), computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may 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, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a device includes one or more processors (CPUs), memory, and a bus. The device may also include input/output interfaces, network interfaces, and the like.

The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip. The memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include transitory computer readable media (transmyedia) such as modulated data signals and carrier waves.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for intelligently creating a request form, comprising:

2. The method according to claim 1, wherein said performing text recognition and semantic reasoning on the voice message to determine key entity information contained in the voice message and the corresponding intention of the user comprises:

3. The method of claim 1, wherein said jumping to a corresponding product order according to said user intent comprises:

4. An apparatus for intelligently creating a request form, comprising:

5. The apparatus according to claim 4, wherein the second processing unit is specifically configured to:

6. The apparatus according to claim 4, wherein the third processing unit is specifically configured to:

7. A storage medium comprising a stored program, wherein the program, when executed, controls an apparatus on which the storage medium resides to perform the method of intelligently creating an application form of any one of claims 1 to 3.

8. An electronic device comprising at least one processor, and at least one memory, bus connected to the processor; the processor and the memory complete mutual communication through the bus; the processor is configured to invoke program instructions in the memory to perform the method of intelligently creating a claim form of any of claims 1 to 3.