TWI674530B - Method and system for operating a virtual assistant - Google Patents

Abstract

A virtual assistant method includes receiving audio input and identifying audio to form corpus data; using natural language processing models to analyze corpus data to generate linguistic feature information corresponding to the corpus data; and performing linguistic feature information based on functional context information Functional situation analysis to confirm the operation corresponding to one of these intents; find out the operation template from the overall database, and enter the vocabulary corresponding to the operation into the operation template to form the operation corresponding instruction; for the enterprise database or enterprise The resource system executes an instruction corresponding to the operation and generates a result corresponding to the operation; and outputs a result corresponding to the operation.

Description

Method and system for operating virtual assistant

This case relates to a method and system for speech recognition and processing, and in particular to a method and system for operating a virtual assistant.

Enterprise resource planning system (Enterprise Resource Planning, ERP), referred to as ERP system, refers to a management platform that provides decision-making for the enterprise decision-making layer based on information technology. Its main purpose is to uniformly manage the flow of people, logistics, information, and funds in order to maximize the use of corporate resources. The ERP system contains three major functions, such as production control, logistics management, and financial management. Therefore, the scale of the ERP system is very large.

In modern life, virtual assistants (or virtual assistants) can help users communicate with electronic products directly in verbal and / or textual natural language, providing users with a more convenient and fast communication mode. The use of virtual assistants in ERP systems can help users quickly communicate with the large ERP system, which can save users the time spent in using the ERP system, and the complexity of the ERP system may make it difficult for users. Query issues.

The main purpose of the present invention is to provide a method and a system for operating a virtual assistant, which mainly improve the problem that the previous ERP system is huge and complicated, which makes it difficult for the user to use. Using the virtual assistant can further assist the user to use the ERP system in a more convenient way. To achieve the effect of saving time and reducing the difficulty of using ERP systems.

In order to achieve the above purpose, the first aspect of the present case is to provide a method for operating a virtual assistant. The method includes the following steps: receiving audio input and identifying the audio to form a corpus data; using a natural language processing model to analyze the corpus data, and Generate linguistic feature information corresponding to the corpus data, where the linguistic feature information includes multiple intents, the probability corresponding to those intents, and multiple vocabularies; perform a functional context analysis of the linguistic feature information based on the functional context information to confirm which of these intents One of the corresponding operations; find the template of the operation from the overall database, and enter the vocabulary of the operation into the template of the operation to form the instruction corresponding to the operation; execute the instruction corresponding to the operation and generate the operation for the enterprise database or enterprise resource system A corresponding result; and a result corresponding to the output operation; wherein the operation includes one of a query data operation and a command execution operation.

The second aspect of the present case is to provide a system for operating a virtual assistant, which is connected to an enterprise database and an enterprise resource system, respectively, and includes a processor, a storage device, and an input / output device. The storage device is electrically connected to the processor, and is used for storing a general database, an application knowledge database, a domain knowledge database, and a historical database. The input / output device is electrically connected to the processor to provide an interface for inputting audio. The processor includes a speech recognition module, a corpus analysis module, a situation analysis module, an instruction generation module, and an operation execution module. The speech recognition module is used to recognize audio to form corpus data. The corpus analysis module and the speech recognition module are electrically connected to analyze the corpus data using a natural language processing model to generate linguistic feature information corresponding to the corpus data, where the linguistic feature information includes a plurality of intents, the intents Corresponding probability and plural words. The situation analysis module and the corpus analysis module are electrically connected to perform a function situation analysis on the linguistic feature information according to the function situation information to confirm an operation corresponding to one of the intentions. The instruction generation module is electrically connected with the situation analysis module, and is used to find the operation template from the overall database, and input the vocabulary corresponding to the operation to the operation template to form the operation corresponding instruction. The operation execution module and the instruction generation module are electrically connected to execute an operation corresponding instruction and generate an operation corresponding result for an enterprise database or an enterprise resource system, and output the operation corresponding result to an input / output device; wherein, the The operation includes one of a query data operation and an execution instruction operation.

The method and system for operating a virtual assistant of the present invention mainly improve the problem that the previous ERP system is huge and complicated, which makes it difficult for the user to use. Combining the virtual assistant can help the user to use the ERP system in a more convenient way, thereby saving time. And the effect of reducing the difficulty of using the ERP system.

100‧‧‧ system for operating virtual assistants

110‧‧‧ processor

130‧‧‧Storage device

150‧‧‧ input / output device

131‧‧‧Overall Database

132‧‧‧Application Knowledge Database

133‧‧‧ Domain Knowledge Database

134‧‧‧History database

111‧‧‧Speech recognition module

112‧‧‧ Corpus Analysis Module

113‧‧‧Scenario Analysis Module

114‧‧‧Command generation module

115‧‧‧operation execution module

121‧‧‧ Training Module

122‧‧‧Template Creation Module

123‧‧‧ Semantic model building module

124‧‧‧vocabulary model building module

125‧‧‧Scenario Training Module

300‧‧‧ Method for operating virtual assistant

710‧‧‧users

720‧‧‧Enterprise Resource System

730‧‧‧Enterprise Database

S310 ~ S350, S410 ~ S480, S231 ~ S322, S231 ~ S322, S331 ~ S332‧‧‧Steps

In order to make the above and other objects, features, advantages, and embodiments of the present invention more comprehensible, the description of the drawings is as follows: FIG. 1 is a schematic diagram of a system for operating a virtual assistant according to some embodiments of the present case; FIG. 2 is a schematic diagram of a processor according to some embodiments of the present case; and FIG. 3 is a view of some processors according to the present case. A flowchart of a method for operating a virtual assistant as shown in the embodiments; FIG. 4 is a flowchart of a training data model according to some embodiments of the present case; and FIG. 5 is a diagram according to some embodiments of the present case. The flowchart of step S320; FIG. 6 is a flowchart of step S330 according to some embodiments of the present case; and FIG. 7 is a diagram of a user and operating a virtual assistant according to some embodiments of the present case Schematic representation of system interaction.

The following disclosure provides many different embodiments or illustrations to implement different features of the invention. The elements and configurations in the particular example are used in the following discussion to simplify the present disclosure. Any illustrations discussed are for illustrative purposes only and do not in any way limit the scope and meaning of the invention or its illustrations. In addition, the present disclosure may repeatedly refer to numerical symbols and / or letters in different examples, and these repetitions are for simplification and explanation, and do not themselves specify the relationship between different embodiments and / or configurations in the following discussion.

Terms used throughout the specification and patent application (Terms), unless otherwise specified, usually have the ordinary meaning of each term used in this field, in the content disclosed here, and in special content. Certain terms used to describe this disclosure are discussed below or elsewhere in this specification to provide additional guidance to those skilled in the art on the description of this disclosure.

As used herein, "coupling" or "connection" can mean that two or more components make direct physical or electrical contact with each other, or indirectly make physical or electrical contact with each other, and "coupling" or " "Connected" may also mean that two or more elements operate or act on each other.

In this article, the terms first, second, third, etc. are used to describe various elements, components, regions, layers, and / or blocks that are understandable. However, these elements, components, regions, layers and / or blocks should not be limited by these terms. These terms are limited to identifying single elements, components, regions, layers, and / or blocks. Therefore, a first element, component, region, layer, and / or block in the following may also be referred to as a second element, component, region, layer, and / or block without departing from the intention of the present invention. As used herein, the term "and / or" includes any combination of one or more of the associated listed items. The "and / or" mentioned in this document refers to any, all or any combination of at least one of the listed elements.

See Figure 1. FIG. 1 is a schematic diagram of a system 100 for operating a virtual assistant according to some embodiments of the present invention. As shown in FIG. 1, the system 100 for operating a virtual assistant includes a processor 110, a storage device 130, and an input / output device 150. The storage device 130 is configured to store a general database 131, an application knowledge database 132, a domain knowledge database 133, and a history database 134, and store the general database 131 and the application knowledge database. 132. The domain knowledge database 133 and the history database 134 are electrically connected to the processor 110. The input / output device 150 is electrically connected to the processor 110 for providing an interface for inputting audio. In one embodiment, the input / output device 150 may be a keyboard, a touch screen, a microphone, a speaker, or other suitable input / output devices. The user can input audio through the interface provided by the input / output device or obtain the result output by the system 100 operating the virtual assistant.

In various embodiments of the present invention, the processor 110 may be implemented as an integrated circuit such as a microcontroller, a microprocessor, a digital signal processor, and an application specific integrated circuit. integrated circuit (ASIC), logic circuit, or other similar components or a combination of the above. The storage device 150 may be implemented as a memory, a hard disk, a flash drive, a memory card, and the like.

Please refer to FIG. 2. FIG. 2 is a schematic diagram of a processor 110 according to some embodiments of the present invention. The processor 110 includes a speech recognition module 111, a corpus analysis module 112, a situation analysis module 113, an instruction generation module 114, an operation execution module 115, a training module 121, a template creation module 122, and a semantic model creation module. Group 123, vocabulary model building module 124, and situation training module 125. The corpus analysis module 112 is electrically connected to the speech recognition module 111, the context analysis module 113 is electrically connected to the corpus analysis module 112, the instruction generation module 114 is electrically connected to the context analysis module 113, and the operation execution module The group 115 is electrically connected to the command generating module 114. The training module 121 is electrically connected to the corpus analysis module 112. The template creation module 122 is electrically connected to the training module 121. The semantic model creation module 123 and the vocabulary model creation module 124 and the template creation module 122 are electrically connected. Connected, the situation training module 125 and the situation analysis module 11 are electrically connected.

Please refer to Figures 1 to 3 together. FIG. 3 is a flowchart of a method 300 for operating a virtual assistant according to some embodiments of the present invention. As shown in FIG. 3, the method 300 for operating a virtual assistant includes the following steps: Step S310: receiving audio input and identifying the audio to form corpus data; step S320: analyzing the corpus data using a natural language processing model to generate and corpus Step S330: Perform a functional situation analysis on the linguistic feature information according to the functional situation information to confirm the operation corresponding to one of the intents; Step S340: find the operation template from the overall database, and Input the vocabulary corresponding to the operation into the operation template to form the operation corresponding instruction; step S350: execute the operation corresponding instruction and generate the result corresponding to the operation for the enterprise database or the enterprise resource system; and step S360: output the result corresponding to the operation.

In step S310, audio input is received and audio is recognized to form corpus data. In one embodiment, the audio received through the input / output device 150 can be recognized by the speech recognition module 111 of the processor 110 to convert the user's natural language into corpus data. In another embodiment, the voice recognition may also send audio to the cloud voice recognition system through the Internet, and after the audio is recognized by the cloud voice recognition system, the recognition result is then transmitted. As corpus data, for example, the cloud speech recognition system can be implemented as Google's speech recognition system.

Before executing step S320, a common vocabulary model and a common semantic model need to be established. Therefore, please refer to FIG. 4, which is a flowchart of a training data model according to some embodiments of the present invention. As shown in Figure 4, the training data model stage includes the following steps: Step S410: Generate a system domain vocabulary based on the application knowledge database and domain knowledge database; Step S420: The system domain vocabulary and a plurality of service application parameters are formed as the key Entity set; step S430: classify a plurality of training corpora into one of query data operation and execute instruction operation; step S440: distinguish the training corpus corresponding to query data operation according to the category in the enterprise database The plurality of query data operation intentions, and the intention to distinguish the training corpus corresponding to the execution of the instruction operation according to the service behavior provided by the enterprise resource system to form a plurality of execution instruction operation intentions; step S450: establishing a template of the query data operation intention, and execution The template of the instruction operation intention; Step S460: Establish an overall database according to the key entity set, the query data operation intention template, and the template for executing the instruction operation intention; Step S470: identify the system domain words in the key entity set appear in the training corpus Plural first Rate, and system areas identified by the lexical analysis training corpus of a plurality of sentence structure, and system areas Plural correlations between vocabularies, and establishing a common vocabulary model according to the first probability and correlation; and step S480: analyzing the query data operation intention and the execution instruction operation intention of the plural second probability of the system domain vocabulary, and Establish a common semantic model based on the sentence structure and the second probability.

In steps S410 and S420, a system domain vocabulary set is generated according to the application knowledge database 132 and the domain knowledge database 133, and then the system domain vocabulary set and a plurality of service application parameters are used to form a key entity set. The key entity set includes a plurality of System domain vocabulary. For example, the key entity set contains information such as enterprise domain vocabulary and service application parameters of the enterprise system. The corporate vocabulary refers to the vocabulary that companies in different fields may need. For example, the vocabulary used in the medical industry and the vocabulary used in the transportation industry must be different. Therefore, the vocabulary in the enterprise field will be based on each use of the ERP system. Enterprises vary. The service application parameters of the enterprise system are the parameters corresponding to various services provided by the enterprise system. For example, the leave function in the enterprise system may require information such as leave time and leave, and the system domain vocabulary in the key entity collection needs Contains information on leave, annual leave, sick leave, and business leave.

In detail, the key entity collection also includes the data field names that will be available when accessing the data, the service name provided by the enterprise system to the user, the parameter values of the restriction conditions set by the user during the query, and the service application parameter values As well as operation functions of the enterprise system, the operation functions of the enterprise system may be operation functions such as leave of absence, overtime application, business application, and reimbursement. The above information may also have corresponding aliases, which also need to be entered in the training database. Incoming, for example: shipping orders may have different names such as shipping details or sales orders for manufacturers in specific fields.

In step S430, the plurality of training corpora are classified into one of a query data operation and a command execution operation. The training corpus can be natural language data such as the user's instructions or questions that may be asked. After the key entity set is established, the training corpus will be classified according to the intention. In one embodiment, the user's intention It is divided into query data operation and execution instruction operation, but the user's intention can be classified more finely, and the present invention is not limited to this. For example, if the user says to the virtual assistant: "Please help me find the shipping order of XX company", it will be classified as query data operation in the intent classification of the present invention, and the virtual assistant will go to the enterprise database to help Check the shipping order of company XX. If the user says to the virtual assistant: "Please ask me for a business trip on January 30." In the intent classification of the present invention, it will be classified as performing an instruction operation, and the virtual assistant will enter the enterprise resource system to help the user ask for leave.

In step S440, the intention of distinguishing the training corpus corresponding to the query data operation according to the category in the enterprise database is to form a plurality of query data operation intentions, and to distinguish the corresponding execution instruction operations according to the service behavior provided by the enterprise resource system. The intent of the training corpus forms a plurality of intents to execute the instruction operation. In one embodiment, the operation of querying data is distinguished according to the enterprise database in each different domain. For example, the database stored in the enterprise database of the medical industry must be different from the enterprise database of the transportation industry, so the user needs of the two are not necessarily the same. For example, users in the medical industry may have different intents for querying medical records and inquiring vacancies in the ward, and users in the transportation industry may have queries Cargo records, querying the status of parcel delivery, etc. are the different intentions of querying data operations. Of course, according to the service behavior provided by the enterprise resource system in each different field, the intention is to distinguish the execution of the instruction operation. As mentioned above, the services provided by the enterprise resource system in the medical industry will of course be different from the transportation industry. Each different field The query data operation or service behavior operation provided by the company may not be universal, so it is also necessary to distinguish the intent of the service provided by the enterprise in each different field. For example, users in the medical industry may have registered services. The provision of services such as hospitalization and ordering healthy meals are different intentions of service behavior operations. For users in the transportation industry, there may be different intentions of service behavior operations to provide services of automatically classifying goods and arranging the order of shipment of goods. .

In steps S450 and S460, a template for querying data operation intention and a template for executing instruction operation is established, and an overall database 131 is established according to a set of key entities, a template for querying data operation intention and a template for executing instruction operation. For example, after distinguishing the query data operation intention and execution instruction operation intention that a user's virtual assistant operating in a certain field company has, the corresponding template can be generated for each intent. According to the above example, medical treatment There will be 4 templates corresponding to querying medical records, querying vacancies in the ward, providing registered services, and providing services for ordering healthy meals in hospitals. The transportation industry will have corresponding querying shipping records, querying parcel delivery status, and providing automatic sorting of goods. Services, four services for arranging the order in which goods are shipped, and then an overall database 131 will be created based on these templates and a collection of key entities.

In step S470, identify the first multiple occurrences of the system domain vocabulary in the key entity set in the training corpus, and identify the System sentence lexical analysis training corpus of multiple sentence structure, and the system domain vocabulary of multiple correlations between each other, and based on the first probability and relevance to establish a common vocabulary model. In one embodiment, two algorithms, n-GRAM and Context-free grammar (CFG), are used to calculate the probability of each system domain vocabulary appearing in the training corpus. The domain vocabulary analysis training corpus's sentence structure and system domain vocabulary are related to each other to establish a common vocabulary model. For example, if the training corpus contains "I want to query the quotation of XX company" and "I want to query the XX company's shipping order", and "XX company", "quotation" and "shipment order" are all Is a vocabulary in the system field, but in the above example, because "XX company" may appear on average for each query data operation intent, the probability of "XX company" is almost the same in each query data operation intention. The "quotations" and "shipments" only appear in large numbers in the training corpus intended to query some specific data, and will not appear in the training corpus intended to query other data, so the "quotation" And the probability of "shipment order" will be particularly high in the corresponding intent, and will be lower in other intents.

In step S480, a plurality of second probabilities of vocabulary of the system domain appear in the query data operation intention and the execution instruction operation intention, and a common semantic model is established according to the sentence structure and the second probability. In an embodiment, a Hidden Markov Model (HMM) algorithm is used to calculate the probability of a system vocabulary appearing in query data operation intentions and executing instruction operation intentions to establish a common semantic model. For example, During the training data model phase, many training corpora are input. Hidden Markov The husband model algorithm must calculate the probability of the system domain vocabulary appearing at different intents. In combination with the above example, if the training corpus contains "I want to query the shipping order of XX company", according to the n-gram syntax and context-free grammar, it can be found that "XX company" and "shipping order" are both system vocabulary. The hidden Markov model algorithm can further determine the "shipment order" and the query shipment according to the relationship between all the identified system domain vocabularies in the query data operation intention, the probability of executing the instruction operation intention, and the system domain vocabulary. The intent of the data is related, and combined with the system field vocabulary of "XX company", users can automatically query the company's shipping related data in the enterprise database.

After the common vocabulary model and the common semantic model are established, step S320 is performed, and the corpus data is analyzed by using a natural language processing model to generate linguistic feature information corresponding to the corpus data. The linguistic feature information includes a plurality of intents and intent correspondence Probability and plural words. For the detailed flow of step S320, please refer to FIG. 5. FIG. 5 is a flowchart of step S320 according to some embodiments of the present invention. As shown in FIG. 5, step S320 includes the following steps: step S321: use a common vocabulary model to identify whether the corpus data has vocabulary in the system domain that matches the key entity set, set the recognition result to the vocabulary in the language feature information, and Analyze the occurrence probability of vocabulary in the linguistic feature information; step S322: analyze the sentence structure of the corpus data based on the vocabulary in the feature information; and step S323: use the common semantic model to The probability of the occurrence of vocabulary and the sentence structure of the corpus data identify the intention of the corpus data and the probability of the corresponding intent.

In step S321 and step S322, the common vocabulary model is used to identify whether the corpus data has vocabulary in the system domain in the key entity set, set the recognition result to the vocabulary in the language feature information, and analyze the occurrence of the vocabulary in the language feature information Probability, and then analyze the sentence structure of the corpus data based on the vocabulary in the feature information. For example, the corpus data input by the user is used to identify the vocabulary in the corpus data that contains the vocabulary of the system domain, and then the sentence structure of the corpus data is further determined. For example, if the user says to the virtual assistant: "I want to check the shipping order of XX company last month", the common vocabulary model can identify "XX company", "last month" and "shipping order" "And other words that fit the vocabulary of the system domain.

In step S323, the common semantic model is used to identify the intention of the corpus data and the probability corresponding to the intent according to the probability of vocabulary appearance in the feature information and the sentence structure of the corpus data. According to the example above, after identifying the words "XX company", "last month", and "shipment order", we will further judge the probability of these words in all intents. All intents referred to here include all query data operation intentions and the probability of performing instruction operation intentions.

In step S330, a functional context analysis is performed on the linguistic feature information according to the functional context information to confirm an operation corresponding to one of the intentions. Before performing functional situation analysis, a functional situation model needs to be established first. When performing a functional situation analysis, the functional situation model first converts the features in the historical database 134 into feature vectors, and then uses machine learning algorithms to convert the historical database The data in 134 are classified and calculated according to different scenarios. The strong and weak relationship between the feature vector and each situation, then a functional situation model is generated. Machine learning algorithms suitable for establishing the above functional scenarios include: Support Vector Machines (SVMs) commonly used in traditional machine learning, and Convolutional Neural Networks (CNN) related to deep learning. , Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) algorithms. For the detailed flow of step S330, please refer to FIG. 6, which is a flowchart of step S330 according to some embodiments of the present invention. As shown in FIG. 6, step S330 includes the following steps: step S331: using corpus data and functional context information to compare with the functional context model and generating a functional context identification result; and step S332: judging the result based on the functional context identification result One of these intentions corresponds to one of querying data operations and executing instruction operations.

In step S331, the corpus data and the functional context information are compared with the functional context model, and a functional context identification result is generated. Functional context information includes the user's identity, the user's position, the user's department, time, and location. Part of the information of the functional context information can be sensed by the input / output device 150, for example, it can detect the current status of the user (for example, whether or not he is back on a business trip). According to the probability and vocabulary of all the intents obtained after identifying the user's corpus data, combined with the functional context information, it can be further confirmed that the user's corpus data is consistent with the data in the training data model.

In step S332, it is determined that one of the intentions corresponds to one of a query data operation and an execution instruction operation according to the functional context recognition result. Because there will be multiple query data operation intentions and multiple instruction operation operation intentions in the training data model, and after the calculation of the common semantic model described above, the probability corresponding to each intent will be generated. Intents with lower probability values can be Use threshold filtering to get the most likely intent and confirm the corresponding operation. As can be seen from the foregoing example, when the words "XX company", "last month", and "shipment order" are identified, these words will be judged with the functional context information to find the most suitable query data operation intention or execute the command operation The intention is that after the above operation, the user will be judged that the user said to the virtual assistant: "I want to check the shipping order of XX company last month". Most likely, you will want to check the shipping order of XX company, so you can Corresponding to what the user wants to perform is a query data operation. The judgement of the functional situation is needed because the user's position, department, operation time, operation place and other information have different needs. For example, purchasers and financial staff will look at [vendor monthly statistics table] However, it is possible that the statistical goals of the [vendor monthly statistics table] of the two are not the same: one is to count the purchase status of the manufacturer, and the other is to count the payment status of the company to the manufacturer. However, when talking with the virtual assistant, the user may not necessarily specify exactly what the [vendor monthly statistics table] is needed. It may only say, "I need the monthly monthly statistics table of the manufacturer last month." It is even more necessary to make a more accurate judgment with the user's functional situation information.

In step S340, a template of the operation is found from the overall database 131, and a vocabulary corresponding to the operation is input into the template of the operation to form an instruction corresponding to the operation. Following the example above, find out what the user wants to run is a query After the data operation, the virtual assistant will find the previously created query data operation template from the overall database 131, and then enter the words "XX company", "last month" and "shipment order" into the template to The instruction corresponding to the operation is formed. The instruction here may be a SQL program instruction, of course, it may also be another type of program instruction.

In steps S350 and S360, an operation corresponding instruction is executed and an operation corresponding result is generated for the enterprise database or an enterprise resource system, and an operation corresponding result is output. Continuing the above example, when the corresponding program instructions for querying data operations are set, the virtual assistant will enter the enterprise database to query the data the user wants, which is "the shipping order of XX company last month", and then the virtual assistant The results of "XX company's last month's shipping order" will be returned to the user via the input / output device 150, which can be displayed to the user for viewing, or the report can be printed directly to the user via the printer and submitted to the user Check it out.

Please continue to refer to FIG. 7. FIG. 7 is a schematic diagram illustrating interaction between a user and a system for operating a virtual assistant according to some embodiments of the present invention. As shown in FIG. 7, the user 710 interacts with the system 100 operating the virtual assistant. The user 710 can communicate with the virtual assistant using natural language. The system 100 operating the virtual assistant divides the user's request into data query operations. And execute the instruction operation. If it is a data query operation, the system 100 that operates the virtual assistant will check the data in the enterprise database 730 and feed it back to the user. If the system 100 executes the instruction operation, the virtual assistant system 100 will execute the enterprise resource system 720 Relevant services are then fed back to the user, and the system 100 operating the virtual assistant will also actively notify background events that may be hidden The user, for example, if the user has to travel expenses to be written off after returning from a business trip, the system 100 operating the virtual assistant will also actively notify the user to write off the documents.

According to the implementation of the above case, it is mainly to improve the problem that the previous ERP system is huge and complicated, which makes it difficult for the user to use. In combination with the virtual assistant, it can help the user to use the ERP system in a more convenient way, and the operation that the user wants to perform. Classification, combined with the user's functional context information can more accurately determine the user's intention, achieve the effect of saving the user's operation time and reducing the difficulty of using the ERP system.

In addition, the above-mentioned illustration includes sequential exemplary steps, but the steps need not be performed in the order shown. It is within the scope of this disclosure to perform these steps in different orders. Within the spirit and scope of the embodiments of the present disclosure, these steps may be added, replaced, changed, and / or omitted as appropriate.

Although this case has been disclosed as above in the form of implementation, it is not intended to limit the case. Any person skilled in this art can make various modifications and retouches without departing from the spirit and scope of the case. Therefore, the scope of protection of this case should be considered after The attached application patent shall prevail.

Claims (8)

A method for operating a virtual assistant includes: receiving an audio input and identifying the audio to form a corpus data; analyzing the corpus data using a natural language processing model to generate a language feature information corresponding to the corpus data, The linguistic feature information includes a plurality of intents, a probability corresponding to the intents, and a plurality of vocabularies, and further includes: using a common vocabulary model to identify whether the corpus data has a plurality of system domain vocabularies that conform to the key entity set. Set the recognition result to the words, and analyze the probability of the words appearing; and analyze the sentence structure of the corpus data according to the words; use a common semantic model to predict the occurrence of the words and the corpus data according to a common semantic model The sentence structure of the corpus identifies the intents of the corpus and the probability of the intents; perform a functional context analysis of the intents of the corpus according to a functional context information to confirm that one of the intents corresponds Of an operation; find a template for that operation from a general database, and compare the words for that operation Input a template of the operation to form an instruction corresponding to the operation; execute an instruction corresponding to the operation against an enterprise database or an enterprise resource system and generate a result corresponding to the operation; and output a result corresponding to the operation; wherein the operation includes One of a data query operation and an instruction execution operation. The method for operating a virtual assistant according to claim 1, further comprising: generating a system domain vocabulary set based on an application knowledge database and a domain knowledge database; the system domain vocabulary set and a plurality of service application parameters form a key Entity set, the key entity set contains the vocabulary of the system domains; classifying a plurality of training corpora into one of the query data operation and the execution instruction operation; distinguishing corresponding query data operations according to categories in the enterprise database The intentions of the training corpus form a plurality of query data operation intentions, and the intention of the training corpus that should perform the instruction operation is formed according to the service behavior provided by the enterprise resource system to form a plurality of execution instruction operation intentions; establishing the Templates of query data operation intentions, and templates of execution command operation intentions; establishing the overall database based on the set of key entities, query data operation intention templates, and execution command operation intention templates; identifying the key The system domain vocabulary in the entity collection is in these The plurality of first chances appearing in the training corpus, and the plurality of sentence structures of the training corpus are analyzed based on the identified system domain vocabularies, and the plurality of correlations between the system domain vocabularies with each other , And establish the common vocabulary model according to the first probabilities and the correlations; and analyze the plurality of second probabilities that the system domain words appear in the query data operation intentions and the execution instruction operation intentions, and according to The The sentence structure and the second chances establish the common semantic model. The method for operating a virtual assistant according to claim 1, further comprising: using a classifier to classify the data in a historical database into relationship strengths to generate a functional situation model. The method for operating a virtual assistant according to claim 3, wherein the functional situation analysis further comprises: using the corpus data and the functional situation information to compare with the functional situation model, and generating a functional situation identification result; and according to The functional situation identification result judges that one of the intentions should correspond to one of the query data operation and the execution instruction operation. A system for operating a virtual assistant, which is respectively connected to an enterprise database and an enterprise resource system, and includes: a processor; a storage device electrically connected to the processor for storing an overall database and an application knowledge data Database, a domain knowledge database and a historical database; an input / output device electrically connected to the processor for providing an interface for inputting an audio; wherein the processor includes: a speech recognition module To identify the audio to form a corpus; A corpus analysis module electrically connected to the speech recognition module for analyzing the corpus data using a natural language processing model to generate a linguistic feature information corresponding to the corpus data, wherein the linguistic feature information The corpus analysis module uses a common vocabulary model to identify whether the corpus data has a plurality of system domain vocabularies that match the key entity set. The recognition result is set to the words, and the probability of occurrence of the words is analyzed, and the sentence structure of the corpus data is analyzed according to the words; and a common semantic model is used to estimate the occurrence of the words and the corpus data based on the common semantic model. The sentence structure identifies the intents of the corpus data and the probability corresponding to the intents; a context analysis module is electrically connected to the corpus analysis module, and is used to analyze the corpus data based on functional context information. The intents perform a functional situation analysis to confirm an operation corresponding to one of the intents; an instruction generation module, which is separated from the situation The module is electrically connected to find a template of the operation from the overall database, and input the vocabulary corresponding to the operation into the template of the operation to form an instruction corresponding to the operation; and an operation execution module, connected with the The instruction generating module is electrically connected to execute the instruction corresponding to the operation against the enterprise database or the enterprise resource system and generate a result corresponding to the operation, and output the result corresponding to the operation to the input / output device; wherein, This operation includes one of a data query operation and an instruction execution operation. The system for operating a virtual assistant according to claim 6, the The processor further includes: a training module electrically connected to the corpus analysis module for generating a system domain vocabulary based on the application knowledge database and the domain knowledge database, the system domain vocabulary collection and a plurality of The service application parameters are formed as a set of key entities. The set of key entities includes the vocabulary of the system domains, and classifies a plurality of training corpora into one of the query data operation and the execution instruction operation, according to the enterprise database. The classification of the training corpus corresponding to the query data operation intention forms a plurality of query data operation intentions, and according to the service behavior provided by the enterprise resource system, the intention of the training corpus that should perform the instruction operation forms a plural number. An execution instruction operation intention; a template establishment module, which is electrically connected with the training module, establishes the query data operation intention templates, and the execution command operation intention templates, according to the key entity set, the queries The data operation intention template and the execution instruction operation intention templates establish the general Database; a vocabulary model building module, which is electrically connected to the template to establish a module, to identify the plural first chances that the system domain words in the key entity set appear in the training corpora, and The identified system domain vocabularies analyze the plurality of sentence structure structures of the training corpora, and the plurality of associations between the system domain vocabularies with each other, and establish a relationship based on the first probabilities and the associations. A common vocabulary model; and a semantic model building module, which is electrically connected to the template, analyzes the query data operation intentions and the execution instruction operation intentions, and a plurality of second chances of the system domain vocabulary appear, And according to those sentence patterns Structure and the second chances to build the common semantic model. The system for operating a virtual assistant according to claim 5, wherein the processor further includes: a situation training module, which is electrically connected to the situation analysis module for using a classifier to store the data in the historical database Classification of relationship strengths produces a functional situation model. The system for operating a virtual assistant according to claim 7, wherein the context analysis module is further configured to compare the functional context information and the functional context information with the functional context model, and generate a functional context identification result, and According to the result of the functional context identification, it is determined that one of the intentions corresponds to one of the data query operation and the execution instruction operation.