WO2021161629A1

WO2021161629A1 - Automatic program code generation system, and program

Info

Publication number: WO2021161629A1
Application number: PCT/JP2020/045006
Authority: WO
Inventors: 基光白川
Original assignee: ソプラ株式会社
Priority date: 2020-02-13
Filing date: 2020-12-03
Publication date: 2021-08-19
Also published as: JP2021128516A; JP6889448B1

Abstract

According to the present invention, when generating a program code for executing a task, the code is very easily and automatically generated without requiring human intervention.　A program code for executing an execution operation, in which an execution operation target is specified in an execution operation command, is generated by: extracting an indication operation and a case component composed of at least an object case received according to the indication operation by a morpheme analysis of received text data; searching for the execution operation command corresponding to the extracted indication operation and the execution operation object corresponding to the extracted object case by referring to an execution operation table in which actual execution operation commands for a reference indication operation are associated with a degree of association having three or more steps and an object case table in which actual execution operation objects for a reference object case are associated with the degree of association having three or more steps, and substituting the execution operation command and the execution operation target which have been searched in the searching step for a basic syntax of the program code.

Description

Program code automatic generation system and program

The present invention relates to a program code automatic generation system and a program suitable for automatically generating a business automatic processing program for realizing business assistance.

In recent years, technologies related to RPA (Robotic Process Automation) have been attracting attention as a means for realizing work assistance such as desk work (routine work). As such a technique, for example, an information processing device of Patent Document 1 has been proposed.

The information processing device of Patent Document 1 has an acquisition unit that acquires user message information, an extraction unit that extracts task information related to the user from the acquired message information, and a task information from the extracted task information. An identification unit that identifies a person in charge and a related person, and a classification unit that classifies the task information into first task information in which the user is the person in charge, or second task information in which the user is the related person. It is characterized by including a registration unit for registering the classified first or second task information in a database, and an output unit for outputting the first or second task information with reference to the database.

Japanese Unexamined Patent Publication No. 2019-16280

By the way, if you want the program to automatically execute new work, you need to create a program. Conventionally, the process of creating a program involves defining the requirements for the new business, designing the system, developing the program code, and then testing and verifying the program code. Such program code was usually manually coded each time a new business was created.

However, with the rapid progress of IT in recent years, new businesses are diverse and the frequency of new creations is increasing.

In addition, there are cases where even one simple task within the company must be changed at any time depending on the situation. For example, even if the in-house work of "send daily report to employee XX's PC" can be programmed and automatically performed, identify what "employee XX" and "daily report" are. However, the program code must be created each time.

In this way, if the program code is manually generated each time the new work is increased and the work content is changed, the amount of work becomes enormous, the work load on the worker increases, and the work delays. If it occurs, there is a problem that it may hinder the flow of business.

Therefore, the present invention has been devised in view of the above-mentioned problems, and an object of the present invention is to execute the business in order to automatically execute the business in the system on the computer side. It is an object of the present invention to provide a program code automatic generation system and a program which can be extremely easily and automatically generated without human intervention when generating the program code of the above.

The program code automatic generation system according to the present invention has a reception means that accepts the input of text data via voice or an input terminal, and an instruction operation by morphologically analyzing the text data received by the reception means. Refer to the extraction means for extracting the case component consisting of at least the target case and the end point case to be dependent, and the execution action table in which the actual execution action instruction for the reference instruction action is associated with three or more levels of association. The actual execution operation target for the target case is associated with the target case table having three or more levels of association, and the actual execution operation destination for the reference end point case is associated with the three or more levels of association. Corresponds to the storage means for storing the extracted end point case, the execution operation instruction corresponding to the extracted instruction operation, the execution operation target corresponding to the extracted target case, and the extracted end point case. The search means for searching the execution operation destination by referring to the degree of association of the execution action table, the target case table, and the end point case table stored by the above storage means, and the basic syntax of the program code by the above search means. By substituting the searched execution operation target, execution operation target, and execution operation destination, the program code for executing the execution operation specified in the execution operation instruction for the execution operation target to the execution operation destination can be obtained. It is characterized by including a code generating means for generating.

The program code automatic generation program according to the present invention relates to an instruction operation by performing a morphological analysis of a reception step that accepts input of text data via voice or an input terminal and the text data received in the reception step. An extraction step that extracts a case component consisting of at least the target case and the end point case to be received, an execution operation table in which the actual execution operation instruction for the reference instruction operation is associated with three or more levels of association, and a reference The actual execution operation target for the target case is associated with the target case table having three or more levels of association, and the actual execution operation destination for the reference end point case is associated with the three or more levels of association. Refer to each degree of association in the end point case table, the execution action instruction corresponding to the above-extracted instruction action, the execution action target corresponding to the above-extracted target case, and the execution corresponding to the above-extracted end point case. By substituting the execution operation target, the execution operation target, and the execution operation destination searched in the above search step into the search step for searching the operation destination and the basic syntax of the program code, the execution operation target is assigned to the execution operation destination. The computer is made to execute the code generation step of generating the program code for executing the execution operation specified in the execution operation instruction.

According to the invention described above, in order to automatically execute a business in a system on the computer side, it is extremely easy and automatic without human intervention when generating a program code for executing the business. It is possible to generate the system.

FIG. 1 is a block diagram of the program code automatic generation system according to the embodiment. 2 (a) and 2 (b) are schematic views showing an example of the configuration of the program code automatic generation device 1. FIG. 3 is a flowchart of a program code automatic generation system to which the present invention is applied. FIG. 4 is a diagram showing an example in which a user who installs this system sets and registers an execution destination in advance for each company. FIG. 5 is a diagram showing an example of an execution operation table. FIG. 6 is a diagram showing another example of the execution operation table shown in FIG. FIG. 7 is a diagram showing an example of an accusative case table. FIG. 8 is a diagram showing another example of the accusative table shown in FIG. FIG. 9 is a diagram showing an example of an end point case table. FIG. 10 is a diagram showing another example of the end point case table shown in FIG. FIG. 11 is a diagram for explaining a case where machine learning by artificial intelligence is used in searching the basic syntax of the program code. FIG. 12 is a diagram for explaining a method of generating a confirmation statement for confirming the input contents to the user.

Hereinafter, an example of the program code automatic generation system according to the embodiment of the present invention will be described with reference to the drawings.

(Embodiment: Program Code Automatic Generation System 100)
An example of the configuration of the program code automatic generation system 100 according to the present embodiment will be described with reference to FIGS. 1 to 2. FIG. 1 is a schematic diagram showing the overall configuration of the program code automatic generation system 100 according to the present embodiment.

The program code automatic generation system 100 is mainly used for generating program code for realizing business assistance (for example, business automation processing) such as routine work. The program code automatic generation system 100 automatically generates a program code for executing a business, and thereby performs each business in the company (for example, delivery of mail, collection of progress of workers, file management, file transfer, work). Management etc.) can be performed automatically on the computer. The program code automatic generation system 100 can set the automatic generation of the program code by voice or text, and a user who does not have specialized knowledge such as a system administrator (for example, the program code automatic generation system 100). Even for users who manage their business by using them), it is possible to easily realize automatic generation of program code for automatically performing new business on a computer.

As shown in FIG. 1, for example, the program code automatic generation system 100 includes a program code automatic generation device 1, and the user may use the program code automatic generation device 1. The program code automatic generation system 100 may include a terminal 2 connected to the program code automatic generation device 1 via, for example, a communication network 4, and the user may use the program code automatic generation device 1 via the terminal 2. The program code automatic generation system 100 includes, for example, a server 3 connected to the program code automatic generation device 1 via a communication network 4, and a user can perform various information with the server 3 via the program code automatic generation device 1 or a terminal 2. Each means may be realized by sending and receiving.

FIG. 2A is a schematic diagram showing an example of the configuration of the program code automatic generation device 1. As the program code automatic generation device 1, for example, a known electronic device such as a personal computer (PC), a smartphone, or a tablet terminal is used. The program code automatic generation device 1 includes, for example, a housing 10, a CPU (Central Processing Unit) 101, a ROM (Read Only Memory) 102, a RAM (Random Access Memory) 103, a storage unit 104, and an I / F 105 to It includes 107, an input unit 108, and a notification unit 109. Each configuration 101 to 107 is connected by an internal bus 110.

The CPU 101 controls the entire program code automatic generation device 1. The ROM 102 stores the operation code of the CPU 101. The RAM 103 is a work area used during the operation of the CPU 101. The storage unit 104 stores various information such as processing data. As the storage unit 104, for example, an HDD (Hard Disk Drive), an SSD (Solid State Drive), or the like is used.

The I / F 105 is an interface for transmitting and receiving various information to and from the terminal 2, the server 3, the communication network 4, and the like. The I / F 106 is an interface for transmitting and receiving various information to and from the input unit 108. The I / F 107 is an interface for transmitting and receiving various information to and from the notification unit 109.

In addition to using a keyboard as the input unit 108, a sound collecting device such as a microphone may be used. A user who uses the program code automatic generation device 1 can input various information such as text data and voice via, for example, the input unit 108.

The notification unit 109 displays various information such as display data stored in the storage unit 104, the processing status of the program code automatic generation device 1, and the like. A display may be used as the notification unit 109, or a speaker may be used, for example.

As I / F105 to I / F107, for example, the same one may be used, and as each I / F105 to I / F107, for example, a plurality of ones may be used. When a touch panel type display is used as the notification unit 109, the notification unit 109 may include the input unit 108.

FIG. 2B is a schematic diagram showing an example of the function of the program code automatic generation device 1. The program code automatic generation device 1 may include an acquisition unit 11 and a calculation unit 12, and may include, for example, an execution unit 13, a storage unit 14, an output unit 15, and an intent storage unit 16. Each function shown in FIG. 2B is realized by the CPU 101 executing a program stored in the storage unit 104 or the like using the RAM 103 as a work area. In addition, a part of each function may be controlled by artificial intelligence. Here, the "artificial intelligence" may be based on any well-known artificial intelligence technology.

<Acquisition unit 11>
The acquisition unit 11 accepts the input of text data via voice or an input terminal. The acquisition unit 11 acquires text data input from the user via, for example, the terminal 2 or the input unit 108. For example, when a conversational sentence is input by voice from the user via the terminal 2 or the input unit 108, the acquisition unit 11 uses a known voice recognition technology (for example, voice recognition technology) to generate text data from the voice. get. As the voice recognition technology, a cloud-type voice recognition technology may be used, for example, via the communication network 4.

<Calculation unit 12>
The calculation unit 12 refers to the database and executes various processing operations and calculations based on the acquired text data. The arithmetic unit 12 extracts individual components of the sentence, including verbs, nouns, case components, etc., by performing morphological analysis on the received conversational sentence. The calculation unit 12 performs a processing operation of assigning an execution operation instruction corresponding to an instruction operation extracted from the received text data, an execution operation target corresponding to the target case, and an execution operation destination corresponding to the end point case. The calculation unit 12 executes a processing operation for determining an intent corresponding to the received text data. The arithmetic unit 12 refers to the storage unit 14 and extracts the basic syntax of the program code. Further, the arithmetic unit 12 generates a program code by substituting the assigned execution operation instruction, execution operation target, and execution operation destination into the basic syntax of the extracted program code.

<Execution unit 13>
The execution unit 13 executes business processing based on the program code generated by the calculation unit 12. As business processing, for example, routine work such as sending an email to the person in charge based on the content and deadline of the task, work management, updating the task progress history, etc. can be mentioned, and the content that can execute the business processing information as a program on the computer is used. Be done.

<Memory unit 14>
The storage unit 14 temporarily stores text data composed of conversational sentences acquired through the acquisition unit 11. The text data stored in the storage unit 14 may be read out and updated under the control of the calculation unit 12, the execution unit 13, and the like. The storage unit 14 holds at least three tables, an execution operation table, a target case table, and an end point case table. Further, the storage unit 14 may hold a code table.

<Output unit 15>
The output unit 15 outputs various information regarding the operation executed by the program code. The display data is notified so that the user can recognize it via the notification unit 109, the terminal 2, or the like. The output unit 15 outputs display data or the like to the terminal 2 or the like via the I / F 105, and outputs display data or the like to the notification unit 109 via the I / F 107.

<Intent storage 16>
One or two or more intents are stored in the intent storage unit 16. The intent may be stored in the intent storage unit 16 in association with the information that identifies the business process. The information that identifies the business process is usually an action name described later, but the format is not limited to these. Correspondence also includes, for example, the case where the intent has information that identifies the business process.

<Terminal 2>
As the terminal 2, for example, a known electronic device such as a personal computer, a smartphone, a tablet terminal, or a wearable terminal is used. The terminal 2 may have at least a part of the same configuration and functions as the program code automatic generation device 1 described above, for example. A plurality of terminals 2 may be provided, for example, and each terminal 2 may be connected to the program code automatic generation device 1 via the communication network 4.

<Server 3>
For example, the server 3 stores the above-mentioned various information. Various information sent from the program code automatic generation device 1 and the like is stored in the server 3 via, for example, the communication network 4. For example, the server 3 stores the same information as the storage unit 104, and may transmit and receive various information to and from the program code automatic generation device 1 and the like via the communication network 4. That is, in the program code automatic generation system 100, the server 3 may be used instead of the program code automatic generation device 1 or the storage unit 104 of the program code automatic generation device 1.

<Communication network 4>
The communication network 4 is an Internet network or the like to which the program code automatic generation device 1 is connected via a communication circuit. The communication network 4 may be composed of a so-called optical fiber communication network. Further, the communication network 4 may be realized by a known communication network such as a wireless communication network in addition to the wired communication network.

Next, the operation of the program code automatic generation system 100 to which the present invention is applied will be described.

As shown in FIG. 3, the conversational sentence is accepted in step S11. Specifically, when a conversational sentence is acquired by the acquisition unit 11 as voice data, text data is generated using a known voice recognition technique (for example, a phoneme recognition technique). Further, when the text data converted into electronic data is acquired by the acquisition unit 11, it will be used as it is. The text data converted into electronic data may include, for example, e-mail texts, information bulletin boards used inside or outside the company, and postings on various sites as they are.

The acquisition unit 11 may acquire text data at each timing of input by the user, or may acquire, for example, a plurality of text data accumulated in a certain period at once. As a method of generating text data from non-text format data input via the terminal 2 or the input unit 108, a known technique can be used. The text data acquired in this way is temporarily stored in the storage unit 14.

Next, the process proceeds to step S12, the conversational sentence as text data acquired in S11 and temporarily stored in the storage unit 14 is read out, and this is morphologically analyzed. This morphological analysis is mainly performed by the arithmetic unit 12. As the morphological analysis technique, any well-known morphological analysis technique may be used.

As a result of the morphological analysis in step S12, for example, for the text data "Register the product name, A5-7853K", the instruction operation consisting of "Register the accusative case consisting of the product name | A5-7853K |". Can be disassembled into. In addition, the text "Transfer this month's daily report of Taro Yamada to Chief Tokugawa" has the accusative case of "Taro Yamada | | This month | | Overtime | It can be decomposed into the instruction operation of "|". In other words, text data can be extracted through a combination of case components consisting of the accusative case and the end point case that are related to the verb consisting of the instruction action.

The case component is a noun phrase required to form a sentence with a verb (instruction action). The case in the case component is a function that selectively requests a combination of nouns or noun phrases necessary for forming a sentence according to the lexical meaning of the verb, and is called case control. The case grammar that is the rationale for this case component is based on a single sentence that is associated with the deep case (object case, conditional case, tool case, start point case, end point case, time case, etc.) that represents the substance. It is a theory that analyzes sentences as being. Then, it can be said that the noun (phrase) required as the deep case of the sentence by the verb is a case component necessary for supplementing the realization of the proposition by the verb. A case component is not just a noun phrase, but a noun phrase that a verb is involved in to realize its proposition. In other words, the case component is an element of nouns (including noun phrases) that are related to a verb, which can be an action start condition for realizing a proposition by a verb that defines an instructional action.

The accusative case here means the execution target of the proposition by the verb that defines the instruction action. In the case of the phrase "transfer file A", the verb "transfer" is subject to "file A" as the accusative case. The end point rating defines the place where the execution target defined by the target case is reflected, the destination to benefit from the execution target, and the destination to which the execution target is sent. In the case of the phrase "send file A to Taro Yamada", the verb "send" is subject to "file A" as the accusative case, and this is sent with Taro Yamada as the end point. This end point is "Taro Yamada".

Next, the process proceeds to step S13, and the intent consisting of the execution operation instruction, the execution operation target, the execution operation destination, etc. is determined from the instruction operation and the case component analyzed through the morphological analysis.

First, the arithmetic unit 12 corresponds to the execution action command corresponding to the extracted instruction action, the execution action target corresponding to the extracted accusative case, and the extracted end point case for the conversation sentence morphologically analyzed in step S12. The execution operation destination is searched by referring to each degree of association between the execution operation table, the target case table, and the end point case table.

The execution operation instruction here is a wording for instructing the execution operation in the actual program code, and corresponds to the actual database registration, writing to a file, transfer, deletion, monitor display, etc.

The execution operation target indicates the target for executing this execution operation instruction, and may be an invoice, a daily report, a specification file, data, an email, or the like, a product name, various events, and information. It may be (for example, working hours, inventory, etc.).

Various program codes can be completed by combining this execution operation target and the execution operation instruction.

For example, if the execution operation instruction is "transfer" and the execution operation instruction is "specification file", it is possible to create a program code called "specification file transfer" by combining these.

The execution operation destination indicates the execution destination for executing the execution operation instruction. For example, the user who installs this system may set and register the execution destination in advance for each company. For example, as shown in FIG. 4, "Taro Yamada's PC", "Tokugawa section chief's PC", "Development department's shared PC", etc. may be registered as execution operation destinations in the in-house LAN. In addition, a business partner who has crossed the internal LAN but is outside the company may also be registered as "a person in charge B of the business partner A company" via an external public communication network.

That is, before implementing the present invention, the end point case table is created, and at the time of this creation, each terminal device in the communication network (for example, "PC of Taro Yamada", "PC of Chief Tokugawa", An operation of pre-registering "a shared PC of the development unit" or the like) as an execution operation destination for each reference in the end point case table may be executed.

Next, the process proceeds to step S14, and the association analysis of the program code is performed. This association analysis of the program code performs an operation of extracting the basic syntax of the program code.

The specific methods of steps S13 and 14 will be described in detail later.

Next, the process proceeds to step S15, and the program code is created. In step S14, as described above, the basic syntax of the program code is merely extracted, and by substituting the target of the actual processing operation and the wording that defines each condition necessary for completing the processing operation. The program code is complete. Therefore, in step S15, the execution operation target is assigned to the execution operation destination by substituting the words defining the execution operation target, the execution operation destination, and the execution operation instruction into the basic syntax of the extracted program code. To generate the program code for executing the execution operation specified in the execution operation instruction.

In the steps S11 to S15, a program can be automatically generated based on the user's intention included in the conversational sentence received in step S11.

After the program code is completed in this way, it may be provided to the user or displayed via the notification unit 109, or the completed program code may be executed via the execution unit 13. You may do so. That is, according to the present invention, it is possible to execute the automatically generated program code as it is. Therefore, when included from the process from step S11, the user can automatically generate a program code incorporating the intention by issuing a conversational sentence, and the generated program code is put into execution as it is. be able to. This means that when the user speaks the action he / she wants the system to perform in a conversational sentence or inputs text data corresponding to the action, the action incorporating the intention is executed as it is based on the automatically generated program code. It becomes possible.

Next, the detailed method of determining the intent in step S13 and analyzing the association of the program code in step S14 will be described.

In executing these methods, the actual execution action instruction for the reference instruction action is associated with the execution action table having three or more levels of association, and the actual execution action target for the reference target accusative case is three. Use the accusative table associated with more than one level of association. Each of these tables is not limited to being organized in a visually recognizable table or matrix, but simply consists of trained data in which a machine learning model of artificial intelligence is stored, and a set thereof. You may be.

FIGS. 5 and 6 show an example of the execution operation table among these. In this execution operation table, it is premised that three or more levels of association between the reference instruction operation and the execution operation instruction are set in advance. It is assumed that the input data is, for example, reference instruction operations P01 to P03. For example, it is assumed that the reference instruction operation P01 is "sent", the reference instruction operation P02 is "up", the reference instruction operation P03 is "erase", and the like. The reference instruction operations P01 to P03 as such input data are linked to the execution operation instruction as output.

Such a reference instruction operation is associated with three or more stages of execution operation instructions (for example, "open file", "transfer", "print", "delete", etc.) as the output solution. They are linked to each other throughout the degree. Reference instruction actions are arranged on the left side via this degree of association, and each execution operation instruction is arranged on the right side via this degree of association. The degree of association indicates the degree of relevance to which execution operation instruction is highly related to the reference instruction operation arranged on the left side. In other words, this degree of association is an index indicating which execution action instruction is likely to be associated with each instruction action, and the accuracy in selecting the most probable execution action instruction from the instruction actions. Is shown. In the example of FIG. 5, w13 to w19 are shown as the degree of association. These w13 to w19 are shown in 10 stages as shown in Table 1 below, and the closer to 10 points, the higher the degree of relevance of each combination as an intermediate node to the execution operation instruction as an output. On the contrary, the closer to one point, the lower the degree of relevance of each combination as an intermediate node to the execution operation instruction as an output.

The degree of association w13 to w19 of three or more stages shown in FIG. 5 is acquired in advance. That is, in determining the actual search solution, a past data set is accumulated as to which of the processing operation and the execution operation instruction is adopted and evaluated, and these are analyzed and analyzed to show in FIG. Create a degree of association.

For example, in the past, it is assumed that "open file" is judged to have the highest suitability as an execution operation instruction for the reference instruction operation P01 and evaluated. By collecting and analyzing such a data set, the degree of association with the reference instruction operation becomes stronger.

This analysis may be performed by artificial intelligence. In such a case, for example, in the case of the instruction operation P01, the analysis is performed based on the past data set. In the case of the instruction operation P01, if there are many cases of "opening a file", the degree of association connected to this execution operation instruction is set higher, and if there are many cases of "printing", this execution operation is performed. Set a higher degree of association that leads to commands. For example, in the example of the processing operation P01, "Open file" and "Print" are linked, but from the previous case, the degree of association of w13 that leads to "Open file" is set to 7 points, and "Print". The degree of association of w14 that leads to is set to 2 points.

Further, this degree of association may be composed of the nodes of the neural network in artificial intelligence. That is, the weighting coefficient for the output of the node of this neural network corresponds to the above-mentioned degree of association. Further, the network is not limited to a neural network, and may be composed of all decision-making factors constituting artificial intelligence.

In such a case, as shown in FIG. 6, a processing operation is input as input data, an execution operation instruction is output as output data, at least one hidden layer is provided between the input node and the output node, and the machine is provided. You may let them learn. The above-mentioned degree of association is set in either one or both of the input node and the hidden layer node, and this is the weight of each node, and the output is selected based on this. Then, when the degree of association exceeds a certain threshold value, the output may be selected.

Such degree of association is what is called learned data in artificial intelligence. After creating such learned data, the execution operation instruction will be actually searched from the instruction operation. In such a case, the instruction operation extracted in step S12 is newly acquired. Based on the newly acquired instruction operation, the execution operation instruction corresponding to this is searched. In such a case, the degree of association shown in FIG. 5 (Table 1) acquired in advance is referred to. For example, when the newly acquired instruction operation is the same as or similar to P02, "transfer" is associated with w15 and "print" is associated with the association degree w16 via the association degree. In such a case, "transfer" with the highest degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and "print", which has the lowest degree of association but the association itself is recognized, may be selected as the optimum solution. In addition to this, it goes without saying that an output solution to which the arrows are not connected may be selected, and any other output solution may be selected in any other priority as long as it is based on the degree of association.

At this time, the synonym dictionary may be stored in the storage unit 14. A synonym dictionary is a dictionary related to synonyms. In the synonym dictionary, a word possessed by the reference instruction operation and one or more synonyms of the word are registered for each one or more reference instruction operations stored in the storage unit 14. Specifically, for example, "send", "deliver", and the like may be registered in association with the reference instruction operation "transfer". Then, through this synonym dictionary, it is possible to determine whether or not the newly acquired instruction operation is similar to the reference instruction operation. If the reference instruction action is "transfer" and the newly acquired instruction action is "send", it corresponds to "deliver" because it is registered in advance as similar in the synonym dictionary. It becomes possible to judge that it should be done.

By referring to such a degree of association, it is possible to accurately determine what kind of execution operation instruction the instruction operation extracted from the text data corresponds to.

FIGS. 7 and 8 show an example in which the actual execution operation target for the reference target case uses the target case table associated with three or more levels of association.

In this accusative table, it is premised that three or more levels of association between the accusative case for reference and the accusative case for execution are set in advance. It is assumed that the input data is, for example, reference target cases P01 to P03. For example, it is assumed that the reference target case P04 is "mail at 12:00 on December 3", the reference target case P05 is "delivery note", and the reference target case P06 is "weekly report". The reference target cases P04 to P06 as such input data are connected to the execution operation target as output.

Such a reference target case is for an execution operation target as this output solution (for example, "mail received at 14:00 on December 7", "invoice", "daily report", "specification", etc.). They are linked to each other through three or more levels of linking. The reference target cases are arranged on the left side via this degree of association, and each execution operation target is arranged on the right side via this degree of association. The degree of association indicates the degree of relevance to which execution operation target is highly related to the reference target cases arranged on the left side. In other words, this degree of association is an index showing what kind of accusative case is likely to be associated with the accusative case, and the accuracy in selecting the most probable accusative case from the accusative case. Is shown. In the example of FIG. 7, w13 to w19 are shown as the degree of association. Of course, the example of the degree of association in FIG. 7 is not necessarily the same as that in FIG.

The degree of association w13 to w19 of three or more stages shown in FIG. 7 is acquired in advance. That is, in determining the actual search solution, it is shown in FIG. 7 by accumulating past data sets and analyzing and analyzing which of the accusative case and the execution operation target was adopted and evaluated. Create a degree of association.

For example, in the past, it is assumed that the "invoice" is judged to have the highest suitability as the execution operation target for the reference target case P04 and evaluated. By collecting and analyzing such data sets, the degree of association with the accusative case for reference becomes stronger.

This analysis may be performed by artificial intelligence. In such a case, for example, in the case of the target P04, the analysis is performed based on the past data set. In the case of accusative P04, if there are many cases of "email received at 14:00 on December 7", the degree of association connected to this execution operation target is set higher, and there are many cases of "invoice". Is set to a higher degree of association connected to this execution operation target. For example, in the example of the accusative case P04 for reference, it is linked to "Email received at 14:00 on December 7" and "Daily report", but it leads to "Email received at 14:00 on December 7" from the previous case. The degree of association of w13 is set to 7 points, and the degree of association of w14 that leads to the "daily report" is set to 2 points.

Further, this degree of association may be composed of the nodes of the neural network in artificial intelligence.

In such a case, as shown in FIG. 8, the processing operation is input as input data, the execution operation instruction is output as output data, at least one hidden layer is provided between the input node and the output node, and the machine is provided. You may let them learn. The above-mentioned degree of association is set in either one or both of the input node and the hidden layer node, and this is the weight of each node, and the output is selected based on this. Then, when the degree of association exceeds a certain threshold value, the output may be selected.

Such degree of association is what is called learned data in artificial intelligence. After creating such learned data, we will actually search for the execution operation target from the accusative case. In such a case, the accusative case extracted in step S12 is newly acquired. Based on the newly acquired accusative case, the execution operation target corresponding to this is searched. In such a case, the degree of association shown in FIG. 7 (Table 1) acquired in advance is referred to. For example, when the newly acquired accusative case is the same as or similar to P05, the "invoice" is associated with the association degree w15 and the "daily report" is associated with the association degree w16 through the association degree. In such a case, the "invoice" with the highest degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and the "daily report", which has the lowest degree of association but the association itself is recognized, may be selected as the optimum solution. In addition to this, it goes without saying that an output solution to which the arrows are not connected may be selected, and any other output solution may be selected in any other priority as long as it is based on the degree of association.

At this time, the synonym dictionary may be stored in the storage unit 14. In the synonym dictionary, a word possessed by the accusative case and one or more synonyms of the word are registered for each one or more accusative cases stored in the storage unit 14. Specifically, for example, a "business report", a "business diary", and the like may be registered in association with the reference target case "daily report". Then, through this synonym dictionary, it is possible to determine whether or not the newly acquired accusative case is similar to the accusative case for reference. If the accusative case for reference is "daily report" and the newly acquired accusative case is "business diary", it corresponds to "daily report" because it is registered in advance as similar in the synonym dictionary. It becomes possible to judge.

By referring to such a degree of association, it is possible to accurately determine what kind of execution operation target the accusative case extracted from the text data corresponds to.

FIGS. 9 and 10 show an example in which the actual execution operation target for the reference end point case uses the end point case table associated with three or more levels of association.

In this end point case table, it is premised that the degree of association between the reference end point case and the execution operation destination is set in advance. It is assumed that the input data is, for example, reference end point cases P07 to P09. For example, the reference end point rating P07 is "Taro Yamada's PC", the reference end point rating P08 is "Doi section chief's PC", and the reference end point rating P09 is "person in charge C of business partner A". And. The reference end point cases P07 to P09 as such input data are connected to the execution operation destination as the output.

Such reference end points are the execution operation destinations as this output solution (for example, "Taro Yamada's PC", "Tokugawa's PC", "Business partner A's person in charge B", "Common to the development department". It is linked to each other through three or more levels of linking to "PC" etc.). The reference end point cases are arranged on the left side via this degree of association, and each execution operation destination is arranged on the right side via this degree of association. The degree of association indicates the degree of relevance to which execution operation destination is highly related to the reference end point case arranged on the left side. In other words, this degree of association is an index indicating what execution operation destination each end point case is likely to be associated with, and the accuracy in selecting the most probable execution operation destination from the end point case. Is shown. In the example of FIG. 9, w13 to w19 are shown as the degree of association. Of course, the example of the degree of association in FIG. 9 is not necessarily the same as that in FIGS. 5 and 7.

The degree of association w13 to w19 of three or more stages shown in FIG. 9 is acquired in advance. In other words, in determining the actual search solution, the past data set, which is adopted or evaluated as the end point case or the execution operation destination, is accumulated, and these are analyzed and analyzed to show in FIG. Create a degree of association.

For example, in the past, it is assumed that "the person in charge B of the business partner A" is judged to have the highest suitability as the execution operation destination for the reference end point rating P07, and is evaluated. By collecting and analyzing such a data set, the degree of association with the reference end point case P07 becomes stronger.

This analysis may be performed by artificial intelligence. In such a case, for example, in the case of the target P07, the analysis is performed based on the past data set. In the case of the end point rating P07, if there are many cases of "Taro Yamada's PC", the degree of association connected to this execution operation destination is set higher, and there are many cases of "person in charge B of business partner A". In that case, the degree of association connected to this execution operation destination is set higher. For example, in the example of the end point rating P07 for reference, it is linked to "Taro Yamada's PC" and "Person in charge B of customer A company", but from the previous case, the connection of w13 connected to "Taro Yamada's PC". The degree is set to 7 points, and the degree of association of w14 connected to "the person in charge B of the business partner A company" is set to 2 points.

In such a case, as shown in FIG. 10, a processing operation is input as input data, an execution operation instruction is output as output data, at least one hidden layer is provided between the input node and the output node, and the machine is provided. You may let them learn. The above-mentioned degree of association is set in either one or both of the input node and the hidden layer node, and this is the weight of each node, and the output is selected based on this. Then, when the degree of association exceeds a certain threshold value, the output may be selected.

Such degree of association is what is called learned data in artificial intelligence. After creating such learned data, we will actually search for the execution operation destination from the end point case. In such a case, the end point case extracted in step S12 is newly acquired. Based on the newly acquired end point case, the execution operation destination corresponding to this is searched. In such a case, the degree of association shown in FIG. 9 (Table 1) acquired in advance is referred to. For example, if the newly acquired end point rating is the same as or similar to P08, the "PC of Tokugawa section chief" is w15 and the "person in charge B of business partner A" is linked through the degree of association. It is associated with degree w16. In such a case, the “PC of Tokugawa section chief” with the highest degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and select "the person in charge B of business partner A" as the optimum solution, although the degree of association is low but the association itself is recognized. May be good. In addition to this, it goes without saying that an output solution to which the arrows are not connected may be selected, and any other output solution may be selected in any other priority as long as it is based on the degree of association.

At this time, the synonym dictionary may be stored in the storage unit 14. In the synonym dictionary, a word possessed by the end point case and one or more synonyms of the word are registered for each one or more reference end point cases stored in the storage unit 14. Through this synonym dictionary, it may be determined whether or not the newly acquired end point case is similar to the reference end point case.

By referring to such a degree of association, it is possible to accurately determine what kind of execution operation destination the end point case extracted from the text data corresponds to.

By performing the association analysis of the program code in steps S13 and 14 in this way, the execution action instruction corresponding to the extracted instruction action, the execution action target corresponding to the extracted accusative case, and the extracted end point case. The execution operation destination corresponding to is narrowed down.

Next, the details of the program code creation method in step S15 will be described. The program code is created by extracting the basic syntax of the highly relevant program code based on the execution operation target, the execution operation target, and the execution operation destination searched through the degree of association. Then, the execution operation target, the execution operation target, and the execution operation destination searched through the degree of association are substituted for the basic syntax of the extracted program code.

Table 2 shows an example of searching for the basic code of the program code.

The basic syntax of the program code is the prototype of the program code for actually executing various processing operations on a PC or the like. The program code can be completed by substituting the necessary wording into the basic syntax of this program code. Examples of the basic syntax of the program code are "INSERT INTO registration destination VALUES {param1};", etc., there is "INSERT" (register) as an execution operation instruction, and "registration destination" as an execution operation destination, ({Param1}) as the execution operation target has already been completed in the syntax. The program code can be completed by substituting the execution operation target, the execution operation target, and the execution operation destination that are actually searched through the degree of association with such a syntax. For example, by substituting the searched execution operation destination "Taro Yamada's PC" as the "registration destination" and substituting the searched sales data as ({param1}), "sales data is transferred to Taro Yamada's PC". The program code "Register" can be completed.

Similarly, in the case of the text data "display the slide for presentation on the display of the conference room", the "slide for presentation" as the target case, the "display of the conference room" as the end point case, and the instruction operation. "Display" is extracted, and the execution operation target, execution operation target, and execution operation destination are searched according to each. Then, the basic syntax of the program code according to the execution operation destination is searched in the same manner.

Actually, the basic syntax of the program code is searched through the code table shown in Table 2. In the code table, the basic syntax of the program code corresponds to each other for the reference execution operation target, the reference execution operation target, and the reference execution operation destination in the same row. For example, if the reference execution operation target is "billing data" and the reference execution operation instruction is "DB reference", the basic syntax of the program code corresponding to this is "SELECT billing amount".

At this time, the combination of one reference execution operation target, reference execution operation target, and reference execution operation destination may correspond to the basic syntax of a plurality of program codes, and conversely, one basic syntax may correspond to a plurality of references. It may correspond to the combination of the execution operation target for reference, the execution operation target for reference, and the execution operation destination for reference.

By storing such a code table in the storage unit 14, it can be read and referred to in the process of calculation by the calculation unit 12.

FIG. 11 shows an example of searching the basic syntax of the program code through machine learning by artificial intelligence for the code table. In the example of FIG. 11, a combination having a reference execution operation instruction as an input variable in the code table, a reference execution operation target, and a reference execution operation destination is input as an intent, and the basic syntax of the program code is set. It becomes the output. Specifically, it is assumed that the input data is, for example, a reference execution operation instruction (“printer output”, “open file”, etc.), a reference execution operation target, and a reference execution operation destination. The intermediate node 61 is a combination of the reference execution operation target and the reference execution operation destination with respect to the reference execution operation instruction as such input data. Each intermediate node 61 is further connected to an output. In this output, the basic syntaxes A to E of the program code as the output solution are displayed. The basic syntax A of the program code is, for example, "SELECT billing amount FROM billing data WHERE company = {param1} AND billing month = {param2};", and the basic syntax B is, for example, "Write Line product list.dat {param1". }; ”.

Each combination (intermediate node) of the reference execution operation instruction, the reference execution operation target, and the reference execution operation destination is related to each other through three or more levels of association with the basic syntax of the program code as this output solution. It is related. The reference execution operation instruction, the reference execution operation target, and the reference execution operation destination are arranged on the left side via this degree of association, and the basic syntax is arranged on the right side via this degree of association. The degree of association indicates the degree of relevance to the basic syntax for the execution operation instructions arranged on the left side. In other words, this degree of association is an index indicating which program code basic syntax is likely to be associated with each reference execution operation instruction, reference execution operation target, and reference execution operation destination. , It shows the accuracy in selecting the most probable basic syntax of the program code from the execution operation instructions.

The degree of association w13 to w22 of three or more stages shown in FIG. 11 is acquired in advance. In determining the actual search solution, the past data indicating which of the reference execution operation instruction, the reference execution operation target, the reference execution operation destination, and the basic syntax of the program code in that case was suitable is used. Accumulate, analyze and analyze these to create a degree of association.

This analysis may be performed by artificial intelligence. In such a case, for example, when the reference execution operation instruction is "transfer", and the reference execution operation target and the reference execution operation destination are "sales data, Taro Yamada's PC", the program code. Analyze the basic syntax of from past data. When there are many cases of basic syntax C, the degree of association leading to this basic syntax C is set higher, and when there are many cases of basic syntax E and few cases of basic syntax C, the association leading to basic syntax E is set. Set the degree high and the degree of association leading to the basic syntax C low. For example, in the example of the intermediate node 61a, the output of the basic syntax A and the basic syntax B is linked, but from the previous case, the degree of association of w13 connected to the basic syntax A is 7 points, and the association of w14 connected to the basic syntax B is set to 7. The degree is set to 2 points.

Further, the degree of association shown in FIG. 11 may be composed of the nodes of the neural network in artificial intelligence. That is, the weighting coefficient for the output of the node of this neural network corresponds to the above-mentioned degree of association. Further, the network is not limited to a neural network, and may be composed of all decision-making factors constituting artificial intelligence.

In the example of the degree of association shown in FIG. 11, the node 61b has the degree of association of the basic syntax C w15 and the degree of association of the basic syntax E w16.

Such degree of association is what is called learned data in artificial intelligence. After creating such learned data, when actually searching for the basic syntax from now on, the above-mentioned learned data will be used. In such a case, the execution operation instruction, the execution operation target, and the execution operation destination searched in steps S13 to S14 are used.

Search for the optimum basic syntax of the program code based on the newly acquired execution operation instruction, execution operation target, and execution operation destination in this way. In such a case, the degree of association shown in FIG. 11 (Table 1) acquired in advance is referred to. For example, when the newly acquired execution operation instruction is "open file" and the intent consisting of the execution operation target and the execution operation destination is P21, the node 61d moves through the degree of association. The node 61d is associated with the basic syntax C at w19 and the basic syntax D at the degree of association w20. In such a case, the basic syntax C having the highest degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and the basic syntax D in which the degree of association is low but the association itself is recognized may be selected as the optimum solution. In addition to this, it goes without saying that an output solution to which the arrows are not connected may be selected, and any other output solution may be selected in any other priority as long as it is based on the degree of association.

Table 3 below shows an example of the degree of association w1 to w12 extending from the input.

The intermediate node 61 may be selected based on the degree of association w1 to w12 extending from this input. That is, the larger the degree of association w1 to w12, the heavier the weighting in the selection of the intermediate node 61 may be. However, the degrees of association w1 to w12 may all have the same value, and the weights in the selection of the intermediate node 61 may all be the same.

The present invention is not limited to the above-described embodiment. By searching for the execution operation target, execution operation target, and execution operation destination, and substituting the execution operation target, execution operation target, and execution operation destination into the basic syntax of the program code, the execution operation target is assigned to the execution operation destination. The case where the program code for executing the execution operation specified in the execution operation instruction is generated has been described as an example, but the present invention is not limited to this. The search for the execution operation destination may be omitted, and the program code for executing the execution operation specified in the execution operation instruction may be generated for the execution operation target.

Further, the case component to be extracted is not limited to the above-mentioned target case and end point case, but may include a start point case and a conditional case.

The starting point case defines the place where the execution target specified by the target case is generated and the start source of the execution target. In the case of the phrase "send file A from Taro Yamada", the verb "send" is subject to "file A" as the accusative case, and this is sent starting from Taro Yamada. , This starting point is "Taro Yamada".

Even when such a start point case is used, the reference end point case in the end point case table shown in FIG. 9 becomes the reference start point case, and the search is the execution operation source. That is, the start point case table in which the actual execution operation source for the reference start point case is associated with three or more levels of association is stored. Then, the text data is analyzed, and the execution operation source for the extracted start point case is searched by referring to the degree of association of the stored start point case table. Next, by substituting the searched execution operation source into the basic syntax of the program code, the execution operation specified in the execution operation instruction is performed from the execution operation source to the execution operation destination. Generate program code to execute.

In addition, the conditional case defines the conditions for executing the operation of the execution target specified by the accusative case. The conditions include when (time), how (method), when to start (operation start condition), when to execute (operation end condition), and the like.

For example, in the case of the phrase "send file A by tomorrow", "file A" is assigned as the accusative case and "by tomorrow" is assigned as the accusative case for the verb "send". This condition is "by tomorrow".

Even when such a start point case is used, the reference end point case shown in FIG. 9 becomes the reference condition case, and the search is the execution operation condition. That is, the condition case table in which the actual execution operation conditions for the reference condition case are associated with each other with three or more levels of association is stored. Then, the text data is analyzed, and the execution operation condition for the extracted conditional case is searched by referring to the degree of association of the stored conditional case table. Next, by substituting the searched execution operation condition into the basic syntax of the program code, the execution operation target is executed for the execution operation destination as specified in the execution operation instruction based on the execution operation condition. The action will be performed.

The present invention is not limited to the above-described embodiment. For example, as shown in FIG. 12, a confirmation statement for confirming the input contents to the user is generated based on the degree of association defined in each of the execution operation table, the target case table, and the end point case table. You may. The generated confirmation text may be output by voice or image. That is, if any of the execution operation instruction, the execution operation target, and the execution operation destination cannot be appropriately specified from the input contents from the user, a confirmation statement for inquiring the user about the intention is generated again and the intention is generated. Run the process to confirm. While the execution action instruction, the execution action target, and the execution action destination as the search solution are all finite, the types of wording of the text data generated by the user are almost infinite. Therefore, depending on the instruction operation and the case component extracted from the text data generated by the user, it may not be possible to search for the execution operation instruction, the execution operation target, and the execution operation destination. Further, when the user uses a dialect, the execution operation instruction, the execution operation target, and the execution operation destination may not be narrowed down through the degree of association depending on the content of the dialect. In such a case, a confirmation statement for inquiring the user about the intention is generated again. The process is to accept re-entry of text data from the user in response to the generation of confirmation text and notification, but this process may be performed in a so-called chat format.

The confirmation statement may be generated based on the degree of association associated with the execution action instruction, the execution action target, and the execution action destination searched through the execution action table, the target case table, and the end point case table. If the execution operation instruction "Open file" is searched for in the execution operation table, but the association degree w13 associated with this is 5 out of 10 grades, to be honest, it is under such a strong association degree. There is a possibility that the execution operation instruction has not been determined in, and the search solution does not capture the user's intention. In other words, it is a case where the execution operation instruction, the execution operation target, and the execution operation destination cannot be narrowed down through the degree of association. In such a case, a confirmation statement is generated, the user's intention is confirmed, and re-input is accepted. Then, the solution search may be performed upsetly based on the contents of the received re-input. In this way, when the degree of association associated with the execution operation instruction, the execution operation target, and the execution operation destination is less than a certain threshold value, it is determined that the search that reflects the user's intention has not been performed. , You may want to generate a confirmation statement. This confirmation sentence may be performed by preparing a plurality of types of example sentences in advance and substituting those corresponding to the search solution into the example sentences. For example, if you want to check whether the user really intended the execution operation command "transfer", this execution operation command is in the ●● part of "Do you want to ●● file A?" A confirmation statement may be generated by substituting "transfer".

In addition, instead of setting such a threshold value, a confirmation statement is generated by comparing the degree of association associated with each of the execution operation instruction, the execution operation target, and the execution operation destination searched using each table. You may try to do it. When the degree of association associated with each of the searched execution operation instruction, execution operation target, and execution operation destination is compared with each other, if the degree of association associated with the searched execution operation target is the lowest, A confirmation statement for confirming the execution operation target may be generated and output.

In addition, since noise is superimposed on the user's voice, when this is incorporated into text data, there is no such wording in the synonym dictionary in the first place, and the reference instruction operation, reference target case, and reference end point are used. In some cases, it cannot be matched with the case. Even when the reference instruction operation, the reference target case, and the reference end point case cannot be collated in this way, a confirmation statement may be generated and output to the user in the same manner. For the generation of this confirmation sentence, an example sentence is created and stored for each reference instruction operation, reference target case, and reference end point case that cannot be collated, and the reference instruction operation and reference that cannot be actually collated. An example sentence may be read and output according to the accusative case and the end point case for reference.

When the degree of association is relatively low, it is judged that the search that reflects the user's intention has not been performed, and it is possible to confirm the intention by generating a confirmation sentence.

1 Program code automatic generation device 2 Terminal 3 Server 4 Communication network 10 Housing 11 Acquisition unit 12 Calculation unit 13 Execution unit 14 Storage unit 15 Output unit 16 Intent storage unit 61 Intermediate node 100 Program code automatic generation system 101 CPU
102 ROM
103 RAM
104 Preservation unit 105-107 I / F
108 Input unit 109 Notification unit 110 Internal bus

Claims

A reception means that accepts text data input via voice or an input terminal,
By morphological analysis of the text data received by the above-mentioned receiving means, an instruction operation, an extraction means for extracting at least a case component consisting of an accusative case, and an extraction means.
The execution operation table in which the actual execution operation instruction for the reference instruction operation is associated with three or more levels of association, and the actual execution operation target for the reference target case have three or more levels of association. A storage means that at least stores the associated accusative table,
Refer to the degree of association between the execution operation table and the accusative table stored by the storage means for the execution operation instruction corresponding to the extracted instruction operation and the execution operation target corresponding to the extracted accusative case. Search means to search by doing
By substituting the execution operation instruction and the execution operation target searched by the above search means into the basic syntax of the program code, the program code for executing the execution operation specified in the execution operation instruction can be obtained. An automatic program code generation system characterized by having a code generation means for generating.
The above-mentioned extraction means extracts a case component consisting of an end point case that depends on an instruction operation, and extracts the case component.
The storage means stores an end point case table in which the actual execution operation destination for the reference end point case is associated with three or more levels of association.
The search means searches for the execution operation destination for the extracted end point case by referring to the degree of association of the end point case table stored by the storage means.
The code generating means substitutes the execution operation destination searched by the search means into the basic syntax of the program code, so that the execution operation target is executed with respect to the execution operation destination specified in the execution operation instruction. The program code automatic generation system according to claim 1, wherein the program code for executing an operation is generated.
The search means informs the user based on the degree of association associated with the execution action table, the target case table, the execution action instruction searched through the execution action table, the execution action target, and the execution action destination, respectively. On the other hand, a confirmation statement generation means for generating a confirmation statement for confirming the input contents, and a confirmation statement generation means
It is provided with an output means for outputting a voice or an image of the confirmation sentence generated by the above confirmation sentence generation means.
The program code automatic generation system according to claim 2, wherein the reception means accepts re-input of text data by a user.
The code generation means refers to a code table associated with the basic syntax of the program code for the combination of the reference execution operation target, the reference execution operation target, and the reference execution operation destination, and the execution operation searched by the search means. The program according to claim 2 or 3, wherein the basic syntax of a highly relevant program code is extracted based on the target, the execution operation target, and the execution operation destination, and the above substitution is performed on the extracted basic syntax. Code automatic generation system.
The above code generation means creates the above code table associated with a combination of a reference execution operation target, a reference execution operation target, and a reference execution operation destination with three or more levels of association with the basic syntax of the program code. The program code automatic generation system according to claim 4, wherein the program code is referred to.
The program code automatic generation system according to any one of claims 1 to 5, further comprising a program execution means for executing the program code generated by the code generation means.
6. Program code automatic generation system.
The above-mentioned extraction means extracts a case component consisting of a starting point case that is affected by the instruction operation, and extracts the case component.
The storage means stores a start point case table in which the actual execution operation source for the reference start point case is associated with three or more levels of association.
The search means searches for an execution operation source for the extracted start point case by referring to the degree of association of the start point case table stored by the storage means.
By substituting the execution operation source searched by the search means into the basic syntax of the program code, the code generation means sets the execution operation target from the execution operation source to the execution operation destination. The program code automatic generation system according to any one of claims 2 to 5, wherein the program code for executing the execution operation specified in the above is generated.
The above-mentioned extraction means extracts a case component consisting of a conditional case that depends on the instruction operation, and extracts the case component.
The storage means stores a condition case table in which the actual execution operation condition with respect to the reference condition case is associated with three or more levels of association.
The search means searches for the execution operation condition for the extracted conditional case by referring to the degree of association of the conditional case table stored by the storage means.
By substituting the execution operation condition searched by the search means into the basic syntax of the program code, the code generation means sends the execution operation target to the execution operation destination based on the execution operation condition. The program code automatic generation system according to any one of claims 2 to 5, wherein a program code for executing an execution operation specified in an operation instruction is generated.
The program code automatic generation system according to any one of claims 1 to 9, wherein the storage means stores the degree of association corresponding to the weighting coefficient of each output of the node of the neural network in artificial intelligence. ..
The automatic program code generation system according to claim 5, wherein the code generation means uses the degree of association corresponding to the weighting coefficient of each output of the node of the neural network in artificial intelligence.
A reception step that accepts text data input via voice or an input terminal,
By morphological analysis of the text data received in the above reception step, the instruction operation, the extraction step of extracting the case component consisting of at least the accusative case related to this, and the extraction step.
The execution operation table in which the actual execution operation instruction for the reference instruction operation is associated with three or more levels of association, and the actual execution operation target for the reference target case have three or more levels of association. With reference to the associated target case table, an execution action instruction corresponding to the above-extracted instruction action, a search step for searching for an execution action target corresponding to the above-extracted target case, and a search step.
By substituting the execution operation instruction and the execution operation target searched in the above search step into the basic syntax of the program code, the program code for executing the execution operation specified in the execution operation instruction is generated. A program code automatic generation program characterized by having a computer execute a code generation step to be performed.