JP6753598B1 - Program code automatic generator and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a program code automatic generation device and a program which can be extremely easily generated and automatically generated without human intervention when generating a program code for executing a business. An automatic program code generation system receives a conversational sentence, refers to a processing operation table in which a processing operation and an execution instruction are associated with each other, and has a highly relevant execution instruction for a processing operation extracted from the received conversational sentence. To assign. Determine the intent that has the action name that identifies the processing action corresponding to the received conversation statement, refer to the code table associated with the basic syntax of the program code for the combination of the execution instruction and the intent, and execute the assigned execution. Extract the basic syntax of the relevant program code based on the instruction and the intent determined in the intent determination step. [Selection diagram] Fig. 5

Description

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

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

The information processing apparatus of Patent Document 1 includes an acquisition unit that acquires message information of a user, an extraction unit that extracts task information related to the user from the acquired message information, and a task of a task from the extracted task information. An identification unit that identifies a person in charge and a person concerned, 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 person concerned. It is characterized by comprising a registration unit for registering the classified first or second task information in a database and an output unit for referring to the database and outputting the first or second task information.

JP, 2019-16280, A

By the way, in order to automatically execute a new business by a program, it is necessary to create a program. Conventionally, the process of creating a program involves defining the requirements for the new business, designing the system, further 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, even one simple task in the company may have to be changed at any time depending on the situation. For example, even if the in-house work of "notifying the boss of this month's overtime hours of employee 〇〇" is made into a program code and can be performed automatically, "employee 〇〇" and "boss" are changed due to transfer etc. Each time you do, you have to rewrite the program code.

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 an automatic program code generation device and a program that can be extremely easily generated and automatically generated without human intervention.

The program code automatic generation device according to the present invention refers to the conversation sentence receiving means that accepts the conversation sentence and the processing operation table in which the processing operation and the execution instruction are associated with each other, and extracts from the conversation sentence received by the conversation sentence receiving means. An execution instruction assigning means for assigning a highly relevant execution instruction and an intent determining means for determining an intent having an action name for specifying the processing operation included in the conversation sentence received by the conversation sentence receiving means. With reference to the code table to which the basic syntax of the program code for the combination of the execution instruction and the intent is associated, the execution instruction assigned by the execution instruction assigning means and the intent determined by the intent determining means Based on the above, the code extraction means for extracting the basic syntax of the highly relevant program code is provided , and the execution instruction assignment means is associated with the processing operation and the execution instruction with three or more levels of association. It is characterized by referring to a processing operation table .
Further, the program code automatic generation device according to the present invention refers to the conversation sentence receiving means for receiving the conversation sentence and the processing operation table in which the processing operation and the execution instruction are associated with each other, and the conversation sentence received by the conversation sentence receiving means. For the processing operation extracted from, an execution instruction assigning means for assigning a highly relevant execution instruction and an intent having an action name for specifying the processing operation included in the conversation sentence received by the conversation sentence receiving means are determined. Determining means and
Refer to the code table to which the basic syntax of the program code for the combination of the execution instruction and the intent is associated, and based on the execution instruction assigned by the execution instruction assigning means and the intent determined by the intent determining means. , A code extraction means for extracting the basic syntax of a highly relevant program code is provided, and the above code extraction means has three or more stages of a combination having an execution instruction and an intent and a basic syntax of the program code for the combination. It is characterized in that it refers to the code table associated with the degree of association of.

The program code automatic generation program according to the present invention refers to the conversation sentence reception step that accepts the conversation sentence and the processing operation table in which the processing operation and the execution instruction are associated with each other, and extracts from the conversation sentence received in the above conversation sentence reception step. An intent determination that determines an intent having an action name that specifies an action name corresponding to the conversational sentence received in the conversational sentence reception step and the execution instruction assignment step that assigns a highly relevant execution instruction to the processed processing operation. Referencing the code table in which the basic syntax of the program code for the combination of the step and the execution instruction and the intent is associated, the execution instruction assigned in the execution instruction assignment step and the intent determined in the intent determination step Based on the above, the computer is made to execute a code extraction step that extracts the basic syntax of the highly relevant program code, and in the above-mentioned execution instruction assignment step, the processing operation and the execution instruction are associated with each other in three or more stages. It is characterized by referring to the associated processing operation table .
Further, the program code automatic generation program according to the present invention refers to the conversation sentence reception step that accepts the conversation sentence and the processing operation table in which the processing operation and the execution instruction are associated with each other, and the conversation sentence received in the conversation sentence reception step. For the processing operation extracted from, an execution instruction assignment step for assigning a highly relevant execution instruction and an intent having an action name for specifying the processing operation corresponding to the conversation sentence received in the above conversation sentence reception step are determined. Referencing the code table in which the tent determination step and the basic syntax of the program code for the combination of the execution instruction and the intent are associated, the execution instruction assigned in the execution instruction allocation step and the in determined in the intent determination step. A computer is made to execute a code extraction step for extracting the basic syntax of highly relevant program code based on the tent, and in the above code extraction step, a combination having an execution instruction and an intent and a program code for the combination are executed. It is characterized in that the basic syntax of is referred to a code table associated with three or more levels of association.

According to the invention described above, in order to automatically execute a business in a computer-side system, 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 diagram showing an example of a processing operation table. FIG. 4 is a diagram showing an example of a code table. FIG. 5 is a flowchart of a program code automatic generation system to which the present invention is applied. FIG. 6 is a diagram showing an operation example of a program code automatic generation system to which the present invention is applied. FIG. 7 is a diagram showing another operation example of the program code automatic generation system to which the present invention is applied. FIG. 8 is a diagram for explaining a case where machine learning by artificial intelligence is used in searching for an execution instruction. FIG. 9 is a diagram showing an example in which the degree of association is set in either one or both of the input node and the hidden layer node, and this is used as the weight of each node. FIG. 10 is a diagram for explaining a case where machine learning by artificial intelligence is used in searching the basic syntax of the program code.

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 4. 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, so that each business in the company (for example, collection of worker's progress, task management, work management, etc.) can be performed on a computer. It can be done automatically. 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 it), 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-. It includes 107, an input unit 108, and a notification unit 109. The components 101 to 107 are connected by the 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 kinds of 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 with the terminal 2, the server 3, the communication network 4, and the like. The I/F 106 is an interface for transmitting/receiving various information to/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.

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

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. As the notification unit 109, a display may be used and, for example, a speaker may be used.

The same I/F 105 to I/F 107 may be used, and a plurality of I/Fs 105 to I/F 107 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. Further, some of the functions 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 acquires text data composed of conversational sentences. 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, phoneme recognition technology) to generate text data from the voice. get. As the voice recognition technology, for example, a cloud-type voice recognition technology may be used via the communication network 4.

<Calculator 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 arithmetic unit 12 performs a processing operation of assigning a highly relevant execution instruction to the processing operation extracted from the received conversational sentence. The calculation unit 12 executes a processing operation for determining an intent having an action name that specifies the processing operation corresponding to the received conversational sentence. The arithmetic unit 12 refers to the storage unit 14 and extracts the basic syntax of the program code according to the execution instruction and the intent. Further, the arithmetic unit 12 generates a program code by substituting a noun or a noun phrase extracted from a conversational sentence 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. Examples of business processing include routine work such as email transmission to a person in charge, work management, task progress history update, etc. based on the content and deadline of the task, and content that can be executed by a computer as business processing information is used. To be

<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 two tables, a processing operation table and a code table.

FIG. 3 shows an example of a processing operation table. The processing operation table is a table for associating what kind of execution instruction of the program the processing operation extracted from the conversation sentence (text data) specifically corresponds to. The processing operation table is composed of a column of processing operations extracted from conversational sentences and a column of meanings of specific execution instructions of the program code. As shown in FIG. 3, the processing operation includes all words that define the processing operation, such as "register", "tell", and "write". The processing action is not limited to the verb, and may be composed of any other grammatical element such as a noun as long as it defines the processing action. Examples of the processing operation composed of nouns may be "writing", "registration", and the like.

The program code execution instruction here is a higher-level conceptualization of the code corresponding to the processing operation, such as "PRINT", "DELETE", and "Write Line" in the program code. It was done.

In this processing operation table, the processing operations and the execution instructions in the same row have a corresponding relationship with each other. For example, the processing operation "input" corresponds to "DB (database) registration", and "write" corresponds to "file write".

At this time, one processing operation may correspond to a plurality of execution instructions, and conversely, one execution instruction may correspond to a plurality of processing operations. For example, two or more execution instructions of "monitor display" and "file creation" may correspond to the processing operation "output", and the execution instruction "monitor display" may correspond to "show" and "show". It may correspond to two or more processing operations of "output".

By storing such a processing operation table in the storage unit 14, it can be read out and referred to in the process of calculation by the calculation unit 12. By referring to this processing operation table, the arithmetic unit 12 can determine which execution instruction of the program the processing operation extracted from the conversational sentence (text data) specifically corresponds to.

FIG. 4 shows an example of a code table. The code table is a table that associates the meaning of a specific execution instruction of the program code with the basic syntax of the program code for an intent having an action name that specifies a processing operation included in a conversational sentence. The specific execution instruction of the program code corresponds to the execution instruction described in the processing operation table. The intent is information managed for each business process, and defines an action name described later. Business processing is processing related to business. It can be said that the work is, for example, a work performed by an organization such as a company or an organization. The work includes, for example, work until the fixed time, overtime after the fixed time, vacation, absenteeism, A case, B case, accounting, manufacturing, etc., but the types are not limited to these. The business process is, for example, information retrieval. The search may be referred to as an inquiry, for example. The information to be searched is, for example, attendance information such as overtime hours and working hours, but may be financial information such as balances and stock prices, or operating conditions of manufacturing lines, and is not limited thereto.

However, the business processing may be, for example, registration of information or processing based on information (for example, payroll calculation based on attendance information, financial transaction based on financial information, etc.), and is not limited thereto.

The intent usually has an action name that identifies a business process (processing operation). The action name is the name of the action. An action is a business process that is usually executed via an API. However, the action may be, for example, a business process executed in response to an SQL statement.

The action name usually corresponds to the API information described later. Therefore, it may be considered that the intent is associated with the API information, for example, via the action name.

The intent also usually has an intent name. The intent name is the name of the intent. Therefore, the intent can be considered as information that associates the intent specified by the intent name or the intent name with the action name or the action specified by the action name.

Specifically, the action name is, for example, "overtime hour inquiry", "working hour data inquiry", or the like, but any information that can specify the business process may be used.

The basic syntax of the program code is the prototype of the program code for actually executing various processing operations by a PC or the like. The program code can be completed by substituting the necessary nouns or noun phrases into the basic syntax of the program code. An example of the basic syntax of the program code is "INSERT INTO billing data (billing month, billing amount) VALUES ([param1], [param2]);", and inserts billing data and data to be processed. By doing so, the program code can be completed.

In the code table, the intent on the same line, the execution instruction of the program code, and the basic syntax of the program code correspond to each other. For example, if the intent is "reference to billing data" and the execution instruction is "DB reference", the basic syntax of the corresponding program code is "SELECT billing amount FROM billing data WHERE company = [param1] AND billing". Month = [param2]; ".

At this time, one intent may correspond to a plurality of execution instructions, and conversely, one execution instruction may correspond to a plurality of intents. In addition, one intent may correspond to the basic syntax of a plurality of program codes, and conversely, one basic syntax may correspond to a plurality of intents. In addition, one execution instruction may correspond to the basic syntax of a plurality of program codes, and conversely, one basic syntax may correspond to a plurality of execution instructions.

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

From the intent extracted from the conversational sentence (text data) and the execution instruction specified from the conversational sentence (text data) via the processing operation, it is possible to determine what kind of program code the basic syntax corresponds to.

<Output unit 15>
The output unit 15 outputs various information regarding the operation executed by the program code. The display data is notified via the notification unit 109 or the terminal 2 so that the user can recognize it. The output unit 15 outputs the display data and the like to the terminal 2 and the like via the I/F 105, and outputs the display data and 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 specifies 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 smart phone, or a tablet 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>
The server 3 stores, for example, the various types of information described above. 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 configured by a so-called optical fiber communication network. 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. 5, 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 by using a known voice recognition technique (for example, 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 posts on various sites as they are.

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

6 and 7 are diagrams for explaining each step shown in FIG. 5 with specific examples. The text data consists of the relationship between the processing operations such as "Register the product name, A5-7853K" and "Tell me about Taro Yamada's overtime hours this month" and the case components involved in this. The clause may have been acquired, and the keywords such as "A5-7853K, register" and "Taro Yamada, this month, overtime hours, tell me" should be acquired. May be good.

Next, the process proceeds to step S12, the conversational sentence as the 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, the conversational sentence "Register the product name, A5-7853K" can be decomposed into "Product name | A5-7853K | Register |". The conversation "Tell me about Taro Yamada's overtime hours this month" can be broken down into "Taro Yamada | | This month | | Overtime | Hours | Tell me".

Next, the process proceeds to step S13, and an intent having an action name having a word that is the same as or similar to one or more independent words is determined from the components analyzed through the morphological analysis.

Specifically, for example, it is assumed that the synonym dictionary is stored in the storage unit 14. A synonym dictionary is a dictionary related to synonyms. In the synonym dictionary, a word possessed by the action name and one or more synonyms of the word are registered for each action name constituting one or more intents stored in the storage unit 14. .. Specifically, for example, "overtime", "overtime hours", and the like may be registered in association with the word "overtime hours" of the action name "overtime hours inquiry".

When the acquisition department 11 accepts the conversation "Tell me about Taro Yamada's overtime hours this month", he acquires one or more independent words such as "Taro Yamada", "this month", and "overtime hours" from the conversation. Then, the intent storage unit 16 is searched using each independent word as a key, and it is determined whether or not there is an intent having an action name that matches the independent word. The match is, for example, an exact match, but may be a partial match. Then, if there is an intent having an action name that specifies the processing operation and having a word that matches the independent word, the intent is determined. In the above example, if there is an intent having the action name "registered product name" having the word "product name" matching the independent word "product name", the intent is determined. In addition, if there is an intent having the action name "reference to overtime hours" having the word "overtime hours" matching the independent word "overtime hours", the intent is determined.

If there is no intent with an action name that has a word that matches the independent word, for example, one synonym of one or more synonyms corresponding to the independent word is obtained from the synonym dictionary, and the synonym of the one is obtained. The intent storage unit 16 is searched using a synonym as a key, and it is determined whether or not there is an intent having an action name having a word matching the one synonym. Then, if there is an intent having an action name having a word that matches the one synonym, the intent is determined. If there is no such intent, in step S13, the same processing is performed for other synonyms to determine the intent. For any synonym, if there is no such intent, it may be output that the intent is not determined.

Next, the process proceeds to step S14, and the association analysis of the program code is performed. The arithmetic unit 12 first extracts the processing operation of the conversational sentence analyzed by morphological analysis in step S12. The extraction of the processing operation is not limited to the extraction of the processing operation itself, and may be the extraction of the morpheme including the wording corresponding to the processing operation.

Regarding the processing operations extracted in this way, as shown in FIGS. 6 and 7, the processing operations and the execution instructions refer to the processing operation table associated with each other, and a process of assigning a more relevant execution instruction is performed.

For example, from the morpheme decomposed into "Product name | A5-7853K | | Register |", the processing operation corresponds to "Register". Therefore, as shown in FIG. Refer to the processing operation table and search for the execution instruction corresponding to the processing operation. As a result, the execution instruction associated with "registration", in other words, the execution instruction highly related to "registration", is "DB (database) registration". It is shown in this processing operation table. Therefore, "DB registration" is assigned as the execution instruction.

For example, from the morpheme decomposed into "Taro Yamada | | This month | | Overtime | Time | | Tell me", the processing operation corresponds to "Tell me", so as shown in Fig. 7. , Refer to the processing operation table and search for the execution instruction corresponding to the processing operation. As a result, it is shown in this processing operation table that the execution instruction associated with "teach", in other words, the execution instruction highly related to "teach" is "DB (database) reference". Has been done. Therefore, "DB reference" is assigned as the execution instruction.

Next, the basic syntax of the program code is associated with each other based on the execution instruction assigned in this way and the intent determined in step S13.

In such a case, by referring to the code table stored in the storage unit 14, a highly relevant program is based on the execution instruction assigned as described above and the intent determined in step S13. Extract the basic syntax of the code.

For example, in the conversational sentence "A5-7853K, register", "DB (database) registration" is assigned as a highly relevant execution instruction as described above, and "register product name" is determined as an intent. Has been done. Refer to the processing operation table, and the basic syntax of the program code that is associated with both these execution instructions and intents, in other words, more relevant, is "INSERT INTO product master (product name) VALUES ({{ parame1}) ”is shown. Therefore, "INSERT INTO product master (product name) VALUES ({parame1})" is extracted as the basic syntax of the program code.

In addition, in the conversation "Tell me about Taro Yamada's overtime hours this month", "DB (database) reference" is assigned as a highly relevant execution instruction as described above, and "Reference overtime hours" is assigned as an intent. "Has been decided. Refer to the processing operation table, and the basic syntax of the program code that is linked to both these execution instructions and intents, in other words, more relevant, is "SELECT time FROM overtime data WHERE date = {param1}". It is shown that AND employee = {param2 ". Therefore, "SELECT time FROM overtime data WHERE date = {param1} AND employee = {param2}" is extracted as the basic syntax of the program code.

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 a noun or noun phrase that defines the target of the actual processing operation and each condition necessary for completing the processing operation is substituted. By doing so, the program code is completed. Therefore, in step S15, a processing operation of substituting a noun or a noun phrase that defines the target of the actual processing operation and each condition necessary for completing the processing operation is performed on the basic syntax of the extracted program code. Do.

In such a case, the result of the morphological analysis performed in step S12 is used to extract the target of the actual processing operation and the noun or noun phrase that defines each condition necessary for completing the processing operation.

For example, in "A5-7853K, register", "INSERT INTO product master (product name) VALUES ({parame1})" is extracted as the basic syntax, but the actual one to be filled in {parame1}. The product name is picked up from the morphologically analyzed statement. As a result, the program code can be completed by picking up "A5-7853K" as the product name and substituting it into the basic syntax.

Similarly, in "Tell me about Taro Yamada's overtime hours this month", "SELECT time FROM overtime data WHERE date = {param1} AND employee = {param2}" is extracted as the basic syntax, but the date {parame1 The program code can be completed by picking up "this month" in the place of} and "Taro Yamada" in the place of {param2} of the employee from the morphologically analyzed statement and substituting this into the basic syntax.

In the steps S11 to S15, the 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 directly executed. be able to. This means that when the user speaks the action he or 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.

The present invention is not limited to the above-described embodiment. The search for the execution instruction by referring to the processing operation table and the search for the program code using the code table may be performed by using machine learning by artificial intelligence.

When machine learning by artificial intelligence is used, for example, as shown in FIG. 8, it is premised that three or more levels of association between the processing operation and the execution instruction are set in advance. It is assumed that the input data is, for example, processing operations P01 to P03. For example, it is assumed that the processing operation P01 is "referenced", the processing operation P02 is "output", the processing operation P03 is "show", and the like. The processing operations P01 to P03 as such input data are linked to the execution instruction as output.

The processing operations are associated with each other through three or more levels of association with the execution instruction (for example, "DB reference", "open file", etc.) as the output solution. The processing operations are arranged on the left side via this degree of association, and each execution instruction is arranged on the right side via this degree of association. The degree of association indicates which execution instruction is highly relevant to the processing operations arranged on the left side. In other words, this degree of association is an index indicating which execution instruction is likely to be associated with each processing operation, and indicates the accuracy in selecting the most probable execution instruction from the processing operations. It is a thing. In the example of FIG. 8, 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 quality of the fish 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 price as an output.

Such three or more levels of association w13 to w19 shown in FIG. 8 are acquired in advance. In other words, in determining the actual search solution, the linkage shown in FIG. 8 is obtained by accumulating past data sets of which of the processing operation and the execution instruction was adopted and evaluated, and analyzing and analyzing these. Make up the degree.

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

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

Further, the degree of association shown in FIG. 8 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. 9, the processing operation is input as input data, the execution instruction is output as output data, at least one hidden layer is provided between the input node and the output node, and machine learning is performed. You may let it. 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 this degree of association exceeds a certain threshold value, the output may be selected.

Such a degree of association is what is called learned data in artificial intelligence. After creating such learned data, the execution instruction will be actually searched from the processing operation. In such a case, the processing operation extracted in step S12 is newly acquired. Based on the newly acquired processing operation, the execution instruction corresponding to this is searched. In such a case, the degree of association shown in FIG. 8 (Table 1) acquired in advance is referred to. For example, when the newly acquired processing operation is the same as or similar to P02, "open file" is associated with w15 and "printer output" is associated with association degree w16 via the association degree. .. In such a case, "Open file" 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 "printer output", 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 as long as it is based on the degree of association, it may be selected in any other priority.

FIG. 10 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. 10, a combination having an execution instruction and an intent as an input variable in the code table is input, and the basic syntax of the program code is output. Specifically, it is assumed that the input data is, for example, an execution instruction (“printer output”, “open file”, etc.) and intents P18 to P21. The intermediate node 61 is a combination of intents for the execution 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 of the execution instruction and the intent (intermediate node) is associated with each other through three or more levels of association with the basic syntax of the program code as this output solution. Execution instructions and intents are arranged on the left side through this degree of association, and the basic syntax is arranged on the right side through this degree of association. The degree of association indicates the degree of relevance to the basic syntax for the execution instructions and intents arranged on the left side. In other words, this degree of association is an indicator of what program code basic syntax each execution instruction and intent is likely to be associated with, and is the most probable program code from the execution instruction and intent. It shows the accuracy in selecting the basic syntax.

Such three or more levels of association w13 to w22 shown in FIG. 10 are acquired in advance. Accumulate past data to determine which of the execution instruction, the intent, and the basic syntax of the program code in that case was suitable for determining the actual search solution, and analyze and analyze these. Create a degree of association with.

This analysis and analysis may be performed by artificial intelligence. In such a case, for example, when the execution instruction is "DB reference" and the intent P20, the basic syntax of the program code is analyzed from the past data. When there are many cases of basic syntax A, the degree of association leading to this basic syntax A is set higher, and when there are many cases of basic syntax B and few cases of basic syntax A, the association leading to basic syntax B is set. Set the degree high and the degree of association leading to the basic syntax A 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 set to 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. 10 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. Other than that, the configuration related to artificial intelligence is the same as the description in FIG.

In the example of the degree of association shown in FIG. 10, the node 61b is a node of the combination of the intent P18 with respect to the execution instruction “DB reference”, the degree of association of the basic syntax C is w15, and the degree of association of the basic syntax E is w16. It has become. The node 61c is a node in which the reference analysis information P19 and P21 are combined with respect to the execution instruction "open file", and the degree of association of the basic syntax B is w17 and the degree of association of the basic syntax D is w18. ..

Such a 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 instruction and the intent are actually acquired. As the execution instruction, those obtained based on the degree of association shown in FIG. 8 may be used as input data. Further, as the intent, the one determined in step S13 is used.

Based on the newly acquired execution instruction and the intent in this way, the basic syntax of the optimum program code is searched. In such a case, the degree of association shown in FIG. 10 (Table 1) acquired in advance is referred to. For example, when the newly acquired execution instruction is "open a file" and the intent is P21, the node 61d is associated via the degree of association, and this node 61d is basically The syntax C is associated with w19, and the basic syntax D is associated with a 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 as long as it is based on the degree of association, it may be selected in any other priority.

In addition, Table 2 below shows examples of the degrees 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 association degrees w1 to w12 may all have the same value, and the weightings in the selection of the intermediate node 61 may all be the same.

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 (10)

Conversational sentence reception means for accepting conversational sentences and
An execution instruction assigning means that assigns highly relevant execution instructions to the processing operations extracted from the conversation sentence received by the conversation sentence receiving means by referring to the processing operation table in which the processing operation and the execution instruction are associated with each other.
An intent determination means for determining an intent having an action name that specifies a processing operation included in the conversation sentence received by the conversation sentence reception means,
Refer to the code table to which the basic syntax of the program code for the combination of the execution instruction and the intent is associated, and based on the execution instruction assigned by the execution instruction assigning means and the intent determined by the intent determining means. Equipped with a code extraction means to extract the basic syntax of highly relevant program code ,
The execution instruction assigning means is a program code automatic generation device, characterized in that it refers to the processing operation table associated with the processing operation and the execution instruction with three or more levels of association . The execution instruction assigning means uses the degree of association corresponding to the weighting coefficient of each output of the node of the neural network in artificial intelligence.
The program code automatic generation device according to claim 1. The above code extraction means refers to a code table in which a combination having an execution instruction and an intent and the basic syntax of the program code for the combination are associated with each other with three or more levels of association.
The program code automatic generation device according to claim 1 or 2. Conversational sentence reception means for accepting conversational sentences and
An execution instruction assigning means that assigns highly relevant execution instructions to the processing operations extracted from the conversation sentence received by the conversation sentence receiving means by referring to the processing operation table in which the processing operation and the execution instruction are associated with each other.
An intent determination means for determining an intent having an action name that specifies a processing operation included in the conversation sentence received by the conversation sentence reception means,
Refer to the code table to which the basic syntax of the program code for the combination of the execution instruction and the intent is associated, and based on the execution instruction assigned by the execution instruction assigning means and the intent determined by the intent determining means. Equipped with a code extraction means to extract the basic syntax of highly relevant program code,
The above code extraction means is characterized in that it refers to a code table in which a combination having an execution instruction and an intent and the basic syntax of the program code for the combination are associated with each other with three or more levels of association. Help program code automatic generation system. The code extraction means uses the degree of association corresponding to the weighting coefficient of each output of the node of the neural network in artificial intelligence.
The program code automatic generation device according to claim 3 or 4. A code generating means for generating a program code by substituting a noun or a noun phrase extracted from a conversation sentence accepted by the conversation sentence receiving means into the basic syntax of the program code extracted by the code extracting means is provided.
The program code automatic generation device according to any one of claims 1 to 5. Conversational sentence reception step to accept conversational sentences and
An execution instruction assignment step that assigns highly relevant execution instructions to the processing operations extracted from the conversation sentence received in the above conversation sentence reception step by referring to the processing operation table in which the processing operation and the execution instruction are related to each other, and
An intent determination step for determining an intent having an action name that specifies a processing operation corresponding to the conversation sentence received in the above conversation sentence reception step,
Refer to the code table to which the basic syntax of the program code for the combination of the execution instruction and the intent is associated, and based on the execution instruction assigned in the execution instruction assignment step and the intent determined in the intent determination step. Have your computer perform a code extraction step to extract the basic syntax of the relevant program code ,
A program code automatic generation program, characterized in that , in the execution instruction assignment step, the processing operation table associated with the processing operation and the execution instruction is referred to by three or more stages of association . In the above code extraction step, refer to the code table in which the combination having the execution instruction and the intent and the basic syntax of the program code for the combination are associated with each other with three or more levels of association.
7. The program code automatic generation program according to claim 7. Conversational sentence reception step to accept conversational sentences and
An execution instruction assignment step that assigns highly relevant execution instructions to the processing operations extracted from the conversation sentence received in the above conversation sentence reception step by referring to the processing operation table in which the processing operation and the execution instruction are related to each other, and
An intent determination step for determining an intent having an action name that specifies a processing operation corresponding to the conversation sentence received in the above conversation sentence reception step,
Refer to the code table to which the basic syntax of the program code for the combination of the execution instruction and the intent is associated, and based on the execution instruction assigned in the execution instruction assignment step and the intent determined in the intent determination step. Have your computer perform a code extraction step to extract the basic syntax of the relevant program code,
In the above code extraction step, refer to the code table in which the combination having the execution instruction and the intent and the basic syntax of the program code for the combination are associated with each other with three or more levels of association.
A program code automatic generation program characterized by. Having a code generation step for generating a program code by substituting a noun or a noun phrase extracted from the conversation sentence received in the conversation sentence reception step into the basic syntax of the program code extracted in the code extraction step.
The program code automatic generation program according to any one of claims 7 to 9, wherein the program code is automatically generated.

Images