JP7126808B2 - Information processing device and program for information processing device - Google Patents

Description

The present invention relates to an information processing device and a program for the information processing device for analyzing the content of a document and performing predetermined processing.

In recent years, an information processing device capable of autonomously performing work (hereinafter sometimes referred to as having artificial intelligence) has been developed for the purpose of substituting for some of the work performed by humans. there is
As an information processing apparatus having such artificial intelligence, for example, Patent Document 1 discloses an apparatus equipped with a personal assistant for autonomously processing (outputting) tasks instructed (inputted) by a user. . In the information processing apparatus disclosed in Patent Document 1, when the personal assistant does not know the processing method of the instructed task, the personal assistant requests the user to add the processing method of the task to the knowledge base. , the business can be processed based on the added processing method.
As an example of the expected use of information processing devices that can work autonomously, for example, in the field of accounting, receipts can be autonomously sorted by expense based on the information written on the receipts. Also, in the design field, it is conceivable to check whether there are any omissions in the contents described in the specifications, and if there are any omissions, complement them and complete the specifications without omissions. be done.

Japanese Patent Publication No. 2016-509301

However, although the technology related to artificial intelligence has developed in recent years, the reality is that it is still not possible to completely replace all the work performed by humans. Therefore, there is a possibility of performing erroneous processing that cannot be caused by humans.

For example, an information processing apparatus equipped with artificial intelligence, such as that disclosed in Patent Document 1, does not include a processing method for a task instructed by a user in its knowledge base, so that it can determine that the task can be processed. The question is repeatedly asked to the user until the question is satisfied, and finally the information processing apparatus itself decides to process the work. Therefore, when processing a difficult task, there is a possibility that an erroneous process is actually performed.

In addition, an information processing apparatus equipped with advanced artificial intelligence intended to take over all of the work performed by humans has a complicated configuration, resulting in high manufacturing costs. Furthermore, since devices equipped with artificial intelligence attempt to take over all of the work performed by humans, when processing difficult tasks, processing may rather take a long time and productivity may decline.

The present invention has been made in view of such problems, and it is possible to reduce the possibility of erroneous processing even when processing difficult tasks, and to shorten the time required to process the tasks. It is an object of the present invention to provide an information processing apparatus which can be manufactured with a simple structure at low cost.

An information processing apparatus according to an embodiment of the present invention is an information processing apparatus that is connected to a plurality of client terminals, analyzes the contents of documents indicated by document data transmitted from the plurality of client terminals, and performs predetermined processing. a document data receiving unit that receives the document data from a predetermined client terminal; and extracts processing data, which is data indicating information used for executing the processing, from the document data; A document data analysis unit that identifies an information item indicated by data for use and generates processing information item data that is data indicating the identified item, and data indicating an information item necessary for executing the processing A storage unit that stores certain necessary information item data, and the necessary information item data and the processing information item data are compared, and lacking information that is an information item lacking in the document data for the processing. a specifying unit for specifying an item; and a question data generating unit for generating question data for specifying information related to the missing information item and transmitting the question data to the predetermined client terminal or other client terminal, The specifying unit analyzes the reply data from the client terminal that received the question data, and if there is information still lacking for the processing in the reply information indicated by the reply data, the item of the information. The additional missing information item is specified, and the question data generation unit generates additional question data for specifying information related to the additional missing information item each time the additional missing information item is specified by the specifying unit. When the total number of transmissions of the question data and the additional question data reaches a predetermined number of times while the document is sent to the predetermined client terminal or other client terminals, it indicates that the document cannot be processed. Data is transmitted to the predetermined client terminal or other client terminals.

With such a configuration, if it is difficult to automatically process the document, the user can assist the user without processing the final document. can be reduced. In addition, since it is not necessary to substitute all the work for document processing performed by humans, there is no need to provide advanced artificial intelligence, the configuration of the device can be simplified, and the device can be manufactured at low cost. can. Furthermore, when it is difficult to process documents automatically, it is possible to reduce the number of times data is sent and received between client terminals, thereby shortening the time required to finally process documents. and increase user productivity.

The information processing apparatus according to the embodiment of the present invention performs the predetermined processing on the document based on the processing data when the specifying unit does not specify the missing information item and the additional missing information item. It is preferable to further have an execution unit.
With such a configuration, the document is automatically processed when it can be processed, so that the document can be processed efficiently.

The processing is processing selected from a plurality of types of processing, and the storage unit stores necessary information item data, which is data indicating information items necessary for executing each of the plurality of types of processing. preferably stored.
With such a configuration, a single information processing apparatus can handle different types of documents.

The information processing apparatus according to the embodiment of the present invention further includes a processing selection unit that automatically selects the predetermined processing from the plurality of types of processing based on the document data received by the document data reception unit. is preferred.
With such a mode, different types of documents can be processed automatically, so that the documents can be processed efficiently.

When the total number of times of transmission of the question data and the additional question data reaches a predetermined number of times, the question data generation unit transmits processing request data indicating a request to process the document to the predetermined client. It is preferably sent to a terminal or other client terminal.
In such a mode, the document is finally processed more reliably by the user himself/herself, so the possibility of erroneous processing can be further reduced, and the processing time of the document can be further shortened.

As a specific embodiment of the document data analysis unit, it is preferable to analyze the document data by an analysis method selected from lexical analysis, morphological analysis and syntactic analysis.

As described above, the information processing apparatus of the present invention receives additional data by asking the user a question when the data received from the client terminal is insufficient to process the document. If the number of times has reached a predetermined number, it will stop processing the document and notify the user that the document cannot be processed. That is, the information processing apparatus of the present invention does not substitute for all the work performed by humans, and when document processing is difficult, human assistance can be received for the final processing of the document. Therefore, according to the information processing apparatus of the present invention, it is possible to reduce the possibility of performing erroneous processing. In addition, since it is not necessary to substitute all the work for document processing performed by humans, there is no need to provide advanced artificial intelligence, the configuration can be simplified, and manufacturing can be performed at low cost. Furthermore, if the document processing is difficult, human assistance can be received for the final processing of the document, so the time required to finally process the document can be shortened. Work productivity can be increased.

FIG. 1 is a conceptual diagram showing the configuration of an information processing system 100 using an information processing device 110 according to an embodiment of the present invention. FIG. 2 is a schematic device configuration diagram showing the internal device configuration of the information processing apparatus 110 according to the embodiment. FIG. 3 is a functional block diagram of the information processing device 110 according to the embodiment. FIG. 4 is a flow chart showing the operation of the information processing device 110 according to the embodiment. FIG. 5 is a conceptual diagram showing an example of functions of the document data analysis section 2 of the information processing apparatus 110 according to the embodiment. FIG. 6 is a conceptual diagram showing an example of functions of the document data receiving section 1, the document data analyzing section 2, the identifying section 4, and the question data generating section 5 of the information processing apparatus 110 according to the embodiment.

An embodiment of the present invention will be described below based on the drawings. The information processing system and information processing apparatus described below are for embodying the technical idea of the present invention, and unless there is a specific description, the present invention is not limited to the following.

The information processing system 100 of the present embodiment analyzes the contents of receipts, for example, and performs a predetermined process, that is, sorting the receipts by expense, instead of a human. This information processing system 100 will be described. As shown in FIG. 1, an information processing system 100 includes an information processing device 110 as a server, and a plurality of client terminals 120 communicably connected to the server via a network X such as the Internet. A "receipt" is a "document" in the claims.

First, the client terminal 120 will be explained. The client terminal 120 is a so-called personal computer used by a user, and has a CPU, a storage device such as a volatile memory, an input unit such as a mouse and a keyboard, an input/output interface for connecting to a display, and the like. The user can input the contents of the receipt as text data to the client terminal 120 via the input unit, and can send this text data to the server by e-mail, for example. The content of the receipt is, for example, the date of issue of the receipt, the name of the company that receives the receipt, the amount of money, and the items purchased. The "text data" referred to here is the "document data" referred to in the scope of claims.
Next, the device configuration and functions of the information processing apparatus 110 of this embodiment, which is a server, will be described.

The information processing apparatus 110 analyzes the document data transmitted from the client terminal 120 and performs predetermined processing. The information processing apparatus 110 may physically consist of a single computer, or may consist of a plurality of computers connected via a network as shown in FIG.
FIG. 2 is a schematic device configuration diagram showing the internal device configuration of the information processing apparatus 110 of this embodiment. As shown in FIG. 2, the information processing apparatus 110 of this embodiment includes a CPU 10, a storage device 20 such as a volatile memory or an HDD, an input unit 40 such as a mouse and a keyboard, an input/output interface 30 for connecting to a display 50, and the like. have By installing a program for the information processing device 110 in the storage device 20 and causing the CPU 10 and peripheral devices to work together based on the program, the information processing device 110 can be configured as shown in the functional block diagram of FIG. , a document data receiving unit 1, a document data analyzing unit 2, a storing unit 3, a specifying unit 4, and a question data generating unit 5.
Details of each part will be described with reference to FIG.

(1) Document data receiving unit 1
The document data receiving section 1 receives the document data from a predetermined client terminal 120 . After the question data generating unit 5, which will be described later, generates question data indicating a question for specifying information related to the missing information item and transmits the question data to the client terminal 120, the document data receiving unit 1 receives the following from the client terminal 120: It receives text data (referring to "reply data" in the scope of claims) including information related to missing information items.

(2) Document data analysis unit 2
The document data analysis unit 2 extracts processing data, which is data indicating information used for executing processing, from the document data received by the document data reception unit 1 . The information used for executing the process is, in this embodiment, specific information necessary for sorting the receipts, such as the date of issue, the name of the company that receives the receipt, and the amount of money. , purchased items, etc.
Further, the document data analysis unit 2 specifies information items indicated by the extracted processing data, and generates processing information item data, which is data indicating the specified items. The information items (processing information items) indicated by the extracted processing data are, in this embodiment, for example, if the information indicated by the extracted processing data is "5000 yen" and "August 1", "Amount" and "Issue Date".

Further, when the document data receiving section 1 receives the return data, the document data analysis section 2 extracts additional processing data indicating information used for executing processing from the return data. Then, the item of information indicated by the extracted data for additional processing is specified, and additional processing information item data, which is data indicating the specified item, is generated.

Various known methods may be used to extract processing data from the document data and generate processing information item data (collectively referred to as "analysis of document data"). FIG. 5 shows an example of analysis of document data by the document data analysis unit 2. As shown in FIG. As shown in FIG. 5, the document data to be received may be either standard text data or non-standard text data. The document data analysis unit 2 can analyze the document data by an appropriate analysis method selected from lexical analysis, morphological analysis and syntactic analysis. The same applies to extraction of data for additional processing from reply data and creation of additional processing information item data.

(3) Storage unit 3
The storage unit 3 is set in a predetermined area of the storage device 20, and stores necessary information item data, which is data indicating items of information necessary for executing processing. In this embodiment, the items of information necessary for executing the process are the items of information necessary for executing the sorting of receipts. Items such as the name of the company that receives the letter, the amount of money, and the items purchased. Such necessary information items can be arbitrarily set by the user according to the type of document to be processed and the content of the process to be performed.

(4) Identification unit 4
The identification unit 4 compares the necessary information item data stored in the storage unit 3 with the processing information item data received from the document data analysis unit 2, and executes It specifies missing information items, which are items of information that are missing for the process to be attempted. By specifying the missing information item by the specifying unit 4, it is possible to specify which information item is missing in the document indicated by the received document data. In this embodiment, the missing information items are, for example, the necessary information items such as "credit", "date of issue of receipt", "name of company receiving receipt", "amount", and "purchased item". , if the processing information items are "credit", "date of issue of receipt", "name of company receiving receipt" and "price", then it is "purchased item".

The identification unit 4 further analyzes the reply data, and if there is information still lacking for processing in the reply information indicated by the reply data, additional missing information that is the item of the missing information It identifies the item.
Specifically, the additional processing information item data is fetched from the document data receiving unit 1, and the processing information item data and the additional processing information item data are compared with the necessary information item data for processing to be executed. Identify additional missing information items that are items of information that are still missing in the Then, additional missing information item data, which is data indicating the specified additional missing information item, is generated.
In the present embodiment, additional missing information items are, for example, necessary information items such as "credit", "date of issue of receipt", "name of company receiving receipt", "amount", and "purchase item". Yes, and if the processing information item and the additional processing information item are "credit", "date of issue of receipt", "name of company receiving receipt" and "price", then it is "purchased item".

The identifying unit 4 also has a learning function of learning and updating the relationship among information indicated by the processing data, the missing information items, and information indicated by reply data described later, information indicated by the processing data, It has an analogy function for analogizing the information indicated by the missing information item based on the relationships learned by the learning function.
For example, it is assumed that the information indicated by the processing data includes that the item to be purchased is "personal computer" and the number of units to be purchased is "1000", and the specified missing information item is "classification of rental". After that, after transmitting question data for identifying the credit classification, it is assumed that the reply data from the client terminal includes the information that "the credit classification is the credit side." In this case, if the information indicated by the processing data includes that the item to be purchased is "personal computer" and the number of units to be purchased is "1000 units", the identification unit 4 classifies the loan as "credit". Learn that there is. From the next time onwards, the information indicated by the processing data includes that the item to be purchased is "personal computer" and the number of units to be purchased is "1000", and the specified missing information item is "classification of rental". In this case, the specifying unit 4 analogizes the “classification of credit” to “credit” and complements the information indicated by the missing information item.
Since the identification unit 4 has the learning function and the analogy function, when there is a missing information item, information related to the missing information item is obtained without sending question data from the question data generation unit 5 to the client terminal 120, which will be described later. can be specified.

(5) Question data generator 5
Based on the missing information item data received from the specifying unit 4, the question data generating unit 5 generates question data indicating a direct or indirect question for specifying information related to the missing information item, The data is sent to the client terminal 120 by e-mail, for example. This question data may be sent to the client terminal that sent the text data indicating the receipt information (referring to the "predetermined client terminal" in the claims), or the user information stored in advance in the memory. , the client terminal 120 ("other client terminal). As a result, when there is insufficient information for executing processing in the contents of the document, the missing information can be retrieved from any one of the plurality of client terminals 120 connected via the network, Missing information in the document can be automatically supplemented, and the possibility of properly processing the document can be increased.

In this embodiment, for example, when the missing information item specified by the specifying unit 4 is "item to be purchased", the question data generating unit 5 presents a question for specifically specifying the content of "item to be purchased". Generate question data. For example, question data indicating a direct question, "What are the items to purchase?" In addition, it is possible to transmit question data indicating an indirect question such as "What is the purchased item used for?". Further, when the information related to the missing information item can be inferred by the analogy function of the specifying unit 4, question data indicating whether or not the inferred missing information item is correct is generated and transmitted to the client terminal 120. can be done.

The question data generating unit 5 further creates additional question data for specifying information related to the additional missing information item each time the specifying unit 4 specifies the additional missing information item, and asks which of the plurality of client terminals 120 to send to. As a result, it is possible to repeatedly retrieve information that is lacking in order to process the content of the document from any one of the plurality of client terminals 120 . The client terminal to which the additional question data is sent may be the same terminal as the client terminal to which the question data is sent, or may be a different terminal. That is, additional question data may be repeatedly transmitted to a client terminal used by a specific user by changing the question content. Further, additional question data indicating the same question content may be transmitted to client terminals used by different users.

The question data generation unit 5 can count the total number of transmissions of the question data and the additional question data to the client terminal 120, and determines whether or not to further transmit the additional question data according to the number of transmissions. It is. When the number of transmissions reaches a predetermined value (an arbitrary integer equal to or greater than 1. For example, 3 times), and the identifying unit 4 still identifies the missing information item, then additional question data is transmitted to one of the plurality of client terminals 120, which indicates that the receipt cannot be processed. The client terminal 120, which is the destination of the unprocessable data, may be the client terminal that sent the document data indicating the receipt information, or a client terminal used by a user who is highly related to the user using the client terminal. 120 is also acceptable.

As a method for generating the question data, additional question data, and unprocessable data described above, for example, known natural language processing technology can be used.

An example of functions of the document data receiving unit 1, the document data analyzing unit 2, the specifying unit 4, and the question data generating unit 5 will be described with reference to FIG.
In FIG. 6, an area (a) surrounded by a dotted line is an example showing functions of the document data receiving section 2 and the document data analyzing section 3. As shown in FIG. A region (b) surrounded by a dotted line is an example showing the function of the specifying unit 4 . A region (c) surrounded by a dotted line is an example showing the function of the question data generating section 5 .

In area (a), the document data receiving section 1 receives document data, and the document data analysis section 2 extracts processing data from the document data and generates processing information item data.

In area (b), the identification unit 4 compares the necessary information item data and the processing information item data, and identifies missing information items, which are information items lacking for processing in the document data. Specifically, in the example shown in FIG. 6, "A to F and 1 to 0" indicate necessary information items, and among them, "A to C, E, G to I, 1 to 4, 6, 7, 9 and 0" indicate processing information items. In the example shown in FIG. 6, by referring to the "past records" and "reference information", the information about the information items "D, J and 5" is inferred, and the information items "F and 8" are regarded as missing information items. have identified.

In area (c), the question data generating unit 5 generates question data for specifying the information related to the missing information item “F and 8” specified by the specifying unit 4, and sends it to the client terminal by e-mail. Send. After that, the user using the client terminal that received the e-mail enters the information related to the missing information item as text data (that is, reply data) into the client terminal, and sends the document data receiving part in the area (a) by e-mail. Send to 1.
On the other hand, when the total number of transmissions of the question data and the cumulative question data reaches a predetermined value "x+1", process-impossible data indicating that the receipt cannot be processed is sent to the client terminal by e-mail.

<Operation of Information Processing Device 110>
Next, the operation of the information processing apparatus 110 according to the present embodiment up to processing a receipt will be described with reference to the flowchart of FIG.

First, the document data receiving section 1 receives text data indicating the contents of a receipt from a predetermined client terminal 120 (step S1).

The document data receiving section 1 transmits text data received from a predetermined client terminal 120 to the document data analyzing section 2 . The document data analysis unit 2 extracts processing data, which is data indicating information used for sorting receipts, from the text data, and specifies the items of information indicated by the processing data. Processing information item data, which is data indicating the item selected, is generated (step S2).

The document data analysis unit 2 transmits the generated processing information item data to the identification unit 4 . The identification unit 4 compares the necessary information item data stored in the storage unit 3 with the processing information item data received from the document data analysis unit 2, and determines whether the text data received from the predetermined client terminal 120 is receipt Missing information items, which are items of information missing for sorting the books, are identified (step S3).

When the identifying unit 4 identifies the missing information item, it generates missing information item data indicating the missing information item and transmits it to the question data generating unit 5 . The question data generation unit 5 counts the total number of transmissions of the previous question data and the additional question data, and the number of transmissions reaches a set predetermined value (indicated as n times in FIG. 4, where n is set by the user). Any integer equal to or greater than 1.) is determined (step S4). If the number of transmissions is less than a predetermined value, question data or additional question data is generated and sent to one of the plurality of client terminals 120, for example, by e-mail (step S5). The user of the client terminal 120 who has received the question data or the additional question data inputs the information related to the missing information item into the client terminal 120 as text data (i.e., "reply data"), and sends it to the document data receiving unit, for example, by e-mail. Send to 1. After that, the processes of steps S1 to S4 are repeatedly executed.

When the specifying unit 4 specifies missing information items, and when the number of transmissions of the question data and the additional question data from the question data generating unit 5 has reached a predetermined value, the receipts are sorted. A message to the effect that it cannot be executed is output (or transmitted) to a plurality of client terminals 120 (step S6).

<Effects of this embodiment>
As described above, when the document data received from the client terminal 120 is insufficient for processing, the information processing apparatus 110 of the present embodiment uses question data for specifying information related to missing information items. is generated and transmitted to the client terminal 120, and on the other hand, when the number of transmissions of the question data reaches a predetermined number of times, a message indicating that the document cannot be processed is provided.

The information processing apparatus 110 of the present embodiment is provided with such a question data generation unit 5, so that when it is difficult to automatically process a document, the final document is not processed, You can get help from users who know how to process documents. Therefore, it is possible to reduce the possibility of erroneously processing documents that are difficult to process, while increasing the possibility of automatically processing documents by transmitting question data.

Furthermore, since the information processing apparatus 110 of the present embodiment does not need to substitute all the work for document processing performed by humans, it does not need to be equipped with advanced artificial intelligence, and the configuration can be simplified. It can be manufactured at low cost. Furthermore, when it is difficult to automatically process a document, the number of times data is sent and received between the client terminal 120 and the information processing apparatus 110 can be reduced, so that the document can be finally processed. It is possible to shorten the time required to complete and improve the productivity of the user's work.

<Preferred embodiment>
The information processing apparatus according to the present invention is not limited to the above-described embodiments.
Preferred embodiments of the information processing apparatus according to the present invention will be described below. Unless otherwise specified, the configuration may be the same as that of the information processing apparatus 110 according to the above-described embodiment.

In a preferred embodiment, when the specifying unit 4 does not specify the missing information items and the missing additional information items, the information processing apparatus 110 performs the processing based on the data for processing and the data for additional processing extracted by the document data analysis unit 2. It may further include a processing execution unit 6 that performs predetermined processing on the document. By having the process execution unit 6, the information processing apparatus 110 automatically processes the document when it can process the document, so that the document can be processed efficiently.

The operation of the information processing device 110 when the information processing device 110 has the process execution unit 6 will be described with reference to FIG. In the information processing apparatus 110 according to such an embodiment, when the specifying unit 4 does not specify the missing information item in step S3, the specifying unit 4 transmits the processing data and the additional processing data to the processing execution unit 6. , the processing execution unit 6 processes the document (step S7).

In another preferred embodiment, the predetermined process performed by the information processing device 110 is a process selected from a plurality of types of processes, and the storage unit 3 stores necessary information for executing each of the plurality of types of processes. It may store necessary information item data, which is data indicating items of information. With such a form, a single information processing apparatus 110 can handle different types of documents.
In such an embodiment, the user may arbitrarily select and set the predetermined processing to be performed on the document. Further, the information processing apparatus 110 further has a processing selection unit that estimates and automatically selects processing to be performed on the document based on the received document data, and the processing selection unit automatically selects the processing. may

In another preferred embodiment, the question data generator 5, when the total number of transmissions of the question data and the additional question data reaches a predetermined number of times, instead of transmitting the unprocessable data, or Along with the transmission of , processing request data indicating a request to process the document may be transmitted to a predetermined client terminal or other client terminal 120 . As a result, when the processing of the document is difficult and the document cannot be processed by the information processing device 110, the document is processed more reliably by the user himself/herself, thereby further reducing the possibility of erroneous processing. At the same time, the document processing time can be further shortened.

In another preferred embodiment, the document data receiving section 1 preferably has an OCR (Optical Character Recognition) function for converting image data into text data. In this form, when the document data transmitted from the client terminal 120 is image data of a receipt photographed by the user or the like, the document data receiving unit 1 converts the image data into an OCR (Optical It can be automatically converted into text data by the Character Recognition (optical character recognition) function.

In addition, various modifications and combinations of the embodiments may be made as long as they do not contradict the gist of the present invention.

Reference Signs List 1: document data receiving unit 2: document data analysis unit 3: storage unit 4: identification unit 5: question data generation unit 6: processing execution unit 10: CPU
20 ... storage device 30 ... input/output interface 40 ... input unit 50 ... display 100 ... information processing system 110 ... information processing device 120 ... client terminal X ... network

Claims (6)

An information processing device that is connected to a plurality of client terminals, analyzes the content of a document indicated by document data transmitted from the plurality of client terminals, and performs predetermined processing,
a document data receiving unit that receives the document data from a predetermined client terminal;
Data for processing, which is data indicating information used for executing the processing, is extracted from the document data, an item of information indicated by the data for processing is specified, and data indicating the specified item. a document data analysis unit that generates processing information item data;
a storage unit storing necessary information item data, which is data indicating items of information necessary for executing the processing;
an identifying unit that compares the necessary information item data and the processing information item data and identifies missing information items, which are information items lacking for the processing in the document data;
a question data generation unit that generates question data for specifying information related to the missing information item and transmits the question data to the predetermined client terminal or other client terminals;
The specifying unit analyzes the reply data from the client terminal that received the question data, and if there is information still lacking for the processing in the reply information indicated by the reply data, the item of the information identifies certain additional missing information items,
The question data generation unit
Each time an additional missing information item is specified by the specifying unit, additional question data for specifying information related to the additional missing information item is generated and transmitted to the predetermined client terminal or other client terminal,
when the total number of transmissions of the question data and the additional question data reaches a predetermined number of times, transmitting unprocessable data indicating that the document cannot be processed to the predetermined client terminal or other client terminals; An information processing apparatus, characterized in that it transmits processing request data indicating a request to process the document by itself to the predetermined client terminal or other client terminals. 2. The method according to claim 1, further comprising a processing execution unit that performs the predetermined processing on the document based on the processing data when the specifying unit does not specify the missing information item and the additional missing information item. Information processing equipment. The processing is processing selected from a plurality of types of processing, and the storage unit stores necessary information item data, which is data indicating information items necessary for executing each of the plurality of types of processing. 3. The information processing apparatus according to claim 1, wherein the information processing apparatus stores. 4. The information processing apparatus according to claim 3, further comprising a processing selection unit that automatically selects the predetermined processing from the plurality of types of processing based on the document data received by the document data reception unit. 5. The information processing apparatus according to claim 1, wherein said document data analysis unit analyzes said document data by an analysis method selected from lexical analysis, morphological analysis and syntactic analysis. A program for an information processing device that is connected to a plurality of client terminals, analyzes the content of a document indicated by document data transmitted from the plurality of client terminals, and performs a predetermined process, the program for executing the process. An information processing device having a storage unit storing necessary information item data, which is data indicating items of information necessary for
a document data receiving unit that receives the document data from a predetermined client terminal;
Data for processing, which is data indicating information used for executing the processing, is extracted from the document data, an item of information indicated by the data for processing is specified, and data indicating the specified item. a document data analysis unit that generates processing information item data ;
an identifying unit that compares the necessary information item data and the processing information item data and identifies missing information items, which are information items lacking for the processing in the document data;
A program for functioning as a question data generation unit that generates question data for specifying information related to the missing information item and transmits the question data to the predetermined client terminal or other client terminals,
The specifying unit analyzes the reply data from the client terminal that received the question data, and if there is information still lacking for the processing in the reply information indicated by the reply data, the item of the information identifies certain additional missing information items,
The question data generation unit
Each time an additional missing information item is specified by the specifying unit, additional question data for specifying information related to the additional missing information item is generated and transmitted to the predetermined client terminal or other client terminal,
when the total number of transmissions of the question data and the additional question data reaches a predetermined number of times, transmitting unprocessable data indicating that the document cannot be processed to the predetermined client terminal or another client terminal; A program for an information processing apparatus, characterized by transmitting processing request data indicating a request to process the document by itself to the predetermined client terminal or other client terminals.

Images