JP2005215726A - Information presenting system for speaker, and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To enable an information processor to extract predetermined words from among the uttered voice of a human being, and to present information by using voice recognition to the human being who utters voice. <P>SOLUTION: This information presenting system is provided with a voice input means 7 for inputting the uttered voice of a speaker, an action data storage means 10 for storing conditions corresponding to predetermined keywords and action information related with those conditions by associating them with each other and an information presentation processing means 9 for presenting information by using voice recognition. This information presentation processing means 9 performs the voice recognition processing of the uttered voice, and detects keywords stored in the action data storing means 10 from the processing result, and decides whether or not the detected keywords satisfy the conditions, and extracts the corresponding action information from the action data storing means 10 when the conditions are satisfied, and executes processing based on the extracted action information. <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

  The present invention recognizes an input human natural speech, and an information processing device extracts a predetermined word from the speech and performs speech recognition for presenting information to the human to speak. The present invention relates to the use of information presentation systems and programs.

Japanese Patent Laid-Open No. 2003-208439 (hereinafter referred to as “conventional invention”) is an invention that recognizes human natural speech, extracts keywords from the speech, and provides information corresponding to the keywords to humans. ).
This conventional invention is intended to be used in a place such as a call center where an operator responds to an inquiry via a telephone from a user. A word that is assumed to be used by the operator during conversation response is extracted in advance, and when this word appears in the conversation between the user and the operator, it is associated with information that can be one or more response information corresponding to the word. Store in the operator terminal. The software installed on the operator terminal performs voice recognition of the conversation between the user and the operator, matches the recognition result with the extracted word, and information that can be one or more response information depending on the degree of matching Is extracted and displayed on the screen of the operator terminal. The operator can use the displayed information itself as information in response to the user, or can obtain appropriate information by specifying one of the displayed information. With this conventional invention, the operator can quickly and efficiently respond to questions from the user.
JP 2003-208439 A

  The basic concept of the present invention is in common with the conventional invention described above. On top of that, improving the information presentation service to users by improving the quality of information provided to speakers, ensuring prompt presentation of information to speakers, and improving the accuracy of voice recognition The task was to plan.

  1st invention is the information presentation system with respect to a speaker. The correspondence of the keyword and action which matched the voice input means which inputs the speech voice of a speaker, the condition corresponding to a predetermined keyword, and action information relevant to it Action data storage means for storing data, and information presentation processing means for presenting information using voice recognition, the information presentation processing means performs voice recognition processing of the uttered voice of the speaker, and from the result of this processing , Detecting a keyword stored in the action data storage means, determining whether the detected keyword satisfies the condition, and extracting the corresponding action information from the action data storage means if the condition is satisfied. The processing based on the extracted action information is executed.

  When a predetermined keyword is detected from the speech voice of the speaker, the system takes an action of presenting information to the speaker. This action may be to display the contents of the read file, to execute a program, or to browse an Internet site. Information that identifies the file or site that is the basis of this action is “action information”.

  A second invention is characterized in that, in the first invention, an output means that can be viewed by a speaker is provided, and the processing based on the extracted action information causes the output means to display information.

  According to a third invention, in the first or second invention, the information presentation processing means converts the input voice into text using a dictation process, and the text is stored in the action data storage means. It is characterized by detecting a keyword.

  According to a fourth invention, in the third invention, there is provided user dictionary storage means for storing a user word for storing a word in association with its notation and reading, and the user dictionary storage is stored in the text obtained by the dictation process. If the user word stored in the means is included, information indicating the head position of the user word in the text is output, and the information presentation processing means can search the keyword only from the head position of the user word. The search is performed.

  A “user word” is a word that serves as a basis for detecting a keyword registered in the action data storage means. A keyword that is not registered as a “user word” at least at the beginning is not detected because it is unclear from which position in the text it can be searched.

  A fifth invention is characterized in that, in the fourth invention, there is provided user word registration processing means for storing a keyword to be stored in the action data storage means as a user word in the user dictionary storage means.

  According to a sixth invention, in any one of the first to fifth inventions, the information presentation processing means is configured such that the action information associated with the condition corresponding to the keyword in the action data storage means is the type of file. If the file name is information specifying the file name, the file is opened, processing corresponding to the type is performed, and if the URL is a URL of a site on the Internet, a request is made to browse the Web page of the site. .

  A seventh invention is characterized in that, in the sixth invention, when the file is opened and the process according to the type is a program file, the speech recognition result is used as an argument of the program. And

  In an eighth invention according to any one of the first to seventh inventions, the voice input means inputs the voice of the conversation between the responder and the questioner corresponding to the question via the telephone line, and the conversation. Is delivered to the information presentation processing means.

  In a ninth aspect based on the eighth aspect, the voice input means includes a dedicated microphone that collects only the voice spoken by the responder corresponding to the question via the telephone line, and the voice input to the microphone is It is characterized by being input data of the information presentation processing means without going through a telephone line.

  According to a tenth aspect of the present invention, in a computer program, when the computer program is read and executed by the computer, the computer is operated as an information presentation system that presents information corresponding to a keyword detected by speech recognition from a speaker's speech. A computer program for registering action data in the action data storage means in which action data in which a condition corresponding to a predetermined keyword is associated with file information related to the computer is input to an input voice of a speaker Means for performing speech recognition processing, detecting a keyword stored in the action data storage means from the result of speech recognition, determining whether the detected keyword satisfies the condition, and responding if the condition is satisfied File information from the action data storage means Out, means for executing the processing based on the extracted file information, characterized in that to function as means for outputting the execution result.

  According to the present invention, the system can recognize a continuous utterance voice and present information suitable for the detected keyword to the speaker. If a call center responder who handles telephone inquiries is a user of the system of the present invention, the system presents information in a timely manner as the utterance progresses.・ Can respond accurately.

  In addition, the present invention is characterized in that it can cope with not only a single keyword but also a plurality of keywords. The logical value is extracted from the logical relationship (and, or, not) between a plurality of keywords. That is, since the sentence itself is extracted, not just a list of words, it is possible to provide higher quality information.

  Furthermore, according to the present invention, keyword candidates are registered as user words, and the keywords are searched from the head position of the user words in the text of the dictation processing result, so that the keywords can be detected quickly. As a result, information can be presented in a timely manner as the speaker's natural utterance progresses. Moreover, since keyword registration and user word registration can be performed with a single operation, troublesome data registration is reduced and inconsistencies between data can be prevented.

  Furthermore, according to the present invention, since the voice of the speaker is collected by a dedicated microphone, there is no deterioration in sound quality, and highly accurate voice recognition is possible.

In the following, an embodiment in which the information presentation system of the present invention is applied to a call center provided with responders who respond to telephone inquiries from customers will be described.
FIG. 1 is a diagram showing a configuration example of the entire system of this embodiment.
The responder is arranged at a place where the information processing apparatus 1 and the telephone 2 are installed. The telephone 2 on the responder side is connected to the telephone 3 on the customer side via the public communication line network N1, and two-way communication is performed. The responder-side information processing device 1 is connected to the manager-side information processing device 4 that manages the responder via the communication line N2. Further, the information processing apparatus 1 can be connected to a homepage server (hereinafter referred to as “HP server”) 5 via the Internet N3.

FIG. 2 is a block diagram illustrating a configuration of the information processing apparatus 1 on the responder side.
The information processing apparatus 1 includes a computer main body 6, audio input means 7, and output means 8.

The computer main body 6 includes information presentation processing means 9, action data storage means 10, user dictionary storage means 11, file storage means 12, and user word registration processing means 13. Further, the computer main body 6 includes a communication interface (not shown), and is connected to the information processing apparatus 4 on the administrator side, the HP server 5, etc. via the voice input means 7 and the output means 8, and the LAN and the Internet. It has a function.

  The voice input means 7 is a means for collecting the speech voice of the speaker, and any means can be used as long as it can collect the voice. Therefore, the telephone 2 may be connected to the computer main body 6 and used as voice input means. However, in this embodiment, in addition to the telephone set 2, a dedicated microphone for collecting the voice of the responder before flowing on the telephone line is provided, and this is used as a voice input means. This is to prevent deterioration of the sound quality once it flows through the telephone line, so that this can be prevented and highly accurate voice recognition can be performed.

Since the voice data collected from the voice input means 7 is analog signal data, it is converted into digital signal data before being input to the information presentation processing means 9. Hereinafter, the voice data to be subjected to voice recognition processing by the information presentation processing means 9 is data after this A / D conversion.
Details of the data conversion and the like are not essential matters for the present invention, and thus description thereof will be omitted.

  The output unit 8 is a unit that outputs information related to the keyword extracted from the speech recognition result of the uttered voice to the responder. As the output means 8, a display that can be viewed by a speaker is conceivable. However, it is not limited to the display, and anything that can know the information presented by the responder may be used.

  The information presentation processing unit 9 performs voice recognition processing on the voice input by the voice input unit 7, detects a keyword from the recognition result, and performs a predetermined process when a condition corresponding to the keyword is satisfied. Then, the processing result is transmitted to the output means 8 for output. These processes are performed by loading a computer program stored in an external auxiliary storage device or ROM onto the memory.

In this embodiment, the speech recognition processing by the information presentation processing means 9 is divided into a processing portion for converting speech into text by a method using dictation and a processing portion for detecting a predetermined keyword from this text. For convenience of explanation, the former is expressed as dictation processing and the latter is expressed as keyword detection processing. This dictation process recognizes a general sentence including “Tenanoha”. Compared to a method using a rule grammar that recognizes a word in a list such as a word that has been created in advance, this method is difficult in terms of processing in many possibilities. Therefore, in order to alleviate this difficulty, modeling using an N-gram that is a known method is used.
The N-gram model, N = take 3 of the case (referred to as tri-gram) as an example, the word was given string w ₁ w _{2 ···} w _n of the occurrence probability _{P (w 1 w 2 ··· w} n ) Is approximated by P (w ₁ w _2... W _n ) = ΠP (w _i | w _i−2, w _i−1 ) × P (w ₁ w ₂ ). It is a model. P (w _i | w _i−2, w _i−1 ) on the right side represents a conditional probability that w _i comes next when the words w _i−2 and w _i−1 come. All products of P (w _i | w _i−2, w _i−1 ) are calculated, and a combination of word strings in which P (w ₁ w _2... W _n ) has the largest value is determined as a recognition result. To do.

Such a dictation process enables speech to be converted into text, so that a keyword can be easily detected by performing a character string search on the text.
Moreover, since the result of speech recognition is obtained as text, this text can be saved as a record of the future. In addition, there is a secondary effect that the responder can easily create a daily report by editing this text.

The action data storage unit 10 stores correspondence data of keywords and actions in which conditions corresponding to the keywords are associated with action information related thereto. The correspondence data between keywords and actions will be described in detail later.
The user dictionary storage unit 11 stores a user dictionary which will be described in detail later.
The file storage means 12 is a means for storing a file or the like registered as the above action information.
The action data storage means 10, the user dictionary storage means 11, and the file storage means 12 are mounted on an auxiliary storage device such as a CD-ROM or a hard disk provided in the computer main body 6.

Next, the user word registration processing means 13 is a means for storing a keyword stored in the action data storage means 10 as a user word in the user dictionary storage means 11.
The information presentation processing unit 9 and the user word registration processing unit 13 are realized by a CPU mounted on the computer main body 6 reading and executing a predetermined computer program from a ROM or an auxiliary storage device.

Next, the correspondence data between keywords and actions stored in the action data storage means 10 will be described. FIG. 3 illustrates the correspondence between the conditions corresponding to the keywords and the action information. In the example of FIG. 3, the keywords are “new microwave oven”, “microwave oven”, “refrigerator”, “price”, “price”, which appear in the condition column 14 (hereinafter referred to as “condition column”) corresponding to the keyword. It is the word "I understand". When a keyword is detected from the output text of the dictation process, it is assumed that the keyword is valid. Keywords that are not detected are invalid.
For the sake of convenience, the description will be made assuming that “effective” has a logical value “true” and “invalid” has a logical value “false”.
The condition corresponding to the keyword means a result obtained by performing a logical operation on the value of each keyword. When this is “true”, it is determined that the condition corresponding to the keyword is satisfied. When the conditions listed in the condition column 14 are satisfied, processing based on the file identifier and URL described in the corresponding action information column 15 is executed.

The conditions corresponding to the keywords will be described in detail below.
The condition column 14a indicates that the process based on the action information column 15a is executed on condition that the value of the keyword “new microwave oven” is true, that is, the “new microwave oven” is detected from the voice of the speaker. means.
In the condition column 14b, when the value of the keyword “microwave oven” is true and “not new microwave oven” is true, that is, the value of the keyword “new microwave oven” is false, processing based on the corresponding action information is performed. It means to execute.
The condition column 14c shows the corresponding action when the value of the keyword “new microwave oven” is true and “price or price” is true, that is, when the value of either the keyword “price” or “price” is true. This means that processing based on information is executed.

  The action information column 15 describes file identifiers and URLs. From the file identifier “c: \ product \ new_microwave.jpg” described in the action information column 15a, the file name, the file storage location, and the file type can be known. Since the file extension is “jpg”, the file is an image file, and when the keyword “new microwave oven” appears, the information presentation processing means 9 reads this file from the file storage means 12, and Data is output to the output means 8.

  There are various other file extensions, such as “exe”, which means an executable file, and “doc”, which means a document file created with Word (a Microsoft product name). Performs processing according to each file type. For example, a file storing a program named “warning” is designated in the action information column 15b. Thus, when the program file is described in the action information column 15, the result of the speech recognition process can be used as an argument. The result of the speech recognition process is a text obtained by the dictation process, a keyword obtained by the keyword detection process, or the like. Also, when taking an argument, the number is not limited to one.

  In the action information column 15c, a URL "http: // pricelist / new_microwave" is described. When the condition column 14c is true, the information presentation processing means 9 requests the HP server 5 to transmit the content of the site with this URL.

Although the program can be specified in the action information column 15 as described above, this program is not limited to the one that causes the responder to acquire information for answering the question from the customer. It may be aimed at the responder's OJT.
For example, it is assumed that “warning” specified in the action information column 15b is a program that issues a warning and displays a correct wording on the screen when an inappropriate wording is detected. If the responder makes an inappropriate wording ("I understand" in the example in Figure 3), this is passed as an argument to the program "warning" and the correct wording (for example, "I'm clever") If you show it, you can give instruction to responders. Or the program which transfers the utterance content of the responder with a high frequency of improper wording to the administrator's computer 4 may be sufficient.
In short, in this embodiment, there is no restriction on what keywords are registered as action data and what processing is executed under what conditions.

Next, the user dictionary stored in the user dictionary storage unit 11 will be described.
FIG. 4 shows an example of a user dictionary. In this dictionary, keywords to be registered in the action data storage means 10 are registered in association with their notations and readings.
The detection of keywords for presenting information, which will be described in detail later, targets only words registered in this user dictionary. Since the keywords to be detected are narrowed down in this way, a processing speed capable of following the natural utterance of the speaker can be realized.

Registration of action data and registration in the user dictionary are laborious operations if they are performed separately.
In this embodiment, when a user registers a keyword in the action data storage unit 10 using an input unit such as a keyboard or a mouse (not shown), the user word registration processing unit 13 registers the notation of the keyword in the user dictionary. The reading corresponding to the notation can be registered without user input by the user word registration processing means 13 referring to a system dictionary (not shown). In addition, the process for obtaining the reading from the word notation is publicly known, and this embodiment also follows the publicly known process.
The “user” here is a person who uses the system of this embodiment, and a call center administrator and responder also correspond to the “user”.

In this embodiment, if the user performs an operation such as a keyboard input for registering a keyword in the action data storage unit 10, it is not necessary to perform an operation for registering in the user dictionary. If a user operation is separately required for registration in the user dictionary, forgetting this operation may result in inconvenience that the action data cannot be matched with the user dictionary. However, since the user word registration processing unit 13 performs registration to the user dictionary without the user being aware of this, such a problem does not occur.
This does not mean that there is no room for the user to perform registration procedures in the user dictionary. For example, in the case of a keyword that is difficult to read, such as “WYSIWYG”, this does not prevent the user from registering “wizig” in the user dictionary by operating the keyboard or the like.

  By the way, the processing by the information presentation processing means 9 is of a nature that is continuously performed during the operation time of the call center. On the other hand, the processing by the user word registration processing means 13 is performed at the time of maintenance after starting the operation of the system or after starting the operation, and is not a property that is constantly performed. In addition, it may be appropriate to assign a specific person in charge to the registration process. Therefore, the user word registration processing means 13 may be provided in the information processing apparatus 4 on the manager side, not in the information processing apparatus 1 on the responder side.

Next, the operation of this embodiment will be described.
A call center responder interacted with a customer who made an inquiry over the phone, and at this time, the responder said, “It was clever. You are inquiring about the price for purchasing a new microwave oven.” An example will be described. In the following description, the examples shown in FIGS. 3 and 4 are used.
The voice of the responder is input to the information presentation processing means 9 via the voice input means 7.

  The information presentation processing means 9 performs a dictation process using a user dictionary stored in the user dictionary storage means 11 and a system dictionary (not shown), and converts the input speech into text. For example, suppose that the dictation process gives a recognition result, for example, "I was having trouble lending. ☆ New ☆ Inquiry about price for milking five microwave ovens." Here, ☆ represents “information indicating the start position of the user word”. As long as it indicates the head position, it may be the corresponding address of the memory in which the text is stored, or information such as what number character.

Next, the information presentation processing means 9 sequentially processes the text in accordance with the utterance of the responder. For example, after receiving the text up to "I was troubled to lend. ☆ New ☆ Microwave", there is information indicating the head position of the keyword. From the strings "New microwave" and "Den" starting with "New" The keyword is searched from the action data storage means 10 for the character string “microwave” starting with the character string.
Here, it is not necessary to use the keyword detection for “I had trouble lending” before “New” appeared. As described above, since the keyword detection range can be narrowed down, rapid processing can be realized.
In the example of the user dictionary shown in FIG. 4, “new microwave oven” is not registered as a user word. However, since “new” is registered, it is understood that a character string starting from “new” should be the target of keyword search. Therefore, the keyword “new type microwave oven” in the example of FIG. 3 will not be missed.

  By searching for keywords, the keywords “new microwave oven” and “microwave oven” are detected, and these keywords are validated. Here, the keyword search is performed by checking whether the left end ("new", "new", "new model" ...) of the character string matches the element of the keyword set (may reach tens of thousands of words). By doing. This search for a single character string and a large number of keywords can be performed at high speed by a known method such as a hash index. In addition, since the keyword search is performed only from the head position of the user word, the number of searches can be reduced and processing can be performed efficiently.

This efficient processing means that this system can respond to the natural utterances of responders. If the efficiency of the search process by this system is poor, it may force the responder to speak unnaturally. Then, the purpose of supporting the responder's work cannot be fulfilled.

Since the keyword “new microwave oven” has been detected, if a condition that satisfies the condition corresponding to the keyword is obtained from the action data storage means 10, “new microwave oven c: \ product \ new_microwave.jpg” corresponds. Therefore, the information presentation processing means 9 opens the file “c: \ product \ new_microwave.jpg”, and transmits the read image data to the output means 8 for display.
Furthermore, when the processing proceeds to “... Price for five milks”, the keyword “price” is detected, and this is validated. Prior to that, “To be breast-fed” does not need to be a target for keyword detection.
In the process so far, “new microwave oven” and “price” are detected and both are valid, so the condition of action data “new microwave oven and (price or price) http: // pricelist / new_microwave” is satisfied . Therefore, a request for browsing the content is made to the site of the URL.

Furthermore, when the utterance of the responder ends and the utterance of the customer starts, the keyword detection processing portion of the information presentation processing means 9 may receive the text that is the processing result of the dictation processing portion over a certain time (for example, 10 seconds). Can not. Therefore, the keyword detection processing portion invalidates the keywords “new microwave oven” and “price” detected so far. Here, for example, after the customer's utterance, when the responder utters "I have a separate question about the refrigerator" and the keyword "refrigerator" is detected, the keyword "price" is already invalidated. Yes. Therefore, it is possible to prevent the action data “refrigerator and (price or price) http: // pricelist / refregerator” from being erroneously determined to satisfy the “condition”.

  In this embodiment, the keyword detection processing part detects that the text as a result of the dictation process has not been received for a certain period of time, thereby invalidating the keywords detected so far. However, the condition for invalidating the keyword is not limited to this. For example, the keyword can be invalidated by operating a keyboard or mouse by the responder or disconnecting the telephone.

  In the above embodiment, only the utterance voice of the responder is used as input data for the voice recognition process. However, the telephone 2 may be connected to the information processing apparatus 1 on the responder side, and the conversation voice between the responder and the customer may be input from the telephone 2 to the information presentation processing means 9. Alternatively, only the voice of the responder may be input from the telephone 2 to the information presentation processing means 9.

  In the above embodiment, the information processing apparatus 1 is connected to the external telephone 3, the HP server 5, and the like via the public communication network N 1, the communication network N 2, and the Internet N 3. However, the present invention can also be applied to a single information processing apparatus 1. In other words, there is room for application to uses other than call centers.

  Further, in the above-described embodiment, the display device that can be browsed by visual sense as the output unit 8 has been described. However, the output unit 8 may be an auditory information presentation unit. For example, if a visually handicapped person inputs a question or the like by voice, an appropriate response is returned by voice, and application to the fields of welfare and education becomes possible.

Furthermore, in the above embodiment, the keyword is detected by the dictation method. However, the method is not limited to the dictation method, and other methods may be used as long as keywords can be detected from continuous utterances.

It is a figure which shows the structure of the information presentation system to which this invention is applied. It is a functional block diagram of the information processing apparatus on the responder side. It is a figure which shows an example of the corresponding data of a keyword and an action. It is a figure which shows an example of the data stored in the user dictionary memory | storage means.

Explanation of symbols

2 Voice input means (telephone)
7 Voice input means (dedicated microphone)
8 Output means 9 Information presentation processing means 10 Action data storage means 11 User dictionary storage means 13 User word registration processing means

Claims (10)

Action data for storing correspondence data of a keyword and an action corresponding to a voice input means for inputting the voice of the speaker, a condition corresponding to a predetermined keyword, and action information related thereto in the information presentation system for the speaker Storage means and information presentation processing means for presenting information using voice recognition, the information presentation processing means performs voice recognition processing of a speaker's uttered voice, and based on the result of this processing, the action data storage means The keyword stored in is detected, it is determined whether or not the detected keyword satisfies the condition, and if the condition is satisfied, the corresponding action information is extracted from the action data storage means, and the extracted action information An information presentation system for a speaker, characterized by executing a process based on. 2. The information presentation system for a speaker according to claim 1, further comprising an output unit that can be browsed by the speaker, wherein the processing based on the extracted action information causes the output unit to display information. The information presentation processing means converts the input voice into text by a method using dictation processing, and detects a keyword stored in the action data storage means from the text. Information presentation system for the speaker described. A user dictionary storage means for storing user words for storing words in correspondence with their notation and reading, and when the user words stored in the user dictionary storage means are included in the text obtained by the dictation process 2. The method according to claim 1, wherein information indicating a head position of the user word in the text is output, and the information presentation processing means executes a keyword search only from the head position of the user word. 3. An information presentation system for a speaker according to 3. 5. The system for presenting information to a speaker according to claim 4, further comprising user word registration processing means for storing keywords stored in the action data storage means as user words in the user dictionary storage means. If the action information associated with the condition corresponding to the keyword in the action data storage means is information specifying the file type and file name, the information presentation processing means opens the file and sets the type 6. The system for presenting information to a speaker according to any one of claims 1 to 5, wherein if the URL of a site on the Internet is performed according to the corresponding process, the web page of the site is requested to be browsed. 7. The information for a speaker according to claim 6, wherein when the file is opened and the process according to the type is a program file, the speech recognition result is used as an argument of the program. Presentation system. The voice input means inputs voice of a conversation between a responder and a questioner corresponding to a question via a telephone line, and passes the voice of the conversation to the information presentation processing means. 8. An information presentation system for a speaker according to any one of 7 above. The voice input means includes a dedicated microphone that collects only the voice spoken by the responder corresponding to the question via the telephone line, and the information input processing means does not pass the voice input to the microphone via the telephone line. 9. The system for presenting information to a speaker according to claim 8, wherein: A computer program for causing a computer to operate as an information presentation system for presenting information corresponding to a keyword detected by speech recognition from a speech voice of a speaker by being read and executed by a computer, the computer comprising: Means for registering action data associating a condition corresponding to a predetermined keyword with file information related to the condition into action data storage means, means for performing speech recognition processing on the input speech of the speaker, voice recognition The keyword stored in the action data storage means is detected from the result, and it is determined whether or not the detected keyword satisfies the condition. If the condition is satisfied, the corresponding file information is extracted from the action data storage means. And execute processing based on the extracted file information That means, a computer program for functioning as means for outputting the execution result.

Images