JP2022013032A - Information processing device, control method, and program - Google Patents

Abstract

To provide a mechanism that determines a word to be used for voice recognition in accordance with contents of voice data, thereby acquiring an appropriate voice recognition result.SOLUTION: In an information processing system, an information processing server 100 is connected to a recognition server 101 that performs voice recognition on voice data so as to communicate with each other, and includes a recognition pattern determination unit 302 that, in accordance with a data item recognized from the voice data, determines a word related to the data item to be used for the voice recognition, and a pattern processing unit 304 that acquires a value of the data item based on a result of the voice recognition performed by the voice recognition device by using the determined word.SELECTED DRAWING: Figure 3

Description

The present invention relates to a speech recognition technique for converting speech data into a character string.

Conventionally, speech recognition technology has been used for the purpose of improving the efficiency of input work for information processing devices. In recent years, technologies such as machine learning have significantly improved the accuracy of speech recognition.

In cloud services and the like, humans analyze a large amount of data and use it as training data for machine learning to further improve accuracy, but there is still a need for users to customize it according to their needs.

In addition, words may be registered depending on the purpose. In particular, rare person names, organization-specific department names, product names, and other proper nouns are not included in general dictionaries, and may be registered in association with pronunciation. In addition, although it is a general term, it is not always necessary to associate it with pronunciation when there are many homophones and allography, but it may be registered in order to raise the priority.

There are several methods for word registration in speech recognition services.

In one service, necessary words are registered in advance, and a series of voice recognition requests are repeated. In this method, the same word information registered in advance for the content of each voice recognition request is used, so even if there are homophones and different notations, they may not be used properly.

In another example of the service, there is also a method in which the registered word can be exchanged according to the content of the voice data to be passed to the service each time the voice recognition is requested. In this method, the number of words that can be registered is limited to a relatively small number, so it is necessary to select an appropriate word for each speech recognition request.

In the technique described in Patent Document 1, it is judged that it is better to register a word as a candidate for registration as a trial, perform voice recognition of evaluation voice data, present the effect to a human, and register the word by the human. If this is the case, it will be additionally registered in the word dictionary.

Japanese Unexamined Patent Publication No. 2018-40906

In the technique of Patent Document 1, all the words determined to be registered are registered in advance. However, in this method, the registered word affects any speech data, and as a result, it is likely to be effective in improving the overall accuracy of speech recognition, but it is suitable for individual speech recognition requests. May not return results. That is, there is a possibility that it will not be partial, instead of being totally optimized.

An object of the present invention is to provide a mechanism for acquiring an appropriate voice recognition result by determining a word to be used for voice recognition according to the content of voice data.

The present invention is an information processing device communicably connected to a voice recognition device that recognizes voice from voice data, and a word related to the data item used in voice recognition is used according to the data item recognized from the voice data. It is characterized by comprising a determination means for determining and an acquisition means for acquiring a value of a data item based on the result of voice recognition by the voice recognition device using the determined word.

INDUSTRIAL APPLICABILITY According to the present invention, it is possible to provide a mechanism for acquiring an appropriate speech recognition result by determining a word to be used for speech recognition according to the content of speech data.

It is a figure which shows an example of the structure of the information processing system which concerns on embodiment of this invention. FIG. 3 is a block diagram showing an example of a hardware configuration applicable to the information processing server 100, the recognition server 101, and the information processing terminal 102 according to the embodiment of the present invention. It is a figure which shows an example of the functional structure which concerns on embodiment of this invention. This is an example of the user interface of the information processing terminal 102 according to the embodiment of the present invention. This is an example of the user interface of the information processing terminal 102 according to the embodiment of the present invention. It is an example of the flowchart explaining the process of voice recognition which concerns on embodiment of this invention. It is an example of the flowchart explaining the process of determining the word to be registered which concerns on embodiment of this invention. It is a figure which shows an example of the storage part which stores the information which is associated with the voice recognition item which concerns on embodiment of this invention. It is a figure which shows an example of the voice data input by the user and the voice recognition result which concerns on embodiment of this invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

FIG. 1 is a diagram showing an example of a configuration of an information processing system according to an embodiment of the present invention.

The information processing terminal 102, the information processing server 100, and the recognition server 101 are communicably connected via the network 103. The network 103 is, for example, the Internet or a LAN.

The information processing terminal 102 is a personal computer or a smartphone, and the application constituting the user interface in the present invention is installed, or the web browser software for executing the web application provided by the information processing server 100 is installed. The web application is accessed by specifying a specific URL.

Further, the information processing terminal 102 is connected to a microphone for inputting voice data according to the present invention as a built-in or external device. A camera used for the purpose described later may also be built-in or connected as an external device.

The information processing server 100 provides the application according to the present invention to the information processing terminal 102, and the voice data received from the information processing terminal 102 is sent to the recognition server 101 to execute the voice recognition process, and the result (text data). To receive.

However, the information processing server 100 and the recognition server 101 may have the same housing. Further, a part of the functions of the application of the present invention may be arranged and executed in the information processing terminal 102. The arrangement of the functions described below is merely an example, and the arrangement is not limited to a specific information processing apparatus. The above is the description of FIG.

FIG. 2 is a block diagram showing an example of a hardware configuration applicable to the information processing server 100, the recognition server 101, and the information processing terminal 102 according to the embodiment of the present invention.

As shown in FIG. 2, the information processing server 100, the recognition server 101, and the information processing terminal 102 are the CPU (Central Processing Unit) 201, the RAM (Random Access Memory) 203, and the ROM (Read Only Memory) via the system bus 204. A configuration is adopted in which 202, an input controller 205, a video controller 206, a memory controller 207, a communication I / F controller 208, and the like are connected.

The CPU 201 comprehensively controls each device and controller connected to the system bus 204.

Further, the ROM 202 or the external memory 211 will be described later, which is necessary for realizing the functions executed by the BIOS (Basic Input / Output System) and the OS (Operating System), which are the control programs of the CPU 201, and the functions executed by each server or each PC. Various programs etc. are stored. In addition, information necessary for carrying out the present invention is stored. The external memory may be a database.

The RAM 203 functions as a main memory, a work area, and the like of the CPU 201. The CPU 201 realizes various operations by loading a program or the like necessary for executing the process from the ROM 202 or the external memory 211 into the RAM 203 and executing the loaded program.

Further, the input controller 205 controls input from a pointing device such as a keyboard (KB) 209 or a mouse (not shown).

The video controller 206 controls the display on a display such as the display 210. The display may be a display such as a liquid crystal display. These are used by the administrator as needed.

The memory controller 207 is an external storage device (hard disk (HD)) for storing boot programs, various applications, font data, user files, edit files, various data, etc., a flexible disk (FD), or a PCMCIA (Personal Computer). Controls access to external memory 211 such as CompactFlash® memory connected via an adapter to the Memory Card International Association card slot.

The communication I / F controller 208 connects and communicates with an external device via the network, and executes communication control processing on the network. For example, communication using TCP / IP (Transmission Control Protocol / Internet Protocol) is possible.

The CPU 201 can be displayed on the display 210, for example, by executing an outline font expansion (rasterization) process in the display information area in the RAM 203. Further, the CPU 201 enables a user instruction by a mouse cursor (not shown) or the like on the display 210.

Various programs described later for realizing the present invention are recorded in the external memory 211, and are executed by the CPU 201 by being loaded into the RAM 203 as needed.

FIG. 3 is a diagram showing an example of a functional configuration according to an embodiment of the present invention. The data input unit 321 receives data such as voice by operating the application of the present invention by the user. In addition, an image or the like of a receipt or the like related to the item (“payment item” in the example described later) may be accepted.

The data transmission unit 322 transmits data such as voice data input by the user's operation to the information processing server 100, and the data reception unit 301 of the information processing server 100 receives the data.

In the recognition pattern determination unit 302, the data includes "items" ("payment items" in the example described later) and "detailed items" already determined ("accommodation start date" and "accommodation cost" in the example described later). Based on the above, the unconfirmed items are judged at that time, and the recognition method is decided. The recognition method is, for example, to register which word is to be registered and to determine which word to perform voice recognition. The information necessary for these decisions is stored in the rule storage unit 306.

The recognition execution unit 303 transmits the registered word and the voice data to the recognition server 101 based on the determined recognition method, causes the voice recognition unit 311 to recognize the registered word and the voice data, and receives the result (recognition character string). Further, as will be described later, image data such as a receipt may be sent so that the character recognition unit 312 recognizes the image data and receives the result (recognition character string).

The information processing server 100 specifies a portion (“accommodation start date”, “accommodation fee”) corresponding to the “detailed item” in the pattern processing unit 304 of the character string recognized by the recognition server 101. At that time, the information described in the pattern 804 stored in the rule storage unit 306 is used as the pattern matching rule.

The result transmission unit 305 transmits the information specified above to the information processing terminal 102, and the result reception unit 324 of the information processing terminal 102 receives the information. This information is presented to the user on the display unit 323, and the user is urged to perform the next operation (“re-recognition” when the information is insufficient, “registration” when the information is sufficient, etc.). This completes the description of FIG.

Next, a screen example for reimbursement of expenses will be described with reference to FIGS. 4 and 5. This screen shows an example of a user interface in the information processing terminal 102.

First, FIG. 4 will be described. When the user activates the "expense settlement application" on the information processing terminal 102, there is a settlement item selection list 401 (list selection) for selecting what kind of expense is to be settled. If the user knows the detailed item to be settled and selects it from the list, the flow of the process described in the flowchart described later becomes simple, but if he / she does not know, he / she does not have to select it.

Further, by pressing the voice recognition button 402, for example, the information processing terminal 102 receives the voice "staying at the Yokohama hotel from July 10 to July 12, totaling 19,800 yen", and the information processing server 100. Send to.

In FIG. 5, the voice input by the user is recognized, the settlement item is “accommodation fee”, and the detailed item (“accommodation start date”, “accommodation end date”, “accommodation destination”, “cost”). Information about is extracted and displayed. Columns 501 are assigned "◎", "x", which are marked according to whether or not the application has successfully acquired the information. In the example, the name of the accommodation is not well recognized ("x").

Whether or not the information acquisition is successful can be changed at the user's discretion. For example, in the example of FIG. 5, "cost" is marked with "◎", but this is an application judgment and may actually be incorrect.

The user may change these recognition results by text input, but may press the voice recognition button 402 again after correctly correcting "◎" and "x" in the column 501.

At that time, it is the expense settlement of the "accommodation fee", and it is sent to the information processing server 100 that only the information about the "accommodation" in it is inaccurate. In the process flow described later, the application processes more appropriate voice recognition and acquisition of information by using the information already known and the information designated as inaccurate, and displays it on the screen again.

Finally, if all the results are described correctly, the registration button 502 is pressed and the user applies as an expense.

Needless to say, these processes can be used not only for "expense settlement" but also for various forms. This completes the description of the screen example using FIGS. 4 and 5.

Next, an example of the process in the present invention will be described with reference to the flowcharts of FIGS. 6 and 7. Each step of the flowchart is executed by the CPU 201 on the information processing server 100. Further, a rule storage unit 306 (FIG. 8) referred to when each step is executed, an example of voice data input by the user and a voice recognition result (FIG. 9) will be described as necessary.

In step S601, the data transmitted from the information processing terminal 102 is received. In addition to the voice data spoken by the user, if any "item" is selected in the settlement item selection list 401, which item it is (for example, "accommodation fee") is also included in the data. It will also be received.

As an example, suppose that the user's first voice input is "staying at the Yokohama Hotel from July 10th to July 12th for a total of 19,800 yen" (user's first utterance 901 in FIG. 9).

In step S602, a word group registered in the voice recognition unit 311 of the recognition server 101 is listed in order to specify the recognition pattern and optimize the voice recognition accuracy for that purpose. This process will be described with reference to the flowchart of FIG.

In step S701, it is determined whether or not an "item" (in this example, a "settlement item") for which detailed information should be determined has been determined. For example, when voice data is first sent from the information processing terminal 102 to the information processing server 100, and the user has not selected an explicit item in the settlement item selection list 401, it is necessary to determine as a result of voice recognition. There is (ie, not decided at this point). In this case (NO), the process proceeds to step S702.

If the user has explicitly determined an item in the settlement item selection list 401, or has already performed voice recognition once and the settlement item to be processed has been determined from the result (YES), the process proceeds to step S703.

In step S702, since the "payment item" is undecided, it is prioritized to improve the accuracy of voice recognition in order to determine the "payment item" rather than to acquire the detailed item (such as "accommodation"). Will be. Therefore, the words (words included in the feature word groups S1 to SZ) for registering the words described in the settlement item feature word 802 in FIG. 8 in the voice recognition service are listed. This process is an example of a process for determining a word related to the type of speech data used in speech recognition.

The word described in the settlement item feature word 802 of FIG. 8 will be described. At this point, it is necessary to determine the "payment item" (for example, "accommodation fee" or "taxi fare") rather than the detailed information of the payment details, and the word (or character) to distinguish them. Priority is given to accurately acquiring the column) from the audio data.

Therefore, in the settlement item feature word 802, for example, a word (or a character string) as in the feature word group S1 is defined as a word that characterizes the fact that the item is “accommodation fee”. If the information contained in the voice data is "accommodation expenses", it is highly likely that "accommodation", "hotel", etc. will appear in the user's voice, so these words are registered and the result of voice recognition. It is important to get it reliably. Also, if it is "taxi fare", "taxi", if it is "train fare", "Toei", "metro", or more specifically, "Asakusa line" may be included in the voice. high. These words are listed for registration in the voice recognition unit 311 before the voice recognition request described later.

Here, the flowchart temporarily returns to step S603 of FIG. In step S603, the words included in the feature word groups S1 to SZ determined in S702 described above are transmitted to the voice recognition unit 311 of the recognition server 101 to be registered in order to improve the voice recognition accuracy, and the voice is recognized at the same time. Data (901) is also transmitted.

In step S604, the result recognized by the voice recognition unit 311 (character string of the recognized result) is received. For example, the "first voice recognition result" (902) of FIG. 9 is received.

In step S605, it is applied to the pattern whether or not the information corresponding to the "payment item" and the "detailed item" is included in the character string of the recognition result received in step S604. Specifically, since the characters "hotel" and "accommodation" are included in 902, it can be determined that the "payment item" is "accommodation expense". This process is an example of a process of specifying the type of voice data based on the result of voice recognition by the voice recognition device using the determined word. When determining the "payment item", not only when the speech recognition result 902 contains a phrase that matches the feature word of 806 as described above, but also a phrase similar to the feature word and related words and phrases are determined. It may be determined when a word or phrase is included, or it may be determined by pattern matching with a recognition result for which a "scrutiny item" has been determined in the past, inference by machine learning, or the like. Furthermore, information on "accommodation end date" and "expense" can be obtained from the detailed items related to the settlement item "accommodation expense". Specifically, it is because the character strings of 922 and 925 in FIG. 9 match the pattern described in the pattern 804 of FIG. This process is an example of a process of extracting a part related to a data item from a result of voice recognition by a voice recognition device under a predetermined condition.

In step S606, it is confirmed whether or not all the detailed items have been acquired for the settlement item of interest. In the above example, since the “accommodation start date” and the “accommodation destination” have not been acquired among the “accommodation expenses”, the result is NO and the process proceeds to step S607. This process is an example of the process of determining whether the value of the data item can be acquired by the acquisition means.

If all the detailed items can be acquired (in the case of "YES"), the recognition result is returned to the information processing terminal 102, and the process of the present invention is completed.

Next, steps S607 and S608 will be described, but this determination is merely an example. That is, the essence of the present invention is to acquire necessary information by dynamically switching the dictionary registered in the voice recognition unit 311 even if the voice data is the same, but the quality of the first voice data is high. If it is bad, it cannot be obtained no matter how many times it is repeated. Therefore, certain restrictions are applied to the reuse of voice data. Since this is just an example, it goes without saying that any other criterion such as the waiting time of the user and the number of detailed items that could not be recognized repeatedly can constitute the present invention. Then, step S607 and step S608 will be described as an example.

In step S607, the conviction of voice recognition is used as a determination criterion. As a general technique, the output of speech recognition includes not only the character string of the recognition result but also "confidence". For example, the closer the numerical value is from 0 to 1, the higher the probability that the answer is correct (matches the user's utterance).

If the certainty is high (YES), the quality of the voice data input by the user is high, for example, there is little noise in the recording environment, the performance of the input device such as a microphone is good, and the speaker's tongue is good. Even if the first voice recognition fails, there is a high possibility that the correct answer will be output by registering a word. Therefore, the process returns to step S602 via step S608, and the process is repeated again.

If the degree of certainty is low, the correct answer cannot be obtained even if the word is registered and recognized again (in the case of NO), so the process proceeds to step S609. The threshold value for obtaining / not obtaining the correct answer as long as the degree of certainty is manually set in a storage unit such as a file in advance.

In step S608, a limit is set on the number of times the voice data is recognized. As a result, for example, even if a word that is a characteristic word is registered in the voice recognition unit 311 to improve the certainty, it is possible to avoid repeating the situation that the necessary information is not actually obtained. .. This number of times is also manually set in the storage unit of the file or the like in advance. Further, if it is not the number of times and the feature word group of FIG. 8 cannot be recognized even if it is expanded to the maximum, it may be determined as "YES" and the process may proceed to step S609.

If NO is obtained in step S608, the process returns to step S602 (that is, the flowchart of FIG. 7) to prepare for voice recognition of the first voice data again.

When the flowchart of FIG. 7 is executed from the second time onward, the "payment item" has already been determined (in the example, "accommodation fee"). In this case, "YES" is set in step S701, and the process proceeds to step S703.

In step S703, preparations are made for passing a word belonging to the feature word group of the “detailed item” that has not been determined yet to the speech recognition unit 311. In this example, since the "accommodation start date" and "accommodation destination" have not been acquired yet, the words of the related feature word groups D1 and D2 are listed, and the process returns to the flowchart of FIG. 6 again. This process is an example of a process of determining a word related to the data item used in the voice recognition according to the data item recognized from the voice data.

In step S603 of FIG. 6, the voice recognition unit 311 is instructed to register the words of the feature word groups D1 and D2, and the voice data first input by the user is passed. This process is an example of a process of determining a word related to a data item as a word used in speech recognition according to the determination result.

The result is received in step S604, and it is confirmed whether these two detailed items can be acquired in step S605. In 902 of FIG. 9, the failed accommodation start date (“July section” (921)) was accurately recognized in the second time, and “July 10” was obtained (903). However, it is assumed that "accommodation" is "?? Hotel" (931) and fails again. This process is an example of a process of acquiring the value of a data item based on the result of voice recognition by the voice recognition device using the determined word.

Therefore, it is determined in the determination of steps S607 and S608 that the first voice data is used and the third voice recognition is executed.

Again, in step S703, it is determined that more words can be registered than the second time because there is only one detailed item to be recognized, "accommodation", and the expanded feature word group in the expanded feature word table 810 of FIG. 8 is determined. Register the word of D2. By registering more hotel names than the feature word group D2, we try to increase the probability of successful recognition. However, it is assumed that it fails according to 941 after all.

As a result, it is determined that the same voice data will not be recognized again (in the case of "YES" in step S608), and in step S609, an instruction is given to the information processing terminal 102 to input voice again only for the "accommodation". This process is an example of a process of accepting input of voice data related to a data item that could not be acquired by the acquisition means.

When the user recognizes that only the "accommodation destination" of the "accommodation fee" has not been correctly acquired by the information processing terminal 102 (501 in FIG. 5), only that information is input by voice and is again input to the information processing server 100. Send.

In step S601 of the information processing server 100, the information is received, and only the "accommodation" is recognized and the information is acquired by the same procedure as in the second and subsequent voice recognition described above. If the information acquisition is successful, the result is returned to the information processing terminal 102 as the final result (step S610). If it cannot be acquired again, it returns that it failed in step S609 as in the previous period.

As described above, assuming that all the detailed items of "accommodation fee" have been input, the explanation using the flowchart of FIGS. 6 and 7, the storage unit of FIG. 8, and the execution example of FIG. 9 is completed. Even if the system considers it successful, the patterns simply match, and the user may not be able to obtain accurate data. In that case, the user can perform operations such as selecting only the item again from the interface of the information processing terminal 102 and inputting voice data, or giving up information input by voice data and directly inputting characters. Not to mention.

It should be noted that the explanation given using FIGS. 6 to 9 is just an example, and what kind of voice data is used at that time even if the same voice data is repeatedly performed in the process of continuously performing voice recognition. Since the focus of the present invention is to focus on acquiring or changing information (word group), the method of determining the priority information to be acquired and the word group to be registered is arbitrary at each stage. Needless to say, all of them are included in the scope of the present invention. Further, the timing of re-requesting different voice data instead of the same voice data is also the same, and the control of the flow is included in the present invention by any method.

Although some embodiments have been described above, the present invention can be, for example, an embodiment as a system, an apparatus, a method, a computer program, a recording medium, or the like, and specifically, a plurality of devices. It may be applied to a system composed of, or may be applied to a device consisting of one device.

Further, the computer program in the present invention is a computer program in which a computer can execute the processing methods shown in FIGS. 6 and 7, and the storage medium of the present invention can execute the processing methods in FIGS. 6 and 7. Computer programs are stored. The computer program in the present invention may be a computer program for each processing method of the devices of FIGS. 6 and 7.

As described above, a computer in which a recording medium on which a computer program that realizes the functions of the above-described embodiment is recorded is supplied to the system or device, and the computer (or CPU or MPU) of the system or device is stored in the recording medium. Needless to say, the object of the present invention is achieved by reading and executing the program.

In this case, the computer program itself read from the recording medium realizes the novel function of the present invention, and the recording medium storing the computer program constitutes the present invention.

Recording media for supplying computer programs include, for example, flexible disks, hard disks, optical disks, magneto-optical disks, CD-ROMs, CD-Rs, DVD-ROMs, magnetic tapes, non-volatile memory cards, ROMs, and silicon disks. , Solid state drive and the like can be used.

Further, by executing the computer program read by the computer, not only the function of the above-described embodiment is realized, but also the OS (operating system) or the like running on the computer is realized based on the instruction of the computer program. Needless to say, there are cases where a part or all of the actual processing is performed and the processing realizes the functions of the above-described embodiment.

Further, the computer program read from the recording medium is written to the memory provided in the function expansion board inserted in the computer or the function expansion unit connected to the computer, and then its function is based on the instruction of the computer program code. Needless to say, there are cases where the CPU provided in the expansion board or the function expansion unit performs a part or all of the actual processing, and the processing realizes the functions of the above-described embodiment.

Further, the present invention may be applied to a system composed of a plurality of devices or a device composed of one device. It goes without saying that the present invention can also be applied when it is achieved by supplying a computer program to a system or an apparatus. In this case, by reading the recording medium containing the computer program for achieving the present invention into the system or device, the system or device can enjoy the effect of the present invention.

Further, by downloading and reading a computer program for achieving the present invention from a server, database, or the like on a network by a communication program, the system or device can enjoy the effect of the present invention.

It should be noted that the present invention also includes all the configurations in which each of the above-described embodiments and modifications thereof are combined.

100 Information processing server 101 Recognition server 102 Information processing terminal 103 Network 301 Data reception unit 302 Recognition pattern determination unit 303 Recognition execution unit 304 Pattern processing unit 305 Result transmission unit 306 Rule storage unit 311 Voice recognition unit 312 Character recognition unit 321 Data input unit 322 Data transmission unit 323 Display unit 324 Result reception unit

Claims (10)

An information processing device that is communicably connected to a voice recognition device that recognizes voice from voice data.
A determination means for determining a word related to the data item used in voice recognition according to a data item recognized from the voice data, and a determination means.
An information processing device including an acquisition means for acquiring a value of a data item based on a result of voice recognition by the voice recognition device using the determined word. A determination means for determining whether or not the value of the data item could be acquired by the acquisition means is provided.
The information processing apparatus according to claim 1, wherein the determination means determines a word related to the data item as a word used in voice recognition according to the determination result. The information processing apparatus according to claim 1 or 2, further comprising a first storage means for storing a word related to the data item. A management means for managing the type of voice data and data items, and
Provided with a specific means for specifying the type of the voice data,
The information processing apparatus according to any one of claims 1 to 3, wherein the data item recognized from the voice data is a data item managed for the specified voice data type. .. A second determination means for determining a word related to the type of speech data used in speech recognition is provided.
The information processing device according to claim 4, wherein the specifying means specifies the type of the voice data based on the result of voice recognition by the voice recognition device using the determined word. The information processing apparatus according to claim 5, further comprising a second storage means for storing a word according to the type of voice data. The information processing apparatus according to any one of claims 1 to 6, further comprising an extraction means for extracting a portion related to the data item from the result of voice recognition by the voice recognition device. The information processing apparatus according to any one of claims 1 to 7, further comprising a receiving means for receiving input of voice data related to a data item that could not be acquired by the acquisition means. It is a control method of an information processing device that is communicably connected to a voice recognition device that recognizes voice from voice data.
A determination step in which the determination means determines a word related to the data item used in speech recognition according to the data item recognized from the speech data.
A control method for an information processing apparatus, wherein the acquisition means includes an acquisition step of acquiring a value of a data item based on a result of voice recognition by the voice recognition device using the determined word. A program that can be executed by an information processing device that is communicably connected to a voice recognition device that recognizes voice from voice data.
The information processing device
A determination means for determining a word related to the data item used in voice recognition according to a data item recognized from the voice data, and a determination means.
A program for functioning as an acquisition means for acquiring a value of a data item based on the result of voice recognition by the voice recognition device using the determined word.

Images