JP7000171B2 - Communication systems, communication methods and communication programs - Google Patents

Description

The present invention relates to communication systems, communication methods and communication programs.

In recent years, UI (User Interface) / UX (User Experience) by voice has become widespread, and there are increasing cases of confirming numbers through voice IF (Interface). Examples of numbers output through voice include distance, time, number of cases, amount of money, speed, and the like. For example, when the user inputs a question about a number to the terminal, the utterance of the numerical value corresponding to the question is output from the terminal to the user.

Japanese Unexamined Patent Publication No. 2014-215396

However, the conventional method has a problem that a specific utterance to the user becomes long and smooth communication may not be possible. For example, when a user asks about the amount of the asset balance, if the number of digits of the asset balance amount is large, it may become unnecessarily long when the asset balance amount is spoken as it is, which hinders smooth communication. There was a case.

In order to solve the above-mentioned problems and achieve the object, the communication system of the present invention is generated by a generation unit that generates voice data to be output to the terminal as a response to input data received from the terminal, and a generation unit. When the voiced voice data includes a specific utterance, a determination unit for determining whether or not the specific utterance satisfies a predetermined condition, and when the determination unit determines that the predetermined condition is satisfied, It is characterized by having an output unit for outputting voice data to the terminal, omitting a part of the specific utterance.

Further, the communication method of the present invention is a communication method executed by a communication system, and is generated by a generation step of generating voice data to be output to the terminal as a response to input data received from the terminal and a generation step of generating the voice data to be output to the terminal. When the voiced voice data includes a specific utterance, a determination step of determining whether or not the specific utterance satisfies a predetermined condition, and a determination step of determining whether or not the predetermined condition is satisfied by the determination step. It is characterized by including an output step of outputting voice data in which a part of the specific utterance is omitted to the terminal.

Further, the communication program of the present invention includes a generation step of generating voice data to be output to the terminal as a response to input data received from the terminal, and a case where the voice data generated by the generation step includes a specific utterance. Is a determination step for determining whether or not the specific utterance satisfies a predetermined condition, and a voice in which a part of the specific utterance is omitted when the determination step determines that the predetermined condition is satisfied. It is characterized in that a computer executes an output step of outputting data to the terminal.

According to the present invention, there is an effect that smooth communication can be achieved by omitting a specific utterance to the user.

FIG. 1 is a block diagram showing a configuration example of a communication system according to the first embodiment. FIG. 2 is a diagram showing an example of data stored in the asset data storage unit. FIG. 3 is a diagram showing an example of data stored in the determination data storage unit. FIG. 4 is a diagram illustrating an example of outputting an accurate number when a user requests a detailed value after outputting an approximate value. FIG. 5 is a diagram illustrating a processing example for determining the number of lower digits to be omitted. FIG. 6 is a flowchart showing an example of the flow of processing executed by the server. FIG. 7 is a diagram showing a computer that executes a communication program.

Hereinafter, the communication system, the communication method, and the embodiment of the communication program according to the present application will be described in detail with reference to the drawings. It should be noted that this embodiment does not limit the communication system, communication method and communication program according to the present application.

[First Embodiment]
In the following embodiment, the configuration of the server 10 in the communication system 100 according to the first embodiment and the processing flow of the server 10 will be described in order, and finally, the effect of the first embodiment will be described.

[Communication system configuration]
First, the configuration of the communication system 100 will be described with reference to FIG. FIG. 1 is a block diagram showing a configuration example of a communication system according to the first embodiment. As shown in FIG. 1, the communication system 100 has a server 10 and a terminal 20, and the server 10 and the terminal 20 are connected to each other via a network 30.

The server 10 is a computer that generates voice data and transmits it to the terminal 20 as a response to the input data received from the terminal 20. For example, the server 10 generates voice data for the user's utterance according to the user's utterance data transmitted by the terminal 20 and information about the user, and transmits the voice data to the terminal 20. The terminal 20 is an information processing device such as a mobile phone, a smartphone, a smart speaker, a PDA (Personal Digital Assistant), a tablet PC, a notebook PC, or a desktop PC.

The server 10 has a communication processing unit 11, a control unit 12, and a storage unit 13. In the following description, an example in which the server 10 has an application function for providing a service for managing the asset balance of the user will be described, but the present invention is not limited to this, and a service for communicating with the user by voice. If so, it can be applied to anything.

The communication processing unit 11 transmits and receives various data to and from the terminal 20 via the network 30. The communication processing unit 11 corresponds to, for example, a NIC or the like, and transmits / receives user voice data to / from the terminal 20. The communication processing unit 11 may, for example, send and receive the voice data itself related to the utterance as the voice data to be transmitted and received to and from the terminal 20, or receive the text data of the voice spoken by the user. , Text data of voice spoken on the terminal 20 side may be transmitted.

The storage unit 13 stores data and programs necessary for various processes by the control unit 12, and particularly closely related to the present invention, the storage unit 13 includes an asset data storage unit 13a and a determination data storage unit 13b. For example, the storage unit 13 is a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory (Flash Memory), or a storage device such as a hard disk or an optical disk.

The asset data storage unit 13a stores the asset balance of each user. For example, the asset data storage unit 13a stores the asset balance in association with the user name, as illustrated in FIG. Specifically, the asset data storage unit 13a stores the asset balance “7,654,321” in association with the user name “A” and the asset balance “B” in association with the user name “B”. 1,541,562 "is memorized. Here, as an example of user information, the case where only the asset balance is stored has been described, but various information such as income and expenditure may also be stored.

The determination data storage unit 13b stores data used when the determination process performed by the determination unit 12b, which will be described later, is executed. For example, the determination data storage unit 13b stores the "number of digits" of the numbers included in the utterance and the "speech time" required for the utterance of the numbers in association with each other.

More specifically, the determination data storage unit 13b stores the utterance time "0.5 seconds" in association with the number of digits "1". This means that it is set to take "0.5 seconds" to speak a one-digit number. Further, the determination data storage unit 13b stores the utterance time "1.2 seconds" in association with the number of digits "2" and stores the utterance time "2.3 seconds" in association with the number of digits "3". Then, the utterance time "3.0 seconds" is stored in association with the number of digits "4".

In the example of FIG. 3, the utterance time is set for each number of digits, but it may be set more finely. For example, in the example of FIG. 3, when the number of digits is 1, the utterance time is set to "0.5 seconds" regardless of whether the number is "0" to "9". The utterance time is different for each of "0" to "9". Therefore, the utterance time may be set for each number.

The control unit 12 has an internal memory for storing a program that defines various processing procedures and required data, and executes various processing by these. However, the control unit 12 is particularly closely related to the present invention. It has a generation unit 12a, a determination unit 12b, and an output unit 12c. Here, the control unit 12 is an electronic circuit such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit), or an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

The generation unit 12a generates voice data to be output to the terminal 20 as a response to the input data received from the terminal 20. For example, when the generation unit 12a receives a question about the asset balance from the terminal 20 as the utterance data of the user A, the generation unit 12a reads out the asset balance "7,654,321" of the user A from the asset data storage unit 13a and costs "7,654,321 yen" (Nanahyaku). Rokujugoman Yonsen Sanbyaku Nijuichien) ”is generated.

In addition, the generation unit 12a uses the estimated value "7,650,000", which omits the lower four digits of "7,654,321", and speaks "about 7.65 million yen (about Nanahyaku Rokujugomanen)". Also generate. Further, when the number is 7 digits, the number of lower digits to be omitted is set in advance, such as omitting the lower 4 digits. It should be noted that the voice data generation method is performed by an existing method, and the description thereof will be omitted here.

When the voice data generated by the generation unit 12a includes a specific utterance, the determination unit 12b determines whether or not the specific utterance satisfies a predetermined condition. Specifically, when the determination unit 12b includes a numerical utterance as a specific utterance among the voice data generated by the generation unit 12a, the determination unit 12b determines whether or not the utterance of the numerical value satisfies a predetermined condition. judge.

For example, the determination unit 12b determines whether or not the ratio of the utterance time of the utterance of the number omitting the lower digit number to the utterance time of the utterance of the number is less than the predetermined threshold value n. Then, the determination unit 12b determines whether or not the difference between the numerical value in the utterance of the numerical value and the numerical value omitting the lower digit number is less than the predetermined threshold value m.

In the following, as a specific example, the voice data to be output when uttering an accurate number without omitting the number is "7,654,321 yen (Nanahyaku Rokujugoman Yonsen Sanbyaku Nijuichien)", which is a number. The case where the voice data to be output when speaking with the approximate value is "Approximately 7.65 million yen (Approximately Nanahyaku Rokujugomanen)" will be explained as an example.

The determination unit 12b determines the utterance time of "7,654,321 (Nanahyaku Rokujugoman)" and the utterance time of "7,650,000 (Nanahyaku Rokujugoman)". Identify by referring to the data stored in. Here, the judgment unit 12b specifies the utterance time of "7,654,321 (Nanahyaku Rokujugoman Yonsen Sanbyaku Nijuichi)" as a 7-digit utterance time, and "7,650,000 (Nanahyaku Rokujugoman)". The utterance time of "" is specified as a three-digit utterance time.

Then, the judgment unit 12b divides the utterance time of "7,650,000 (Nanahyaku Rokujugoman)" by the utterance time of "7,654,321 (Nanahyaku Rokujugoman Yonsen Sanbyaku Nijuichi)" and divides the value. Is less than the threshold value n% (for example, 70%). In the above description, the case where the determination unit 12b specifies the utterance time of the utterance portion of the numerical value by referring to the data stored in the determination data storage unit 13b and makes a determination is described as an example, but the present invention is limited to this. It's not a thing. For example, the judgment unit 12b has the actual utterance time of "7,654,321 yen (Nanahyaku Rokujugoman Yonsen Sanbyaku Nijuichien)" and "Approximately 7.65 million yen (Approximately Nanahyaku Rokujugomanen). It is possible to measure the actual utterance time of ")" and perform the above determination process.

Subsequently, when the divided value is less than the threshold value n, the determination unit 12b subtracts "7,650,000" from "7,654,321" and divides the subtracted value "4,321" by "7,654,321". Then, the determination unit 12b determines whether the divided value is less than the threshold value m (for example, 3%). As a result, when the divided value is less than the threshold value m, the determination unit 12b omits the lower digit of the utterance of the number and omits the voice data "Approximately 7.65 million yen (approximately Nanahyaku Rokujugo). I'm sorry) ”is instructed to the output unit 12c to output to the terminal 20. The determination unit 12b determines whether or not the number included in the utterance is a predetermined digit or more set in advance without using the utterance time or the like, and if it is a predetermined digit or more, the lower digit number. It may be possible to perform a simple process of determining that the audio data in which is omitted is to be output.

When the determination unit 12b determines that the predetermined condition is satisfied, the output unit 12c outputs voice data in which a part of the specific utterance is omitted to the terminal 20. Specifically, when the determination unit 12b determines that the predetermined condition is satisfied, the output unit 12c outputs the voice data in which the lower digit of the utterance of the number is omitted to the terminal 20.

For example, when the ratio of the utterance time of the number obtained by omitting the lower digit to the utterance time of the number taken by the determination unit 12b by the determination unit 12b is less than a predetermined threshold value, the output unit 12c speaks the number. The voice data in which the lower digit is omitted is output to the terminal 20. Further, when the difference between the numerical value in the utterance of the number and the numerical value in which the lower digit number is omitted is less than a predetermined threshold value, the output unit 12c omits the lower digit number in the utterance of the numerical value. The voice data is output to the terminal 20.

To explain using the above example, for example, when the output unit 12c receives an instruction to output the voice data "approximately 7.65 million yen (approximately Nanahyaku Rokujugomanen)" to the terminal 20. Outputs the voice data "Approximately 7.65 million yen (approximately Nanahyaku Rokujugomanen)" to the terminal 20.

Further, the determination unit 12b may determine whether or not the utterance time required for uttering the numbers exceeds a predetermined time. In this case, when the determination unit 12b determines that the utterance time required for uttering the numbers exceeds the predetermined time, the output unit 12c speaks the numbers so that the utterance time is within the predetermined time. The voice data in which the lower digit is omitted is output to the terminal 20.

For example, the determination unit 12b determines whether the utterance time of "7,654,321 yen (Nanahyaku Rokujugoman Yonsen Sanbyaku Nijuichien)" exceeds a predetermined time. Then, when the determination unit 12b determines that the utterance time exceeds a predetermined time, the output unit 12c sets the lower digit of the utterance of the number so that the utterance time is within the predetermined time. The omitted voice data "Approximately 7.65 million yen (approximately Nanahyaku Rokujugomanen)" is output to the terminal 20. In other words, although it depends on the asset balance, it does not make much sense to output the "4,321 yen" part precisely when checking your own asset balance, and it is a waste of time. Outputs an approximate value.

Further, when the output unit 12c receives a request for utterance of an accurate number from the terminal 20 after outputting the voice data in which the lower digit number is omitted to the terminal 20, the output unit 12c omits the lower digit number. Outputs utterances of unnumbered numbers. As for the method of determining the request for utterance of an accurate number, for example, it is performed by determining whether or not a preset word or sentence (for example, "detailed", "detailed number", etc.) is included. And.

Here, an example of outputting an accurate number when a user requests a detailed value after outputting an approximate value will be described with reference to FIG. FIG. 4 is a diagram illustrating an example of outputting an accurate number when a user requests a detailed value after outputting an approximate value. As illustrated in FIG. 4, for example, when the user speaks to the terminal 20 "Tell me the current asset balance", the terminal 20 transmits the voice data spoken by the user to the server 10. Then, after performing the above-mentioned processing, the server 10 transmits the voice data saying "It is about 7.65 million yen (about Nanahyaku Rokujugomanen)" to the terminal 20.

Then, after saying "It is about 7.65 million yen (about Nanahyaku Rokujugomanen)", the terminal 20 accepts the utterance "Details" as a request from the user to utter an accurate number. In this case, the server 10 transmits voice data saying "It is 7,654,321 yen (Nanahyaku Rokujugoman Yonsen Sanbyaku Nijuichien)" as voice data of accurate numbers to the terminal 20.

In the above explanation, an example of the amount of money has been described as a number included in the utterance, but the present invention is not limited to this, and can be applied to time, speed, and the like. For example, "sound velocity (Mach)" is generally defined as 1,225 km / h, but if n = 70% and m = 3% are applied according to the above example, "about 1,200 km / h". Can be made to speak.

Further, in the above description, the case where the number of lower digits to be omitted is set in advance has been described, but the process of determining may be performed according to the threshold value m. Here, a process of determining the number of lower digits to be omitted will be described with reference to FIG. FIG. 5 is a diagram illustrating a processing example for determining the number of lower digits to be omitted. In the example of FIG. 5, the number of lower digits to be omitted when m = 3% is set for the circumference ratio “3.14159265 ...” and when m = 5% is set. The number of lower digits to be omitted is illustrated.

When the approximate value of the circumference ratio "3.14159265 ..." is set to "3", the server 10 subtracts "3" from "3.14159265 ..." and subtracts the subtracted value "0. 14159265 ”is divided by“ 3.14159265 ... ”. Then, in the determination unit 12b, the divided value becomes "0.045 ...", and when the threshold value m = 5%, the value is less than the threshold value, so that the number of lower digits after the first decimal place is omitted. Then it is decided.

On the other hand, when the threshold value m = 3%, the divided value "0.045 ..." exceeds the threshold value m. In this case, the server 10 sets the approximate value of the circumference ratio "3.14159265 ..." to "3.1", subtracts "3.1" from "3.14159265 ...", and subtracts it. The value "0.04159265" is divided by "3.1418265 ...". Then, the determination unit 12b determines that the divided value is "0.13 ..." and the threshold value m is less than 3%, so that the number of lower digits after the second decimal place is omitted. In this way, the process of determining the number of lower digits to be omitted may be performed.

For example, an accurate amount of money can be realized by outputting it in units of 1 yen when visually grasping it. However, in this case, in order to make it easier to read, a comma is added every three digits to make it easier to understand the approximate amount. When realizing UI / UX with a voice device, there is no concept corresponding to this comma, so reading out the amount in units of 1 yen does not lead to correct transmission of information. Therefore, when the predetermined condition is satisfied, the server 10 outputs an approximate value to avoid unnecessary output of a correct numerical value by the voice UI / UX and realize smooth communication between a person and a computer. ..

In the above description, the case where the number of lower digits of the number included in the utterance is omitted has been described, but the present invention is not limited to this, and a part of a specific utterance may be omitted. For example, when the utterance includes "Kasumigaseki-chome, Chiyoda-ku, Tokyo ...", the server 10 transmits voice data to the terminal 20 to say "Chiyoda-ku, Tokyo" for this part. Subsequent "Kasumigaseki ○ chome ..." may be omitted.

[Server processing procedure]
Next, an example of the processing procedure by the server 10 according to the first embodiment will be described with reference to FIG. FIG. 6 is a flowchart showing an example of the flow of processing executed by the server.

First, as illustrated in FIG. 6, when the generation unit 12a of the server 10 receives the input data from the terminal 20 (step S101 affirmative), the generation unit 12a generates the voice data to be output to the terminal 20 (step S102). Then, the determination unit 12b determines whether or not the ratio of the utterance time when the lower digit to the utterance time when an accurate number is spoken is omitted is less than n% (step S103).

As a result, when the determination unit 12b determines that the ratio of the utterance time when the lower digit is omitted to the utterance time when an accurate number is spoken is less than n% (step S103 affirmative), It is determined whether or not the difference between the exact number and the number omitting the lower digit is less than m (step S104).

Subsequently, when the determination unit 12b determines that the difference between the accurate number and the number with the lower digit omitted is less than m (step S104 affirmative), the output unit 12c omits the lower digit number. The voice data is output to the terminal (step S105).

Further, when it is determined that the ratio of the utterance time when the lower digit to the utterance time when the determination unit 12b utters an accurate number is omitted is n% or more (step S103 negation), or when the determination unit 12b When it is determined that the difference between the accurate number and the number omitting the lower digit is m or more (negation of step S104), the output unit 12c outputs the voice data of the accurate number to the terminal 20 (the voice data of the accurate number is output to the terminal 20). Step S106).

[Effect of the first embodiment]
The server 10 of the communication system 100 according to the first embodiment generates voice data to be output to the terminal 20 as a response to the input data received from the terminal 20, and the generated voice data includes a specific utterance. Determines whether or not the particular utterance satisfies a predetermined condition. Then, when it is determined that the predetermined condition is satisfied, the server 10 outputs the voice data in which a part of the specific utterance is omitted to the terminal 20. Therefore, in the server 10, it is possible to omit a specific utterance to the user and to achieve smooth communication by voice UI / UX.

Further, when the server 10 includes a numerical utterance as a specific utterance in the generated voice data, the server 10 determines whether or not the numerical utterance satisfies a predetermined condition, and satisfies the predetermined condition. If it is determined, the voice data in which the lower digit of the utterance of the numerical value is omitted is output to the terminal 20. Therefore, in the server 10, it is possible to shorten the total time required for the response by omitting the lower digit number among the utterances of the number having a large number of digits, and to achieve smooth communication.

That is, in the voice UI / UX, it is possible to shorten the total time required for the response and improve the intuitive understanding of the user. In the past, accuracy was ensured by always reading out accurate numerical values. However, in voice UI / UX, it is not always desirable to read aloud accurately, and there are cases where it is faster and easier to understand when an approximate estimated value is output. Also, in communication between people, there are many examples of facilitating communication by using ambiguous expressions such as "roughly" and "approximate". In the communication system 100 according to the first embodiment, as a part of bringing a computer closer to a human being, the introduction of "ambiguity" brings about the effect of facilitating communication.

Further, the server 10 determines whether or not the ratio of the utterance time of the number obtained by omitting the lower digit to the utterance time of the number is less than the predetermined threshold value, and the ratio is the predetermined threshold value. If it is less than, the voice data in which the lower digit of the utterance of the number is omitted is output to the terminal 20. Therefore, since the lower digit number is omitted only when the number is shorter than a certain percentage of the time when the correct number is spoken, the total time required for the response can be effectively shortened.

Further, the server 10 determines whether or not the difference between the numerical value in the utterance of the numerical value and the numerical value omitting the lower digit number is less than a predetermined threshold value, and if the difference is less than a predetermined threshold value, the server 10 determines. , The voice data in which the lower digit of the utterance of the number is omitted is output to the terminal 20. Therefore, if the difference between the accurate value and the estimated value is larger than a certain value, the value is not omitted, and only when the difference is less than a certain value, the lower digit number is omitted. It is possible to achieve smooth communication without using.

Further, the server 10 determines whether or not the utterance time required to speak the numbers exceeds a predetermined time, and if it is determined that the utterance time required to speak the numbers exceeds the predetermined time, the utterance time is determined. The voice data in which the lower digit of the utterance of the number is omitted is output to the terminal 20 so as to be within a predetermined time. For this reason, only when it is determined that the predetermined time is exceeded when an accurate number is spoken, the lower digit number is omitted, so if the speech time required for the number to be spoken becomes long, it will take a response. It is possible to effectively reduce the total time.

Further, when the server 10 receives a request for utterance of an accurate number from the terminal 20 after outputting the voice data in which the lower digit number is omitted to the terminal 20, the server 10 omits the lower digit number. Outputs no number utterances. Therefore, it is possible to output the correct numerical value only when the user wants to know the detailed numerical value.

[System configuration, etc.]
Further, each component of each of the illustrated devices is a functional concept, and does not necessarily have to be physically configured as shown in the figure. That is, the specific form of distribution / integration of each device is not limited to the one shown in the figure, and all or part of them may be functionally or physically distributed / physically distributed in any unit according to various loads and usage conditions. Can be integrated and configured. For example, the functions of the generation unit 12a, the determination unit 12b, and the output unit 12c of the server 10 may be distributed and held by a plurality of servers. Further, each processing function performed by each device is realized by a CPU or GPU (Graphics Processing Unit) and a program analyzed and executed by the CPU or GPU, or is wired. It can be realized as hardware by logic.

Further, among the processes described in the present embodiment, all or part of the processes described as being automatically performed can be manually performed, or the processes described as being manually performed. It is also possible to automatically perform all or part of the above by a known method. In addition, the processing procedure, control procedure, specific name, and information including various data and parameters shown in the above document and drawings can be arbitrarily changed unless otherwise specified.

[program]
It is also possible to create a program in which the processing executed by the server 10 described in the above embodiment is described in a language that can be executed by a computer. For example, it is possible to create a communication program in which the processing executed by the server 10 according to the embodiment is described in a language that can be executed by a computer. In this case, when the computer executes the communication program, the same effect as that of the above embodiment can be obtained. Further, the same processing as that of the above embodiment may be realized by recording the communication program on a computer-readable recording medium, reading the communication program recorded on the recording medium into the computer, and executing the program.

FIG. 7 is a diagram showing a computer that executes a communication program. As illustrated in FIG. 7, the computer 1000 has, for example, a memory 1010, a CPU 1020, a hard disk drive interface 1030, a disk drive interface 1040, a serial port interface 1050, a video adapter 1060, and a network interface 1070. However, each of these parts is connected by a bus 1080.

The memory 1010 includes a ROM (Read Only Memory) 1011 and a RAM 1012, as illustrated in FIG. The ROM 1011 stores, for example, a boot program such as a BIOS (Basic Input Output System). The hard disk drive interface 1030 is connected to the hard disk drive 1090, as illustrated in FIG. The disk drive interface 1040 is connected to the disk drive 1100 as illustrated in FIG. For example, a removable storage medium such as a magnetic disk or an optical disk is inserted into the disk drive 1100. The serial port interface 1050 is connected to, for example, a mouse 1110 and a keyboard 1120, as illustrated in FIG. The video adapter 1060 is connected, for example, to a display 1130, as illustrated in FIG.

Here, as illustrated in FIG. 7, the hard disk drive 1090 stores, for example, the OS 1091, the application program 1092, the program module 1093, and the program data 1094. That is, the above-mentioned communication program is stored in, for example, the hard disk drive 1090 as a program module in which a command executed by the computer 1000 is described.

Further, the various data described in the above embodiment are stored as program data in, for example, a memory 1010 or a hard disk drive 1090. Then, the CPU 1020 reads the program module 1093 and the program data 1094 stored in the memory 1010 and the hard disk drive 1090 into the RAM 1012 as needed, and executes various processing procedures.

The program module 1093 and program data 1094 related to the communication program are not limited to those stored in the hard disk drive 1090, and may be stored in, for example, a removable storage medium and read by the CPU 1020 via a disk drive or the like. good. Alternatively, the program module 1093 and the program data 1094 related to the communication program are stored in another computer connected via a network (LAN (Local Area Network), WAN (Wide Area Network), etc.), and are stored in another computer via the network interface 1070. It may be read by the CPU 1020.

The above-described embodiments and modifications thereof are included in the invention described in the claims and the equivalent scope thereof, as included in the technology disclosed in the present application.

10 Server 11 Communication processing unit 12 Control unit 12a Generation unit 12b Judgment unit 12c Output unit 13 Storage unit 13a Asset data storage unit 13b Judgment data storage unit 20 Terminal 30 Network 100 Communication system

Claims (7)

As a response to the input data received from the terminal, a generation unit that generates voice data to be output to the terminal, and a generation unit.
When the voice data generated by the generation unit includes a specific utterance, a determination unit for determining whether or not the specific utterance satisfies a predetermined condition, and a determination unit.
When the determination unit determines that a predetermined condition is satisfied, it has an output unit that outputs voice data to the terminal by omitting a part of the specific utterance.
When the specific utterance includes the utterance of a number among the voice data generated by the generation unit, the determination unit determines whether or not the utterance of the number satisfies a predetermined condition.
The communication unit is characterized in that, when it is determined by the determination unit that a predetermined condition is satisfied, the output unit outputs voice data in which the lower digit of the utterance of the number is omitted to the terminal. system. The determination unit determines whether or not the ratio of the utterance time of the number obtained by omitting the lower digit to the utterance time of the number is less than a predetermined threshold value.
The output unit is characterized in that when the ratio is less than a predetermined threshold value by the determination unit, the output unit outputs voice data in which the lower digit of the utterance of the number is omitted to the terminal. The communication system according to Item 1 . The determination unit determines whether or not the difference between the numerical value in the utterance of the numerical value and the numerical value omitting the lower digit number is less than a predetermined threshold value.
The output unit is characterized in that when the difference is less than a predetermined threshold value by the determination unit, the output unit outputs voice data in which the lower digit of the utterance of the number is omitted to the terminal. The communication system according to Item 1 . The determination unit determines whether or not the utterance time required for utterance of the number exceeds a predetermined time.
When the determination unit determines that the utterance time for uttering the number exceeds a predetermined time, the output unit determines that the utterance time is within the predetermined time. The communication system according to claim 1 , wherein voice data in which the lower digit is omitted is output to the terminal. When the output unit receives a request for utterance of an accurate number from the terminal after outputting voice data in which the lower digit number is omitted to the terminal, the output unit omits the lower digit number. The communication system according to claim 1 , wherein the utterance of an unnumbered number is output. A communication method performed by a communication system,
A generation step of generating voice data to be output to the terminal as a response to the input data received from the terminal, and
When the voice data generated by the generation step includes a specific utterance, a determination step of determining whether or not the specific utterance satisfies a predetermined condition, and a determination step.
When it is determined by the determination step that a predetermined condition is satisfied, the output step of outputting voice data in which a part of the specific utterance is omitted to the terminal is included.
When the specific utterance includes the utterance of a number among the voice data generated by the generation step, the determination step determines whether or not the utterance of the number satisfies a predetermined condition.
The output step is a communication characterized in that, when it is determined by the determination step that a predetermined condition is satisfied, voice data in which the lower digit of the utterance of the number is omitted is output to the terminal. Method. As a response to the input data received from the terminal, a generation step of generating voice data to be output to the terminal, and a generation step.
When the voice data generated by the generation step includes a specific utterance, a determination step for determining whether or not the specific utterance satisfies a predetermined condition, and a determination step.
When it is determined by the determination step that the predetermined condition is satisfied, the computer is made to execute the output step of outputting the voice data in which a part of the specific utterance is omitted to the terminal .
In the determination step, when the specific utterance includes the utterance of a number among the voice data generated by the generation step, it is determined whether or not the utterance of the number satisfies a predetermined condition.
The output step is a communication characterized in that, when it is determined by the determination step that a predetermined condition is satisfied, voice data in which the lower digit of the utterance of the number is omitted is output to the terminal. program.

Images