JP6494828B1 - Management device, management method and management program - Google Patents

Abstract

A management apparatus, management method and management program capable of easily identifying a user and receiving an order by voice are provided. A management apparatus 1 according to the present invention includes a reception unit 12a, an identification unit 12b, and a specification unit 12d. The receiving unit 12a receives an input of voice by the user. The identification unit 12 b identifies the user using the voice accepted by the acceptance unit 12 a. The identifying unit 12d identifies the order content using the voice accepted by the accepting unit 12a. [Selected figure] Figure 2

Description

  The present invention relates to a management apparatus, a management method, and a management program.

  2. Description of the Related Art Conventionally, techniques for receiving user's orders by voice recognition are known. For example, there is known a technology for receiving by voice the order of food in a cafeteria or an order for a product listed in a catalog, and identifying the food or product by voice recognition and capturing it as order information.

Unexamined-Japanese-Patent No. 2013-054442 JP, 2014-191600, A

  However, in the prior art, when receiving a food or product order by voice, the user who made the order is not identified. Therefore, for example, a plurality of orders with different dates and times by the same user accepted by voice can not be totaled for each user and settled later.

  This application is made in view of the above, and an object of the present application is to provide a management device, a management method, and a management program capable of easily identifying a user and receiving an order by voice.

  A management apparatus according to the present application uses a reception unit that receives an input of a user's voice, an identification unit that identifies the user using the voice received by the reception unit, and the voice received by the reception unit. And an identifying unit for identifying the contents of the user's order.

  According to one aspect of the embodiment, it is possible to easily identify the user and receive an order by voice.

FIG. 1 is a diagram illustrating an example of management processing according to the embodiment. FIG. 2 is a diagram showing an example of the configuration of a management apparatus according to the embodiment. FIG. 3 is a diagram illustrating an example of the identification model according to the embodiment. FIG. 4 is a diagram illustrating an example of a specific model according to the embodiment. FIG. 5 is a diagram showing an example of the settlement information according to the embodiment. FIG. 6 is a flowchart showing a management processing procedure executed by the management device according to the embodiment. FIG. 7 is a flowchart showing a management processing procedure executed by a management apparatus according to another embodiment. FIG. 8 is a hardware configuration diagram showing an example of a computer that implements the function of the management apparatus according to the embodiment.

  Hereinafter, a management apparatus, a management method, and a mode for implementing a management program according to the present application (hereinafter, referred to as “embodiment”) will be described in detail with reference to the drawings. Note that the management apparatus, management method, and management program according to the present application are not limited by this embodiment. Moreover, the same code | symbol is attached | subjected to the same site | part in the following each embodiment, and the overlapping description is abbreviate | omitted.

(Embodiment)
[1. Management processing]
First, an example of a management process according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of management processing according to the embodiment. As shown in FIG. 1, the management apparatus according to the embodiment performs management processing for identifying the user and receiving the order content using the voice of the user indicating the order content such as the menu name and the quantity.

  FIG. 1 exemplifies the case where the order content is the menu name “curry rice”. As shown in FIG. 1, when the user utters the menu name "curry rice" using a microphone provided in the management apparatus (step S1), the management apparatus identifies the user using, for example, a voiceprint or the like.

  Next, the management device specifies the menu name by speech recognition of the menu name "curry rice" uttered by the user. Then, the management apparatus confirms the order using the specified menu name. Thus, the management apparatus can easily identify the user and accept the order only by the user uttering the contents of the order.

  Further, the management apparatus associates the date and time of the received order and the menu name with the user ID (IDentification) which is identification information of the user, generates the adjustment information 13e, and stores the information in the storage unit. The management apparatus counts the settlement information 13e for each user ID, and settles the price according to the contents of the user's order by a predetermined settlement method such as account withdrawal or credit card payment. As described above, the management apparatus adds up a plurality of orders of different dates and times by the same user accepted by voice, and settles them after each user.

  In the management apparatus, an identification model representing a feature of biological information such as a voiceprint of a user is stored in the storage unit in association with a user ID. The management apparatus confirms the user identification result to the user by voice or GUI (Graphical User Interface) or the like, generates learning data (identification learning data) of the identification model using the user's response result, and stores it in the storage unit . Then, the management device learns the identification model using the generated identification learning data.

  Further, in the management device, a specific model for specifying a menu name by voice recognition is stored in advance in a storage unit. The management apparatus confirms the identification result of the menu name to the user by voice or GUI, and generates the learning data (the identification data for identification) of the specific model using the response result of the user, and stores it in the storage unit. Then, the management device learns a specific model using the generated specific learning data.

[2. Configuration of Management Device]
Next, the management apparatus 1 will be described with reference to FIG. FIG. 2 is a view showing a configuration example of the management device 1 according to the embodiment. As shown in FIG. 2, the management device 1 includes an input / output unit 11, a control unit 12, and a storage unit 13.

(About the input / output unit 11)
The input / output unit 11 is realized by an input device such as a microphone, a camera, a fingerprint sensor, a keyboard, or a mouse, and an output device such as a display or a printer. For example, the user's voice, face image, iris, fingerprint or the like is input to the input / output unit 11.

  The management apparatus 1 includes a communication unit realized by an NIC (Network Interface Card) or the like, and transmits / receives information to / from a terminal device used by a user having a microphone, a camera, a display, etc. via the communication unit. You may

(About storage unit 13)
The storage unit 13 is realized by, for example, a semiconductor memory device such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 2, the storage unit 13 stores the identification model 13 a and the specific model 13 b. The storage unit 13 also stores identification learning data 13c, identification learning data 13d, and settlement information 13e generated by management processing described later.

(About the identification model 13a)
The identification model 13a is a model that represents a feature of biological information such as a voiceprint of the user, and is stored in advance in the storage unit 13 in association with the user ID. In the management process described later, the user is identified using the voice of the user and the identification model 13a. The biometric information of the user is not limited to the voiceprint, and may be, for example, a face image, an iris or a fingerprint.

  FIG. 3 is a diagram showing an example of the identification model 13a. FIG. 3 exemplifies the case where the biometric information of the user is a voiceprint. As shown in FIG. 3, the identification model 13a in this case is one in which voiceprint information is associated with a user ID for identifying a user. In other words, the identification model 13a is the voiceprint information to which the tag of the user ID is added as the teacher label.

(About the specific model 13b)
The specific model 13 b is a model for specifying the order content by voice recognition, and is stored in advance in the storage unit 13. In the management process described later, the order content is specified using the voice of the user and the specific model 13b.

  FIG. 4 is a diagram showing an example of the specific model 13 b. FIG. 4 exemplifies the case where the order content is a menu name. In the specific model 13b in this case, as shown in FIG. 4, a tag of a menu name such as "apple" is attached to voice data as a teacher label.

(About identification learning data 13c)
The identification learning data 13c is learning data for generating the identification model 13a, and the user responds to the confirmation of the user identification result indicating the correct or incorrect answer to the identification result by the identification unit 12b in the management process described later. It is generated using the result. The identification model 13a is generated using the identification learning data 13c, and the identification model 13a is updated.

(About the specific learning data 13d)
The identification learning data 13d is learning data for generating the specific model 13b, and in the management process described later, the user's confirmation of the identification result of the order content, which indicates the correct or incorrect answer to the identification result by the identification unit 12d. It is generated using the response result. The specific model 13b is generated using the identification learning data 13d, and the specific model 13b is updated.

(About settlement information 13e)
The settlement information 13 e is information generated in association with the identified user content of the identified user and the identified order content in the management process described later. FIG. 5 is a diagram showing an example of the adjustment information 13e according to the embodiment. As shown in FIG. 5, the settlement information 13 e is information in which “user ID”, “date and time”, “menu” and the like are associated with one another. FIG. 5 exemplifies the case where the order content is a menu name. The order content may include, in addition to the menu name, for example, information representing a quantity such as "one plate" or "large size".

  The “user ID” is user identification information that identifies the user, such as the name and membership number. "Date" indicates the date when the settlement information 13e was generated. The “menu name” indicates, for example, a menu name in a cafeteria or the like. In the example shown in FIG. 1, as shown in FIG. 5, the settlement information 13e with the user ID "A", the date and time "o month x day Δ hour square minute", and the menu name "curry rice" is generated. It is stored in the storage unit 13.

(About the control unit 12)
It returns to the explanation of FIG. The control unit 12 is a controller, and for example, various programs (an example of a management program stored in a storage device in the management apparatus 1 by a central processing unit (CPU), a micro processing unit (MPU), etc. (Equivalent) is realized by executing the RAM as a work area. Further, the control unit 12 is realized by, for example, an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

  As shown in FIG. 2, the control unit 12 includes a reception unit 12a, an identification unit 12b, an identification learning unit 12c, an identification unit 12d, an identification learning unit 12e and a settlement unit 12f, and functions of management processing described below Realize or carry out the action.

(About reception part 12a)
The receiving unit 12a receives an input of voice by the user. Specifically, the reception unit 12 a receives the voice of the user input from the microphone via the input / output unit 11. Further, the reception unit 12a may receive an input such as a face image or iris of a user photographed by a camera, or a fingerprint of the user acquired by a fingerprint sensor.

(About the identification unit 12b)
The identification unit 12 b identifies the user using the voice accepted by the acceptance unit 12 a. Specifically, the identification unit 12 b identifies the user using the voice indicating the order content received by the reception unit 12 a and the identification model 13 a indicating a feature such as a voiceprint of the user.

  Here, the identification unit 12b extracts a feature such as a voiceprint from speech uttering an arbitrary word, compares the extracted voiceprint information with the identification model 13a, and identifies the user by specifying the user ID.

  Alternatively, the identification unit 12b may identify the user using a predetermined term by the user. For example, the user may be identified by the utterance of a predetermined term common to all users, such as "Please" other than the order content. In that case, the receiving unit 12a receives an input of voice indicating a predetermined term. In addition, the identification model 13a in this case corresponds to voice data of a predetermined term and a user ID. The identification unit 12 b identifies the user by identifying the user ID by comparing the received voice data with the identification model 13 a.

  Further, as described above, the biometric information of the user represented by the identification model 13a is not limited to the voiceprint, and may be a face image, an iris, a fingerprint, or the like. In that case, for example, when the user utters the order content, the reception unit 12a receives, via the input / output unit 11, the face image or iris photographed by the camera, the fingerprint acquired by the fingerprint sensor, etc. Is realized by

  The identification unit 12b confirms the identification result to the user, and receives a response. For example, a message confirming the identification result such as “Are you A?” Is output to the input / output unit 11, and a response “Yes” or “No” is accepted via the input / output unit 11. For example, the identification unit 12 b displays a message of confirmation of the identification result on the touch panel display, and receives an operation input of a user who selects one of “Yes” and “No”. A message of confirmation of the identification result may be output by voice, or the user may receive an input of a voice response of either “Yes” or “No”.

  If the identification result is incorrect, the process of identifying the user is repeated until the correct answer is obtained. Here, the correct answer means that the identification result is correct, for example, a response indicating “Yes” is obtained from the user. On the other hand, if the identification result is incorrect, for example, a response indicating “No” is obtained from the user, it is incorrect. Further, the confirmation of the identification result may be performed, for example, when the accuracy of the identification is lower than a predetermined threshold.

  Further, the identification unit 12 b generates identification learning data 13 c using the voice accepted by the acceptance unit 12 a and the user's response result, and stores the identification learning data 13 c in the storage unit 13. The identification learning data 13c may be either correct teacher data or incorrect teacher data.

  Further, as for identification of the user, it is desirable that identification is performed using combination authentication with a second method using information other than the biometric information used for user identification such as face authentication when voice print is performed. For example, the success rate of identification by voiceprint is about 80%, while the identification by combination authentication improves the success rate. Alternatively, it is desirable that there is a correction mechanism such as confirmation of facts by e-mail afterward.

(About the identification learning unit 12c)
The identification learning unit 12c generates an identification model 13a for identifying the user using the voice accepted by the accepting unit 12a, using the identification learning data 13c indicating the correct or incorrect answer to the identification result by the identifying unit 12b. Do. Specifically, the identification learning unit 12c performs learning using the identification learning data 13c, and updates the identification model 13a of the storage unit 13. In that case, the identification unit 12b identifies the user using the speech accepted by the acceptance unit 12a and the identification model 13a updated by learning.

(About the identification unit 12d)
The identifying unit 12d identifies the order content using the voice accepted by the accepting unit 12a. Specifically, the identification unit 12 b identifies the order content using the voice accepted by the acceptance unit 12 a and the specific model 13 b. The order content is, for example, a menu name as described above. The order content may include, in addition to the menu name, for example, predetermined information representing a quantity such as “one plate” or “large plate”.

  The identification unit 12 d confirms the identification result to the user, and receives a response. For example, a message confirming the specific result such as "is curry rice?" Is output to the input / output unit 11, and a response of either "Yes" or "No" is accepted via the input / output unit 11. For example, the identifying unit 12 d displays a message of confirmation of the identification result on the touch panel display, and receives an operation input of a user who selects one of “Yes” and “No”. A message of confirmation of the specific result may be output by voice, or the user may receive an input of a voice response of either “Yes” or “No”.

  If the specified result is incorrect, the process of specifying the order content is repeated until the correct result is obtained. Here, the correct answer means that the specific result is correct, for example, a response indicating “Yes” is obtained from the user. On the other hand, if the specific result is incorrect and, for example, a response indicating "No" is obtained from the user, it is incorrect. Further, the confirmation of the identification result may be performed, for example, when the identification accuracy is lower than a predetermined threshold.

  Further, the identification unit 12 d generates the identification learning data 13 d using the voice accepted by the acceptance unit 12 a and the response result of the user, and stores the same in the storage unit 13. The identification learning data 13 d may be either correct teacher data or incorrect teacher data.

(About the specific learning unit 12e)
The specific learning unit 12e uses the identification learning data 13d indicating the correct or incorrect answer to the identification result by the identification unit 12d, and uses the voice accepted by the accepting unit 12a to identify the specific model 13b for identifying the order content. Generate Specifically, the specific learning unit 12 e performs learning using the specific learning data 13 d and updates the specific model 13 b of the storage unit 13. In that case, the specifying unit 12d specifies the order content using the voice received by the receiving unit 12a and the specific model 13b updated by learning.

(Regarding the settlement unit 12f)
The settlement unit 12f uses the settlement information 13e in which the identification information of the user identified by the identification unit 12b is associated with the order content identified by the identification unit 12d, and settles the price according to the order content. Specifically, the settlement unit 12 f associates the user ID of the user identified by the identification unit 12 b with the order content identified by the identification unit 12 d to generate the adjustment information 13 e, and stores the information in the storage unit 13. Do.

  Further, the settlement unit 12f aggregates the accumulated settlement information 13e for each user ID at a predetermined timing such as when the user leaves the store or at the end of the month, and calculates the price according to the contents of the user's order. Then, the settlement unit 12f performs settlement of the calculated charges for each user according to a predetermined settlement method such as account debiting and credit card payment, which are pre-arranged with the user. As a result, it becomes possible to count up a plurality of orders with different dates and times by the same user accepted by voice and to settle them later for each user.

[3. Processing procedure]
Next, processing procedures executed by the management device 1 according to the embodiment will be described with reference to FIG. FIG. 6 is a flowchart showing a management processing procedure executed by the management device 1 according to the embodiment.

  As shown in FIG. 6, in the management device 1, the reception unit 12a stands by until the user speaks the order contents toward the microphone installed in the cafeteria or the like (Step S1, No). When the receiving unit 12a receives an input of the user's voice (Step S1, Yes), the identifying unit 12b identifies the user using the voiceprint of the voice received by the receiving unit 12a (Step S2). Further, the identification unit 12b outputs a message for confirming the identification result to the user (step S3), and receives a response (step S4). Further, the identification unit 12 b generates identification learning data 13 c using the user's response result, and stores the identification learning data 13 c in the storage unit 13 (step S 5).

  If the identification result of the user is correct, the identification unit 12d identifies the order content uttered by the user by voice recognition (step S6). Further, the identifying unit 12d outputs a message for confirming the identification result to the user (step S7), and receives a response (step S8). Further, the identification unit 12d generates identification learning data 13d using the user's response result, and stores the identification learning data 13d in the storage unit 13 (step S9).

  If the identification result of the user and the identification result of the order content are correct (step S10, Yes), the identifying unit 12d advances the process to step S11. On the other hand, when either of the user identification result and the specification result of the order content is incorrect and both are not correct (step S10, No), the identifying unit 12d returns the process to step S1.

  In the process of step S11, the settlement unit 12f associates the user ID of the user identified by the identification unit 12b with the order content identified by the identification unit 12d to generate the adjustment information 13e, and the storage unit 13 It accumulates (step S11). Further, the settlement unit 12f aggregates the accumulated settlement information 13e for each user ID at a predetermined timing, and calculates a payment according to the content of the user's order. Then, the settlement unit 12f settles the calculated payment for each user according to a predetermined settlement method previously determined with the user (step S12). Thus, the series of management processing ends.

  If the identification result of the user is incorrect, the identification unit 12b repeats the process of identifying the user until the correct answer is obtained. Further, the confirmation of the identification result may be performed, for example, when the accuracy of the identification is lower than a predetermined threshold.

  Further, at a predetermined timing, the identification learning unit 12c performs learning using the stored identification learning data 13c, and updates the identification model 13a of the storage unit 13. The identification unit 12 b identifies the user using the updated identification model 13 a in the subsequent processing.

  If the specification result of the order content is incorrect, the specification unit 12d repeats the process of specifying the order content until the correct result is obtained. Confirmation of the specific result may be performed, for example, when the specific accuracy is lower than a predetermined threshold.

  Further, at a predetermined timing, the specific learning unit 12 e performs learning using the accumulated specific learning data 13 d and updates the specific model 13 b of the storage unit 13. The specifying unit 12d specifies the order content using the updated specific model 13b in the subsequent processing.

  Further, the processing order of the process relating to user identification (steps S2 to S5) and the process relating to order content identification (steps S6 to S9) is not limited to the above. For example, processing related to user identification may be performed after processing related to order content identification. Alternatively, as shown in FIG. 7, the process relating to user identification and the process relating to order identification may be performed in parallel.

  FIG. 7 is a flowchart showing a management processing procedure executed by the management device 1 according to another embodiment. The management process shown in FIG. 7 differs from FIG. 6 in that the process relating to user identification (steps S2 to S5) and the process relating to order specification (steps S6 to S9) are performed in parallel. The other processing contents are the same as those in FIG.

[4. effect〕
As described above, the management device 1 according to the embodiment includes the reception unit 12a, the identification unit 12b, and the identification unit 12d. The receiving unit 12a receives an input of voice by the user. The identification unit 12 b identifies the user using the voice accepted by the acceptance unit 12 a. The identifying unit 12d identifies the order content using the voice accepted by the accepting unit 12a. This makes it possible to easily identify the user and receive an order by voice.

  The management device 1 according to the embodiment further includes the identification learning unit 12c. The identification learning unit 12c generates an identification model 13a for identifying the user using the voice accepted by the accepting unit 12a, using the identification learning data 13c indicating the correct or incorrect answer to the identification result by the identifying unit 12b. Do. In that case, the identification unit 12 b identifies the user using the voice accepted by the acceptance unit 12 a and the identification model 13 a generated by the identification learning unit 12 c. This makes it possible to improve the accuracy of user identification.

  The management device 1 according to the embodiment further includes a specific learning unit 12e. The specific learning unit 12e uses the identification learning data 13d indicating the correct or incorrect answer to the identification result by the identification unit 12d, and uses the voice accepted by the accepting unit 12a to identify the specific model 13b for identifying the order content. Generate In that case, the identification unit 12d identifies the order content using the voice accepted by the acceptance unit 12a and the identification model 13b generated by the identification learning unit 12e. This makes it possible to improve the accuracy of voice recognition for specifying the order content.

  The management device 1 according to the embodiment further includes a settlement unit 12 f. The settlement unit 12f uses the settlement information 13e in which the identification information of the user identified by the identification unit 12b is associated with the order content identified by the identification unit 12d, and settles the price according to the order content. As a result, it is possible to count and order later a plurality of orders having different dates and times by the same user accepted by voice. Thus, the convenience of the user can be further improved.

  In addition, in the management device 1 according to the embodiment, the receiving unit 12a further receives an input of voice indicating a predetermined term by the user. In that case, the identification unit 12b identifies the user using the predetermined term. This makes it possible to reduce user identification errors.

  In addition, in the management device 1 according to the embodiment, the receiving unit 12a further receives an input of biological information other than the voice of the user. In that case, the identification unit 12b identifies the user using the biometric information of the user instead of the voice. Thereby, it becomes possible to apply the system of a suitable user identification according to the use condition of the management apparatus 1. FIG.

[5. Hardware configuration]
Further, the management device 1 according to the embodiment described above is realized by, for example, a computer 1000 configured as shown in FIG. FIG. 8 is a hardware configuration diagram showing an example of a computer 1000 for realizing the function of the management device 1 according to the embodiment. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

  The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400 to control each part. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 starts up, a program depending on the hardware of the computer 1000, and the like.

  The HDD 1400 stores a program executed by the CPU 1100, data used by the program, and the like. The communication interface 1500 receives data from another device via the network N and sends it to the CPU 1100, and transmits data generated by the CPU 1100 to the other device via the network N.

  The CPU 1100 controls an output device such as a display or a printer and an input device such as a keyboard or a mouse via the input / output interface 1600. The CPU 1100 acquires data from an input device via the input / output interface 1600. The CPU 1100 also outputs the generated data to the output device via the input / output interface 1600.

  The media interface 1700 reads a program or data stored in the recording medium 1800 and provides the CPU 1100 with the program via the RAM 1200. The CPU 1100 loads such a program from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a digital versatile disc (DVD) or a phase change rewritable disc (PD), a magneto-optical recording medium such as a magneto-optical disk (MO), a tape medium, a magnetic recording medium, or a semiconductor memory. Etc.

  For example, when the computer 1000 functions as the management device 1 according to the embodiment, the CPU 1100 of the computer 1000 realizes the function of the control unit 12 by executing a program loaded on the RAM 1200. Further, data in the storage unit 13 is stored in the HDD 1400. The CPU 1100 of the computer 1000 reads these programs from the recording medium 1800 and executes them, but as another example, these programs may be acquired from another device via the network N.

  Although some of the embodiments of the present application have been described above in detail based on the drawings, these are only examples, and various modifications can be made based on the knowledge of those skilled in the art, including the aspects described in the section of the description of the invention. It is possible to implement the invention in other improved forms.

[6. Other]
Further, among the processes described in the above embodiment, all or part of the process described as being automatically performed may be manually performed, or the process described as being manually performed. All or part of them can be performed automatically by known methods. In addition, information including processing procedures, specific names, various data and parameters shown in the above-mentioned documents and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

  Further, each component of each device illustrated is functionally conceptual, and does not necessarily have to be physically configured as illustrated. That is, the specific form of the distribution and integration of each device is not limited to the illustrated one, and all or a part thereof may be functionally or physically dispersed in any unit depending on various loads, usage conditions, etc. It can be integrated and configured.

  In addition, the processes described in the above-described embodiment can be appropriately combined within the range in which the process contents do not contradict each other.

  Also, the "section (module, unit)" described above can be read as "means" or "circuit". For example, the receiving unit 12a can be read as a receiving unit or a receiving circuit.

Reference Signs List 1 management apparatus 11 input / output unit 12 control unit 12a reception unit 12b identification unit 12c identification learning unit 12d identification unit 12e identification learning unit 12e settlement unit 13 storage unit 13a identification model 13b identification model 13c learning data for identification 13d identification learning data 13e Settlement information

Claims (6)

A reception unit that receives an input of voice from a user;
Identify the user using the voice accepted by the accepting unit, the estimation result estimated by the identification model for identifying the user, and the response result of the user indicating the correct or incorrect answer to the estimation result The identification unit to
Specify the order content using the voice received by the reception unit, the estimation result estimated by the specific model for specifying the order content, and the user's response result indicating the correct or incorrect answer to the estimation result A specific part to
An identification learning unit that generates the identification model using the voice received by the receiving unit, the estimation result, and a response result of the user;
Specification that generates a specific model for specifying order content using the voice by the predetermined user accepted by the reception unit, the estimation result corresponding to the predetermined user, and the response result of the predetermined user Learning department,
A management apparatus comprising: It further comprises a settlement unit which settles the payment according to the order content using the settlement information in which the identification information of the user identified by the identification unit is associated with the order content identified by the identification unit. the apparatus according to claim 1, characterized in that. The receiving unit further receives an input of voice indicating a predetermined term by a user,
The identification unit, the management apparatus according to claim 1 or 2, wherein the identifying the user by using the given language. The reception unit further receives an input of biological information other than the voice of the user,
The identification unit, the management apparatus according to claim 1 or 2, characterized in that identifying the user using the biometric information of the user instead of the voice. A computer implemented management method, which
A reception process for receiving an input of voice by a user;
Identify the user using the voice accepted in the accepting step, the estimation result estimated by the identification model for identifying the user, and the response result of the user indicating the correct or incorrect answer to the estimation result Identification process,
Specify the order content using the voice received in the reception process, the estimation result estimated by the specific model for specifying the order content, and the user response result indicating the correct or incorrect answer to the estimation result The specific process to
An identification learning step of generating the identification model using the voice accepted by the accepting step, the estimation result, and a response result of the user;
Specification that generates a specific model for specifying order content using voice of a predetermined user accepted by the reception process, the estimation result corresponding to the predetermined user, and the response result of the predetermined user Learning process,
Management method characterized by including. A reception procedure for receiving an input of voice from a user;
Identify the user using the speech accepted in the acceptance procedure, the estimation result estimated by the identification model for identifying the user, and the response result of the user indicating the correct or incorrect answer to the estimation result Identification procedure to
Specify the order content using the voice received in the reception procedure, the estimation result estimated by the specific model for identifying the order content, and the user's response result indicating the correct or incorrect answer to the estimation result Specific procedures to
An identification learning procedure for generating the identification model using the voice accepted by the accepting procedure, the estimation result, and the response result of the user;
Specification that generates a specific model for specifying order content using the voice by a predetermined user accepted by the acceptance procedure, the estimation result corresponding to the predetermined user, and the response result of the predetermined user Learning procedure,
A management program that causes a computer to execute.