JP7041434B2 - Artificial intelligence speaker system, application software - Google Patents

Description

The present invention relates to an artificial intelligence speaker system including a microphone, a speaker, a communication means, an artificial intelligence control means having a learning function, and a database, and application software.

Traditionally, it comprises at least one processor implemented to execute computer-readable instructions, where at least one processor selects question data and accounts for at least one of the users registered with the messaging service. Confirmed the communication session set up between and the artificial intelligence account registered in the messaging service, and sent the question data to at least one user through the communication session confirmed as an instant message of the artificial intelligence account and confirmed. Artificial intelligence learning systems are known that receive response data to question data from at least one user through a communication session and generate training data for artificial intelligence based on the question data and the received response data (eg, patents). Document 1).

Japanese Unexamined Patent Publication No. 2017-153078

However, since the conventional artificial intelligence learning system described above has a configuration in which the artificial intelligence and the user interact with each other by text data via a terminal to learn the artificial intelligence, there is a problem that it is difficult for the artificial intelligence to grasp the intention of the user. was there.

Therefore, the present invention solves the problems of the prior art as described above, that is, the object of the present invention is an artificial intelligence that grasps the intention of the voice input person and executes the desired content of the voice input person. To provide intelligent speaker systems and application software.

The invention according to claim 1 is an artificial intelligence speaker system including a microphone, a speaker, a communication means, an artificial intelligence control means having a learning function, and a database, and is configured to be freely linked with a digital signage terminal. The artificial intelligence control means reads out the content of the current display content using the speaker based on the data of the current display content of the digital signage terminal, and the artificial intelligence control means is from the microphone. The words of the input data are separated by morphological analysis or division rules to grasp the intention of the voice input person, grasp the words that are meaningful to the intention, and based on the grasped contents, access the database using communication means to access the database. A related operation is selected from among them, a predetermined operation is selected and executed , and a display content change command is issued to the control unit of the digital signage terminal by using a communication means as the selection execution of the predetermined operation. The transmission configuration solves the above-mentioned problems.

In the invention according to claim 2, in addition to the configuration of the artificial intelligence speaker system according to claim 1, the contact information to a predetermined person in charge is registered in advance in the database, and the artificial intelligence control means is used. The above-mentioned problems are further solved by the configuration of contacting a predetermined person in charge based on the grasped contents.

In the invention according to claim 3, in addition to the configuration of the artificial intelligence speaker system according to claim 1 or 2, a plurality of predetermined information is registered in the database, and the artificial intelligence control means is used. The above-mentioned problems are further solved by the configuration in which relevant information is selected from the database and read aloud using a speaker based on the grasped contents.

In the invention according to claim 4, in addition to the configuration of the artificial intelligence speaker system according to any one of claims 1 to 3, the database has a contact information for a predetermined person in advance. The above-mentioned problem is further solved by the configuration in which the registered artificial intelligence control means records the input content by voice in the database based on the grasped content and contacts a predetermined person in charge. Is.

The invention according to claim 5 has a configuration that can be freely linked with another system that is different from the database, in addition to the configuration of the artificial intelligence speaker system according to any one of claims 1 to 4. The artificial intelligence control means accesses the database of another system based on the grasped contents, selects relevant information from the database of the other system, and reads it out using a speaker. This further solves the above-mentioned problems.

The invention according to claim 6 has a configuration that can be freely linked with a predetermined sensor in addition to the configuration of the artificial intelligence speaker system according to any one of claims 1 to 5, and the predetermined sensor. The above-mentioned problem is further solved by the configuration in which the artificial intelligence control means notifies the change of the sensing situation by using the speaker when the sensing situation is changed.

The invention according to claim 7 has a configuration that can be freely linked with a predetermined application software in addition to the configuration of the artificial intelligence speaker system according to any one of claims 1 to 6 , and the artificial intelligence. At least one of the control means inputting on the predetermined application software based on the grasped content and the artificial intelligence control means notifying using the speaker based on the notification from the predetermined application software is executed. The above-mentioned problems are further solved by the configuration.

The invention according to claim 8 further includes an artificial intelligence voice emotion recognition means provided in the server in addition to the configuration of the artificial intelligence speaker system according to any one of claims 1 to 7 . , The artificial intelligence control means transmits the voice input data voiced from the microphone to the artificial intelligence voice emotion recognition means, receives the feedback information from the artificial intelligence voice emotion recognition means, and records the feedback information in the database. By doing so, the above-mentioned problems are further solved.

The invention according to claim 9 is application software of an artificial intelligence speaker system including a microphone, a speaker, a communication means, an artificial intelligence control means having a learning function, and a database, and the artificial intelligence control means. However, based on the data of the current display content of the digital signage terminal that can be linked freely, the reading step of reading out the content of the current display content using the speaker and the artificial intelligence control means are the input data from the microphone. The communication means is based on the intention grasping step of grasping the intention of the voice input person by dividing the words by morphological analysis or the division rule and grasping the words meaningful to the intention, and the contents grasped by the artificial intelligence control means. Use to access the database, select a relevant one from the database, select and execute a predetermined operation, and use a communication means to select and execute a predetermined operation, the control unit of the digital signage terminal. It solves the above-mentioned problem by providing a selection execution step for transmitting a display content change command to the user.

The artificial intelligence speaker system of the present invention is provided with a microphone, a speaker, a communication means, an artificial intelligence control means having a learning function, and a database, so that voice can be emitted or input by voice. Not only can it be done, but it can also have the following unique effects.

According to the artificial intelligence speaker system of the present invention according to the first aspect of the present invention, the input content spoken by the voice input person is a so-called intent and a so-called word meaningful for the intention, which is separated by a morphological analysis or a word-separation rule. Since the entity is grasped and the operation according to the input content is executed, the desired content of the voice input person can be executed.
Further, since the command is transmitted to the predetermined device according to the input content of the voice input person, the predetermined device can execute the desired content of the voice input person.
In addition, since the explanation about the current display content of the digital signage terminal is read aloud, the viewer of the display content can understand the content of the display content in detail.
Furthermore, since the viewer or moderator of the displayed content inputs a voice instruction to change the displayed content using a microphone, a command to that effect is sent to the digital signage terminal, so that the viewer or moderator of the displayed content can use it. The displayed content can be changed without manual operation, and at this time, the content can be changed to the desired content.

According to the artificial intelligence speaker system of the invention of claim 2, in addition to the effect of the invention of claim 1, when the voice input person inputs by voice that he / she wants the person in charge to be contacted, the artificial intelligence control is performed. Since the person in charge is contacted by means, the reception function that calls the person in charge at the company or store and the secretary function that contacts the person in charge can be fulfilled.

According to the artificial intelligence speaker system of the invention according to claim 3, in addition to the effect of the invention according to claim 1 or 2, the voice input person asks a question about what he / she wants to know or asks a voice about a problem. When you enter with, the artificial intelligence control means selects the content and solution that the voice input person wants to know from the database and reads it out, so the help desk function that informs you of the solution, the explanation function of the product etc., now It can fulfill the inventory check function that informs you of the inventory of the product and the assistant function (secretary function) that informs you of the schedule.

According to the artificial intelligence speaker system of the invention according to claim 4, in addition to the effect of the invention according to any one of claims 1 to 3, the voice input contents are recorded in the database by the artificial intelligence control means. Since the person in charge is contacted at the same time, the daily report function by voice input, the transportation expense settlement function by voice input, the work request function by voice input, the ordering / ordering function by voice input, and the questionnaire totaling function by voice input can be fulfilled. can.

According to the artificial intelligent speaker system of the invention according to the fifth aspect, in addition to the effect of the invention according to any one of claims 1 to 4, another existing one is provided by a so-called application programming interface (API). Since the information of the content that the voice input person wants to know is selected from other existing systems and mission-critical systems and read aloud by freely linking with the system and mission-critical systems, the explanation function of products etc. and the current inventory are notified. It can fulfill the inventory confirmation function that gives you.

According to the artificial intelligence speaker system of the invention according to claim 6, in addition to the effect of the invention according to any one of claims 1 to 5, the change in the sensing state by the sensor is notified by voice. Therefore, the user can surely know the change in the sensing situation.

According to the artificial intelligent speaker system of the invention according to claim 7 , in addition to the effect of the invention according to any one of claims 1 to 6 , a task management application, a chat application, a calendar application, and an e-mail In cooperation with apps, workflow apps, chatbot apps, social networking service apps, etc., the content that the user (voice input person) wants to record in the app is input and recorded on the desired application software by artificial intelligence control means. Users can connect and operate the desired application software simply by speaking without moving their hands.
In addition, when there is any notification on the application software, the speaker notifies the notification by voice, so that the user can know the notification on the application software without moving his / her hand.

According to the artificial intelligence speaker system of the invention according to claim 8 , in addition to the effect of the invention according to any one of claims 1 to 7 , the voice data of the voice input person is artificial intelligence voice emotion recognition. Since the emotion is recognized by the means and fed back to record the information about the emotion, the emotion of the voice input person can be grasped.
For example, when the answer to the questionnaire is input by voice, the emotions such as whether the voice input person is happy, sad, satisfied, or dissatisfied are converted into data for each item of the questionnaire question. Can be done.

According to the application software of the invention according to claim 9 , the input content spoken by the voice input person is intended to be separated by a morphological analysis or a division rule, as in the effect of the invention according to claim 1, so-called. Since the so-called entity, which is a word meaningful to the intent and the intention, is grasped and the operation according to the input content is executed, the desired content of the voice input person can be executed.
Further, since the command is transmitted to the predetermined device according to the input content of the voice input person, the predetermined device can execute the desired content of the voice input person.
In addition, since the explanation about the current display content of the digital signage terminal is read aloud, the viewer of the display content can understand the content of the display content in detail.
Furthermore, since the viewer or moderator of the displayed content inputs a voice instruction to change the displayed content using a microphone, a command to that effect is sent to the digital signage terminal, so that the viewer or moderator of the displayed content can use it. The displayed content can be changed without manual operation, and at this time, the content can be changed to the desired content.

The conceptual diagram which shows the artificial intelligence speaker system of 1st Embodiment of this invention. The figure which shows the chart of the artificial intelligence speaker system of 1st Embodiment of this invention. The figure which shows the case where the artificial intelligence speaker system was used for reception as the 2nd Example of this invention. The figure which shows the case where the artificial intelligence speaker system was used for the help desk as the 3rd Example of this invention. The figure which shows the case where the artificial intelligence speaker system was used for the transportation expense settlement application as the 4th Example of this invention. The figure which shows the case where the artificial intelligence speaker system is linked with other backbone system as the 5th Example of this invention. The figure which shows the case where the artificial intelligence speaker system is linked with the predetermined sensor as the 6th Example of this invention. The figure which shows the case where the artificial intelligence speaker system is linked with the digital signage terminal as the 7th Example of this invention. The figure which shows the case where the artificial intelligence speaker system is linked with the predetermined application software as the 8th Example of this invention. The figure which shows the case where the artificial intelligence speaker system is linked with the predetermined application software as the 9th Example of this invention.

The artificial intelligence speaker system of the present invention includes a microphone, a speaker, a communication means, an artificial intelligence control means having a learning function, and a database, and the artificial intelligence control means morphologically analyzes words of input data from the microphone. Or, grasp the intention of the voice input person by separating with the division rule, grasp the words that are meaningful for the intention, and based on the grasped contents, access the database using communication means and have a relevance from the database. As long as the configuration is such that a predetermined operation is selected and executed, and the desired content of the voice input person is executed, any specific embodiment thereof may be used. I do not care.
Further, in the application software of the artificial intelligence speaker system, the artificial intelligence control means grasps the intention of the voice input person by dividing the words of the input data from the microphone by morphological analysis or a division rule, and the words meaningful to the intention are input. Based on the grasped intention grasping step and the grasped contents, the artificial intelligence control means accesses the database using the communication means, selects a relevant one from the database, and selects a predetermined action. As long as it includes the selection execution step to be executed, the specific embodiment thereof may be any as long as it executes the desired content of the voice input person.

For example, the terminal having the artificial intelligence control means and the terminal having the database may have a separate configuration or a common configuration.
In other words, the artificial intelligence control means may be provided in the terminal together with the microphone and the speaker, or may be provided in the terminal together with the server having the database.
Also, the relevant ones include relevant data, information, other predetermined application software, and other predetermined systems.
In addition, certain actions include electronic actions that are primarily performed by the program, such as looking up, replying, selecting relevant ones from a database, contacting by phone, email, chat, etc. ..
The artificial intelligence control means and the database may be configured to be provided on one server or a plurality of servers on the cloud.

Hereinafter, the artificial intelligence speaker system 100, which is the first embodiment of the present invention, will be described with reference to FIGS. 1 and 2.
Here, FIG. 1 is a conceptual diagram showing the artificial intelligence speaker system 100 of the first embodiment of the present invention, and FIG. 2 is a diagram showing a chart of the artificial intelligence speaker system 100 of the first embodiment of the present invention. be.
Is.

As shown in FIG. 1, the artificial intelligence speaker system 100 according to the first embodiment of the present invention includes an artificial intelligence speaker terminal 110 and a server 120 having a database.
Of these, the artificial intelligence speaker terminal 110 has a microphone 111 and a speaker 112, and further includes a communication means and an artificial intelligence control means.
Then, when the user speaks to the artificial intelligence speaker terminal 110, the artificial intelligence control means separates the words of the input data from the microphone 111 by morphological analysis or a division rule to grasp the intention of the voice input person and for the intention. Grasp a meaningful word, and based on the grasped content, access the server 120 having a database using communication means, select a relevant one from the database, and select a predetermined action. Is configured to run.

More specifically, the operation of the artificial intelligence speaker system 100 will be described with reference to the chart of FIG.
In step S1 of FIG. 2, the artificial intelligence control means determines whether or not there is a voice input from the microphone 111.
If it is determined that there is a voice input, the process proceeds to step S2, and if it is determined that there is no voice input yet, step S1 is repeated.
For example, suppose that a user calls with a predetermined keyword that the artificial intelligence speaker terminal 110 reacts to, and then says "Tell me about the weather tomorrow in Tokyo!".
Then, the artificial intelligence control means determines that there is a voice input, and proceeds to step S2.

In step S2, as an intention grasping step, the artificial intelligence control means analyzes the words of the input data by voice.
For example, the input data "Tell me about the weather tomorrow in Tokyo!" Is divided into the part-speech units of the words listed in the dictionary, or by the phrase according to the division rule.
Here, the division rule will be described.
Rule 1: The phrase is cut off.
Rule 2: When a part of a phrase can create a phrase, cut off that part.
Rule 3: The part where another word can be inserted in the meantime is cut off.
Rule 4: The part where various words can be continued behind it is cut off.

Then, from the words "weather" and "tell me", the artificial intelligence control means grasps (estimates) that the so-called intent, which is the intention of the user, is "asking (want to know) the weather".
This allows you to select the action of replying about the weather in a later step.
Furthermore, the so-called entity, which is a word that has meaning for the intent, is grasped.
In the case of this example, it is necessary to grasp what kind of "weather" is specifically asked, and the artificial intelligence control means grasps that the entity for the intent is "Tokyo" and "tomorrow".
As a result, the artificial intelligence control means grasps that the weather in Tokyo should be investigated and answered, and the process proceeds to step S3.

In addition, in order to improve the accuracy of grasping the intent and the entity, the administrator may input an example sentence, select the intent and the entity, and let the artificial intelligence control means learn.
For example, by selecting "weather" and "tell me" and setting that it is an "intention", the words "weather" and "tell me" are instructed to learn as an intention to know the weather.
In addition, the word "tomorrow" is set by selecting "tomorrow" to indicate that it is a time / date concept of "when" and selecting "Tokyo" to indicate that it is a spatial concept of "where". Is an instruction to learn as an entity of the concept of time and date, and the word "Tokyo" is to be learned as an entity of the concept of place.
By setting by the administrator as described above, not only the artificial intelligence control means grasps the set word as an intent or an entity, but also the artificial intelligence control means has a learning function, so that it is set. Even if there is no word, it will be grasped as an intent or entity from the context of the voice input data.

In step S3, the artificial intelligence control means of the artificial intelligence speaker terminal 110 accesses the server 120 having the database by using the communication means, and proceeds to step S4.
In step S4, as the selection execution step, the artificial intelligence control means selects the actions of "examine" and "answer" from some predetermined actions registered.
As a result, the operation according to the input content is executed.
Here, the registration place of the predetermined operation may be in the artificial intelligence speaker terminal 110 or in the server 120.
Further, the timing of selecting the operation has been described as after accessing the database, but of course, it may be before accessing the database.
In the case of this example, the artificial intelligence control means acquires the information of "the tomorrow's weather in Tokyo is cloudy and then sunny and the probability of precipitation is 20%" about the tomorrow's Tokyo weather from the database of the server 120. Information about tomorrow's Tokyo weather, "Tomorrow's weather in Tokyo is cloudy and then sunny with a probability of precipitation of 20%" is read aloud using the speaker 112 of the artificial intelligence speaker terminal 110.

The artificial intelligence speaker system 100 may further have an artificial intelligence voice emotion recognition means provided in the server 120.
Then, the artificial intelligence control means transmits the voice input data voiced from the microphone 111 to the artificial intelligence voice emotion recognition means, receives the feedback information from the artificial intelligence voice emotion recognition means, and records the feedback information in the database. It may be configured as.
The artificial intelligence voice emotion recognition means determines, for example, emotions such as joy, dissatisfaction, and calmness of a voice input person and their degree by performing acoustic analysis and recognizing emotions from the amount of features of the voice itself.
As a result, the voice data of the voice input person is emotion-recognized and fed back by the artificial intelligence voice emotion recognition means, and the information about the emotion is recorded.
As a result, the emotion of the voice input person can be grasped.
For example, when the answer to the questionnaire is input by voice, the emotions such as whether the voice input person is happy, sad, satisfied, or dissatisfied are converted into data for each item of the questionnaire question. Can be done.

The artificial intelligence speaker system 100 according to the first embodiment of the present invention thus obtained is an artificial intelligence speaker including a microphone 111, a speaker 112, a communication means, and an artificial intelligence control means having a learning function. It has a terminal 110 and a server 120 equipped with a database, and an artificial intelligence control means grasps the intention of the voice input person by dividing the words of the input data from the microphone 111 by a morphological analysis or a division rule and is meaningful for the intention. It is a configuration that grasps a certain word, accesses the database using communication means based on the grasped content, selects a related one from the database, and selects and executes a predetermined action. Thereby, the desired content of the user who is the voice input person can be executed.

Further, the artificial intelligence speaker system 100 further has an artificial intelligence voice emotion recognition means provided in the server 120, and the artificial intelligence control means transfers the voice input data voiced from the microphone 111 to the artificial intelligence voice emotion recognition means. It is possible to grasp the emotions of the voice input person by transmitting, receiving the feedback information from the artificial intelligence voice emotion recognition means, and recording the feedback information in the database.

Further, in the application software of the artificial intelligence speaker system 100, the artificial intelligence control means grasps the intention of the voice input person by dividing the words of the input data from the microphone 111 by morphological analysis or a division rule, and the words are meaningful to the intention. Based on the grasped contents, the artificial intelligence control means accesses the database by using the communication means, selects a relevant one from the database, and performs a predetermined operation. By providing the selection execution steps S3 and S4 to be selected and executed, the desired content of the user who is the voice input person can be executed, and the effect is enormous.

Subsequently, the artificial intelligence speaker system 100, which is the second embodiment of the present invention, will be described with reference to FIG.
Here, FIG. 3 is a diagram showing a case where the artificial intelligence speaker system 100 is used for reception as a second embodiment of the present invention.
The artificial intelligence speaker system 100 of the second embodiment is accepted as an example of the use of the artificial intelligence speaker system 100 of the first embodiment, and many elements are common to the artificial intelligence speaker system 100 of the first embodiment. Therefore, detailed explanations of common matters will be omitted.

As shown in FIG. 3, the artificial intelligence speaker system 100 according to the second embodiment of the present invention includes an artificial intelligence speaker terminal 110 and a server 120 having a database.
The artificial intelligence speaker terminal 110 is installed at the reception desk of a company as an example.
Then, the contact information for the predetermined person in charge is registered in advance in the database of the server 120.
For example, a visitor said, "Hello! I'm Sasaki from XX company. I made an appointment with Mr. Suzuki at 15:00!" After calling with a predetermined keyword that the artificial intelligence speaker terminal 110 responds to. do.
Then, the artificial intelligence control means of the artificial intelligence speaker terminal 110 divides the input data from the microphone 111 into each phrase according to the division rule, grasps the intention of the voice input person, and grasps the words meaningful to the intention.

In the case of this example, from the words "○○ company", "Sasaki", "Suzuki", "promise", and "I came", the intent that the visitor (voice input person) intended is "I want to meet Suzuki". The artificial intelligence control means grasps that.
As a result, you can select the action of notifying Mr. Suzuki that there is a visitor.
In addition, grasp the entity, which is a word that has meaning for the intent.
In the case of this example, it is necessary to specifically grasp who wants to meet Mr. Suzuki, and the artificial intelligence control means grasps that the entity for the intent is "○○ company" and "Sasaki".

The artificial intelligence control means of the artificial intelligence speaker terminal 110 accesses the server 120 having the database by using the communication means, and "contacts the person in charge" and "replies" from some registered predetermined actions. Select the action of "to do".
In the case of this example, the artificial intelligence control means selects the ID information of the message communication application software for push notification, which is an example of the contact information of Mr. Suzuki, who is the person in charge registered in advance, from the database, and uses the communication means. Notify Mr. Suzuki's personal computer terminal 130 that "Mr. Sasaki of XX company is at the reception!"

You may also call the phone at Mr. Suzuki's desk to notify by voice.
Along with this, the artificial intelligence control means uses the speaker 112 to reply "Hello! I've been waiting. I'm calling Suzuki in charge, so please wait a moment!".
In addition, if there is a reserved conference room, artificial intelligence control means will access the conference room reservation system to confirm the reserved conference room and say, "I was waiting. It is just down the corridor on the right side. You may read the guidance saying "Please wait in the first meeting room!".
As a result, when the voice input person inputs by voice that he / she wants the person in charge to be contacted, the person in charge is contacted by the artificial intelligence control means.
As a result, it is possible to fulfill the reception function of calling the person in charge at the company or the store and the secretary function of contacting the person in charge.

In the artificial intelligence speaker system 100 which is the second embodiment of the present invention thus obtained, the contact information to the predetermined person in charge is registered in advance in the database, and the artificial intelligence control means grasps the contents. Based on this, by configuring to contact the person in charge, the reception function that calls the person in charge at the company or store and the secretary function that contacts the person in charge can be fulfilled, and the effect is enormous. be.

Subsequently, the artificial intelligence speaker system 100, which is the third embodiment of the present invention, will be described with reference to FIG.
Here, FIG. 4 is a diagram showing a case where the artificial intelligence speaker system 100 is used as a help desk as a third embodiment of the present invention.
The artificial intelligence speaker system 100 of the third embodiment is an example of the use of the artificial intelligence speaker system 100 of the first embodiment as a help desk, and the artificial intelligence of the first embodiment and the second embodiment has many elements. Since it is common with the intelligent speaker system 100, detailed description of common matters will be omitted.

As shown in FIG. 4, the artificial intelligence speaker system 100 according to the third embodiment of the present invention includes an artificial intelligence speaker terminal 110 and a server 120 having a database.
The artificial intelligence speaker terminal 110 is installed in a company office as an example.
For example, suppose an employee of a company calls out with a predetermined keyword that the artificial intelligence speaker terminal 110 responds to, and then says, "I'm having trouble with the monitor of my computer turning on and off. What should I do?" ..
Then, the artificial intelligence control means of the artificial intelligence speaker terminal 110 divides the input data from the microphone 111 into each phrase according to the division rule, grasps the intention of the voice input person, and grasps the words meaningful to the intention.

In the case of this example, from the words "PC", "trouble", "masu", "what should I do", and "what should I do?" The artificial intelligence control means grasps that "I want you to do it."
As a result, the operation of answering about the personal computer may be selected.
In addition, grasp the entity, which is a word that has meaning for the intent.
In the case of this example, it is necessary to grasp the specific state of the personal computer, and the artificial intelligence control means that the entity for the intent is "monitor", "turn on", "turn off". To grasp.

The artificial intelligence control means of the artificial intelligence speaker terminal 110 accesses the server 120 having the database by using the communication means, and also performs the actions of "examining" and "answering" from some registered predetermined actions. select.
In the case of this example, the artificial intelligence control means selects the item that seems to be the most relevant (most appropriate) from the so-called Q & A data registered in advance from the database, and the coping method "Let's restart the computer once! ”Is read aloud using the speaker 112 and answered.
As a result, when a voice input person inputs a question or a problem about the content that the voice input person wants to know by voice, the content or solution that the voice input person wants to know is selected from the database and read aloud by the artificial intelligence control means. Be done.

In this embodiment, the help desk function that informs the solution is described, but it may be used as another function.
For example, the voice input person may request information about the product, and the artificial intelligence control means of the artificial intelligence speaker terminal 110 may be used as a product explanation function for explaining the product or the like.
Further, the voice input person may request information about the stock of the product and the artificial intelligence control means of the artificial intelligence speaker terminal 110 may use it as an inventory confirmation function to notify the current stock, or the voice input person may use himself or herself. It may be used as an assistant function (secretary function) in which the artificial intelligence control means of the artificial intelligence speaker terminal 110 informs the schedule by requesting information about the schedule of another member.
As a result, it is possible to fulfill a help desk function that informs the solution, an explanation function such as a product, an inventory confirmation function that informs the current inventory, and an assistant function (secretary function) that informs the schedule.

In the artificial intelligence speaker system 100 which is the third embodiment of the present invention thus obtained, a plurality of predetermined informations are registered in the database, and the database is based on the contents grasped by the artificial intelligence control means. By selecting relevant information from and reading it out using the speaker 112, a help desk function that informs you of the solution, an explanation function of products, etc., an inventory confirmation function that informs you of the current inventory, and a schedule The effect is enormous, such as being able to fulfill the assistant function (secretary function) that informs you.

Subsequently, the artificial intelligence speaker system 100, which is the fourth embodiment of the present invention, will be described with reference to FIG.
Here, FIG. 5 is a diagram showing a case where the artificial intelligence speaker system 100 is used for the transportation expense settlement application as the fourth embodiment of the present invention.
The artificial intelligence speaker system 100 of the fourth embodiment is an application for transportation expense settlement using the use of the artificial intelligence speaker system 100 of the first embodiment as an example, and many elements are described in the first to third embodiments. Since it is common with the artificial intelligence speaker system 100 of the above, detailed description of common matters will be omitted.

As shown in FIG. 5, the artificial intelligence speaker system 100 according to the fourth embodiment of the present invention includes an artificial intelligence speaker terminal 110 and a server 120 having a database.
The artificial intelligence speaker terminal 110 is installed in a company office as an example.
Then, the contact information for the predetermined person in charge is registered in advance in the database of the server 120.
For example, after an employee called out with a predetermined keyword that the artificial intelligence speaker terminal 110 responds to, "This is an application for transportation expense reimbursement! I'm Sasaki, a sales person. It's 27,420 yen! "
Then, the artificial intelligence control means of the artificial intelligence speaker terminal 110 divides the input data from the microphone 111 into each phrase according to the division rule, grasps the intention of the voice input person, and grasps the words meaningful to the intention.

In the case of this example, the artificial intelligence control means grasps from the words "transportation expenses" and "application" that the intent intended by the employee (voice input person) is "want to apply for transportation expenses settlement". ..
As a result, the operation of recording the application contents and the operation of notifying the accounting staff of the application contents may be selected.
In addition, grasp the entity, which is a word that has meaning for the intent.
In the case of this example, it is necessary to know exactly who, when, where, where, by what means of transportation, and how much it cost, and the entities for the intent are "Sasaki" and "Tokyo". , "Osaka", "Shinkansen", "round trip", "27,420 yen" is grasped by the artificial intelligence control means.

The artificial intelligence control means of the artificial intelligence speaker terminal 110 accesses the server 120 having the database by using the communication means, and "records the input contents" and "the person in charge" from some registered predetermined operations. Select the actions of "contact to" and "reply".
In the case of this example, the artificial intelligence control means records the voice input data as the application content in the database.
Along with this, the ID information of the message communication application software for push notification, which is an example of the contact information of the accountant registered in advance, is selected from the database, and the personal computer terminal 130 of the accountant is used by the communication means. We will notify you that there was an application for reimbursement of transportation expenses for "Sasaki-san, a salesperson, December 15th, Osaka business trip travel expenses of 27,420 yen".
Further, the artificial intelligence control means uses the speaker 112 to reply to the employee who input the voice to the effect that "the application for transportation expense settlement has been accepted!".

As a result, the voice input content is recorded in the database by the artificial intelligence control means and the person in charge is notified.
In this embodiment, the transportation expense settlement function by voice input has been described, but it may be used as another function.
For example, it may be used as a daily report function by voice input, a work request function by voice input, an ordering / ordering function by voice input, and a questionnaire totaling function by voice input.
As a result, it is possible to fulfill the daily report function by voice input, the transportation expense settlement function by voice input, the work request function by voice input, the ordering / ordering function by voice input, and the questionnaire totaling function by voice input.

In the artificial intelligence speaker system 100 which is the fourth embodiment of the present invention thus obtained, the contact information to the predetermined person in charge is registered in advance in the database, and the artificial intelligence control means grasps the contents. Based on this, by recording the input contents by voice in the database and contacting the designated person in charge, the daily report function by voice input, the transportation expense settlement function by voice input, the work request function by voice input, and the voice input The effect is enormous, such as being able to fulfill the ordering / ordering function by voice input and the questionnaire function by voice input.

Subsequently, the artificial intelligence speaker system 100, which is the fifth embodiment of the present invention, will be described with reference to FIG.
Here, FIG. 6 is a diagram showing a case where the artificial intelligence speaker system 100 is linked with another backbone system as the fifth embodiment of the present invention.
The artificial intelligence speaker system 100 of the fifth embodiment is a system in which the artificial intelligence speaker system 100 of the first embodiment is linked with another backbone system, and many elements are described in the first to fourth embodiments. Since it is common with the artificial intelligence speaker system 100, detailed description of common matters will be omitted.
The core system includes ERP (Enterprise Resource Planning) system, production management system, sales management system, inventory management system, order management system, financial / accounting system, etc. The core system is an indispensable system for corporate activities. Is.

As shown in FIG. 6, the artificial intelligence speaker system 100 according to the fifth embodiment of the present invention includes an artificial intelligence speaker terminal 110 and a server 120 having a database.
Further, it is freely configured to communicate with other system servers 140 and to cooperate with each other.
The artificial intelligence speaker terminal 110 is installed in a company office as an example.
For example, suppose an employee calls out with a predetermined keyword that the artificial intelligence speaker terminal 110 reacts to, and then says, "Tell me about the sales of product A yesterday!".
Then, the artificial intelligence control means of the artificial intelligence speaker terminal 110 divides the input data from the microphone 111 into each phrase according to the division rule, grasps the intention of the voice input person, and grasps the words meaningful to the intention.

In the case of this example, the artificial intelligence control means grasps from the words "sales" and "tell me" that the intent intended by the employee (voice input person) is "want to know the sales".
As a result, the operation of checking the sales and the operation of replying to the sales may be selected.
In addition, grasp the entity, which is a word that has meaning for the intent.
In the case of this example, it is necessary to know when and what the sales are specifically wanted to know, and the artificial intelligence control means knows that the entity for the intent is "yesterday" and "product A". do.

The artificial intelligence control means of the artificial intelligence speaker terminal 110 accesses the server 120 having the database by using the communication means, and also performs the operations of "examining" and "replying" from some registered predetermined operations. Select.
In the case of this example, since there is no sales information in the database of the server 120, the artificial intelligence control means directly or indirectly accesses another system server 140 that can cooperate with the server 120 via the server 120. ..
Then, the artificial intelligence control means acquires the information of "the sales of the product A yesterday 1.2 million yen" about the sales of the product A yesterday from the database of the other system server 140, and the acquired product A yesterday. The information about the sales of "Yesterday's product A sales of 1.2 million yen!" Is read aloud using the speaker 112 of the artificial intelligence speaker terminal 110.

As a result, the so-called application programming interface (API) makes it possible to link with other existing systems and mission-critical systems, and information of the content that the voice input person wants to know is selected from other existing systems and mission-critical systems and read aloud. Be done.
In this embodiment, the example of answering the sales of the product in cooperation with the core system has been described, but the configuration may be in cooperation with other existing systems, so-called information systems.
Here, the information system includes e-mail software, groupware software, schedule management tool software, in-house SNS (business chat), and the like.
As a result, in cooperation with other systems, it is possible to fulfill the function of explaining products and the like, and the inventory confirmation function of notifying the current inventory.

The artificial intelligence speaker system 100, which is the fifth embodiment of the present invention thus obtained, has a configuration that can be freely linked with another system server 140 that is different from the database of the server 120, and the artificial intelligence control means can be used. Based on the grasped contents, the system is configured to access the database of the other system server 140, select relevant information from the database of the other system server 140, and read it out using the speaker 112. The effect is enormous, such as being able to fulfill the explanation function of the server and the inventory confirmation function that informs the current inventory.

Subsequently, the artificial intelligence speaker system 100, which is the sixth embodiment of the present invention, will be described with reference to FIG. 7.
Here, FIG. 7 is a diagram showing a case where the artificial intelligence speaker system 100 is linked with a predetermined sensor as the sixth embodiment of the present invention.
The artificial intelligence speaker system 100 of the sixth embodiment is a system in which the artificial intelligence speaker system 100 of the first embodiment is linked with a predetermined sensor, and the artificial intelligence of the first to fifth embodiments has many elements. Since it is common with the speaker system 100, detailed description of common matters will be omitted.

As shown in FIG. 7, the artificial intelligence speaker system 100 according to the sixth embodiment of the present invention includes an artificial intelligence speaker terminal 110 and a server 120 having a database.
Further, the room is provided with an illuminance sensor 150, which is an example of the sensor.
The artificial intelligence speaker system 100 is configured to freely cooperate with the illuminance sensor 150, which is an example of the sensor.
Further, the artificial intelligence control means is configured to notify the change of the sensing situation by using the speaker 112.

For example, when the inside of the room gradually becomes dark and becomes less than a predetermined illuminance value, the sensing state of the illuminance sensor 150 changes.
At this time, the artificial intelligence control means is configured to use the speaker 112 to notify "The room is getting dark! Do you want to turn on the lighting?" As an example of the change in the sensing situation.
As a result, the change in the sensing status by the illuminance sensor 150 is notified by voice.
As a result, the user can surely know the change in the sensing situation.

Then, it is assumed that the user notices this notification, calls with a predetermined keyword that the artificial intelligence speaker terminal 110 reacts to, and then says, "Yes, turn on the lighting!".
Here, if the artificial intelligence speaker system 100 is configured to freely cooperate with a switch of a lighting device which is an example of a predetermined device, the artificial intelligence control means grasps the intention of the voice input person who is the user and takes the intention. You can grasp meaningful words and switch on the lights in the room.
The illuminance sensor 150 is mentioned as an example of the predetermined sensor, but the present invention is not limited to this.
For example, a motion sensor (pyroelectric sensor), a gyro sensor, a button sensor, a temperature / humidity sensor, an image sensor, or the like may be used.

The artificial intelligence speaker system 100 according to the sixth embodiment of the present invention thus obtained has a configuration that can be freely linked with the illuminance sensor 150 which is an example of a predetermined sensor, and the sensing situation by the illuminance sensor 150 has changed. At that time, since the artificial intelligence control means is configured to notify the change of the sensing situation by using the speaker 112, the user can surely know the change of the sensing situation, and the effect is enormous.

Subsequently, the artificial intelligence speaker system 100, which is the seventh embodiment of the present invention, will be described with reference to FIG.
Here, FIG. 8 is a diagram showing a case where the artificial intelligence speaker system 100 is linked with the digital signage terminal 160 as the seventh embodiment of the present invention.
The artificial intelligence speaker system 100 of the seventh embodiment is a system in which the artificial intelligence speaker system 100 of the first embodiment is linked with the digital signage terminal 160, and the artificial intelligence of the first to sixth embodiments is provided for many elements. Since it is common with the intelligent speaker system 100, detailed description of common matters will be omitted.

As shown in FIG. 8, the artificial intelligence speaker system 100 according to the seventh embodiment of the present invention includes an artificial intelligence speaker terminal 110 and a server 120 having a database.
Further, it is freely communicative with the digital signage terminal 160 as an example of a predetermined device, and is configured to be freely linked.
Then, the artificial intelligence control means is configured to read out the content of the current display content by using the speaker 112 based on the data of the current display content of the digital signage terminal 160.
Further, the artificial intelligence control means is configured to transmit a display content change command to the control unit of the digital signage terminal 160 by using the communication means based on the intention of the voice input person and the word meaningful to the intention. ing.

As an example, the artificial intelligence speaker terminal 110 is installed in the vicinity of the digital signage terminal 160 in the storefront of a restaurant.
Then, it is assumed that the digital signage terminal 160 is displaying the content about the lunch menu stored in the server 120.
In the case of this example, the artificial intelligence control means grasps the current display content of the digital signage terminal 160 directly to the digital signage terminal 160 or via the server 120.
Then, the artificial intelligence control means reads out the content of the current display content by using the speaker 112 based on the data of the current display content of the digital signage terminal 160.

For example, if the digital signage terminal 160 is displaying a lunch menu of fluffy pancakes and gentle vegetable soup, the text data of the explanation of this display content is "Today's recommendation is now fluffy and mouthful. It's a vegetable soup that warms your body with plenty of warm vegetables on a pancake that melts inside! "
As a result, the explanation about the current display content of the digital signage terminal 160 is read aloud.
As a result, the prospective customer who sees the displayed content can understand the content of the displayed content in detail.

At this time, it is assumed that the prospective customer's preference is not pancake but cheesecake.
Then, suppose that a prospective customer calls out with a predetermined keyword that the artificial intelligence speaker terminal 110 reacts to, and then says, "What is cheesecake?"
Then, the artificial intelligence control means of the artificial intelligence speaker terminal 110 divides the input data from the microphone 111 into each phrase according to the division rule, grasps the intention of the voice input person, and grasps the words meaningful to the intention.

In the case of this example, the artificial intelligence control means says that the intent that the prospective customer (voice input person) intends is "I want to know the cake on the menu of the shop" from the words "cake" and "is there?" grasp.
As a result, the operation of examining the menu and the operation of replying to the menu may be selected.
In addition, grasp the entity, which is a word that has meaning for the intent.
In the case of this example, it is necessary to grasp what kind of cake is specifically, and the artificial intelligence control means grasps that the entity for the intent is "cheese" and "what".

The artificial intelligence control means of the artificial intelligence speaker terminal 110 accesses the server 120 having a database by using a communication means, and issues a command to "examine" and "change the display" from some registered predetermined operations. Select the action of "Start".
In the case of this example, the artificial intelligence control means acquires the information of the menu "cheesecake" from the database of the server 120, and the server 120 or the digital signage having a control unit which controls the display by using the communication means. A display content change command for changing to the content of "cheesecake" is transmitted to the terminal 160.
As a result, the display content of the digital signage terminal 160 is switched from "pancake & vegetable soup" to "cheesecake".

Then, the artificial intelligence control means reads out the text data of the explanation of this display content, "It is a cheesecake with a rich texture of New York style!".
At this time, when there are a plurality of types of cheesecake, the digital signage terminal 160 displays them in order, and the artificial intelligence control means reads out the explanations in order using the speaker 112.
As a result, the prospective customer who is a viewer of the displayed content can change the displayed content without manually operating the content, and at this time, the content can be changed to the desired content.
In this embodiment, the digital signage terminal 160 has been described as an example of a predetermined device, but an air conditioner device, a lighting device, an oven range device, a refrigerator, a washing machine, a bath water heater, a TV program recorder, etc. May be.

The artificial intelligence speaker system 100 according to the seventh embodiment of the present invention thus obtained has a configuration that can be freely linked with the digital signage terminal 160 which is an example of a predetermined device, and is grasped by the artificial intelligence control means. Based on the content, the predetermined device executes the desired content of the voice input person by using a communication means to transmit a command to the control unit of the digital signage terminal 160, which is an example of the predetermined device. can do.

Further, the predetermined device is the digital signage terminal 160, and the artificial intelligence control means reads out and grasps the content of the current display content by using the speaker 112 based on the data of the current display content of the digital signage terminal 160. By using a communication means to transmit a display content change command to the control unit of the digital signage terminal 160 based on the content, the viewer of the display content can understand the content of the display content in detail. The display content can be changed without any manual operation by the viewer or the moderator of the display content, and at this time, the content can be changed to the desired content, and the effect is enormous.

Subsequently, the artificial intelligence speaker system 100, which is the eighth embodiment of the present invention, will be described with reference to FIG.
Here, FIG. 9 is a diagram showing a case where the artificial intelligence speaker system 100 is linked with a predetermined application software as the eighth embodiment of the present invention.
The artificial intelligence speaker system 100 of the eighth embodiment is a system in which the artificial intelligence speaker system 100 of the first embodiment is linked with the schedule management application software, and the artificial intelligence of the first to seventh embodiments has many elements. Since it is common with the intelligent speaker system 100, detailed description of common matters will be omitted.

As shown in FIG. 9, the artificial intelligence speaker system 100 according to the eighth embodiment of the present invention includes an artificial intelligence speaker terminal 110 and a server 120 having a database.
Further, it is configured to be freely linked with the schedule management application software as an example of predetermined application software.
Then, the artificial intelligence control means is configured to input on the application software based on the intention of the voice input person and the words meaningful to the intention.
Further, the artificial intelligence control means is configured to notify using the speaker 112 based on the notification from the application software.

The artificial intelligence speaker terminal 110 is installed in a company office as an example.
For example, after an employee called out with a predetermined keyword that the artificial intelligence speaker terminal 110 responds to, "I'm Sasaki. I will visit △△ Foods Co., Ltd. at 15:00 tomorrow and schedule a meeting with Mr. Suzuki. Be there! "
Then, the artificial intelligence control means of the artificial intelligence speaker terminal 110 divides the input data from the microphone 111 into each phrase according to the division rule, grasps the intention of the voice input person, and grasps the words meaningful to the intention.

In the case of this example, the artificial intelligence control means grasps from the words "plan" and "put in" that the intent that the employee (voice input person) intends is "want to register the schedule".
As a result, the operation of registering the schedule and the operation of replying to the schedule may be selected.
In addition, grasp the entity, which is a word that has meaning for the intent.
In the case of this example, it is necessary to know specifically who, when, and what kind of schedule you want to register, and the entities for the intent are "Sasaki", "Tomorrow", "15:00", "△△". Artificial intelligence control means grasps that it is "Food Co., Ltd." and "Suzuki".

The artificial intelligence control means of the artificial intelligence speaker terminal 110 accesses the server 120 having a database by using a communication means, and "registers a schedule on the schedule management application software" from among several registered predetermined operations. And "Reply" actions are selected.
In the case of this example, the artificial intelligence control means may start the schedule management application software to register (input) the contents of the voice input data, or may not start the schedule management application software in the data file data related to the schedule management application software. You may write and register.

Further, the artificial intelligence control means uses the speaker 112 to reply to the employee who input the voice to the effect that "the schedule has been registered in the schedule management application!".
As a result, the content that the user (voice input person) wants to register (record) in the application is input and registered (recorded) on the schedule management application software by the artificial intelligence control means.
As a result, the user can connect and operate the schedule management application software simply by speaking without moving his or her hand.

Further, it is assumed that the schedule management application software is set to notify the scheduled time before the scheduled time.
In this case, the schedule management application software notifies the artificial intelligence speaker terminal 110 one time before the scheduled time.
Then, based on this notification, the artificial intelligence control means will use the speaker 112, for example, "Now, it's 14:00. Today's 15:00, we will visit △△ Foods Co., Ltd. and have a meeting with Mr. Suzuki! "The content of the notification is read aloud.
As a result, the speaker 112 notifies the user by voice to that effect.
As a result, the user can know the notification on the application software without moving his / her hand.

Also, for example, suppose an employee calls out with a predetermined keyword that the artificial intelligence speaker terminal 110 responds to, and then says, "I'm Sasaki. Tell me about my schedule today!".
Then, the artificial intelligence control means of the artificial intelligence speaker terminal 110 divides the input data from the microphone 111 into each phrase according to the division rule, grasps the intention of the voice input person, and grasps the words meaningful to the intention.
In the case of this example, the artificial intelligence control means grasps from the words "plan" and "tell me" that the intent intended by the employee (voice input person) is "want to know the schedule".
As a result, the operation of checking the schedule and the operation of replying to the schedule may be selected.
In addition, grasp the entity, which is a word that has meaning for the intent.
In the case of this example, it is necessary to know who specifically wants to know when and when, and the artificial intelligence control means knows that the entity for the intent is "Sasaki" or "Today". ..

The artificial intelligence control means of the artificial intelligence speaker terminal 110 accesses the server 120 having the database by using the communication means, and also performs the operations of "examining" and "replying" from some registered predetermined operations. Select.
In the case of this example, the schedule management application software that can be freely linked may be started to read and acquire the data of Mr. Sasaki's schedule today, or the data related to the schedule management application software may be started without starting the schedule management application software. You may read the data of the file and get the data of Mr. Sasaki's schedule for today.

And, as an example of the information of Mr. Sasaki's schedule today, which was acquired by the artificial intelligence control means, "We are planning to visit △△ Foods Co., Ltd. at 15:00 today and have a meeting with Mr. Suzuki." Is read aloud using the speaker 112 of the artificial intelligence speaker terminal 110.
As a result, the schedule content is notified to the employee (voice input person) by voice from the speaker 112.
As a result, the employee (voice input person) can confirm the schedule registered on the schedule management application software without moving his / her hand.

In this embodiment, the configuration that can be freely linked with the schedule management application software has been described, but the configuration that can be freely linked with other application software may be used.
For example, meeting room reservation management application software, task management application software, chat application software, calendar application software, email application software, workflow application software, chatbot application software, customer relationship management application software (CRM app), social networking service application. It may be configured to be freely linked with software and their application systems.
Further, the application software and the application system that can be freely linked may be so-called cloud services configured on the cloud.
Furthermore, according to the request (intention) of the voice input person, the schedule management application software is used to adjust the schedules of other members, and the conference room is reserved (registered) in the common free time. It may be configured to schedule members of.

The artificial intelligence speaker system 100 according to the eighth embodiment of the present invention thus obtained has a configuration that can be freely linked with a predetermined application software, and is a predetermined application based on the contents grasped by the artificial intelligence control means. The user does not move his / her hand because it is configured to execute at least one of inputting on the software and the artificial intelligence control means notifying using the speaker 112 based on the notification from the predetermined application software. The effect is enormous, such as being able to connect to and operate the desired application software simply by talking to the user, and being able to know the notifications on the application software without moving the user.

Subsequently, the artificial intelligence speaker system 100, which is the ninth embodiment of the present invention, will be described with reference to FIG.
Here, FIG. 10 is a diagram showing a case where the artificial intelligence speaker system 100 is linked with a predetermined application software as a ninth embodiment of the present invention.
The artificial intelligence speaker system 100 of the ninth embodiment is a system in which the artificial intelligence speaker system 100 of the first embodiment is linked with the schedule management application software, and the artificial intelligence of the first to eighth embodiments for many elements. Since it is common with the intelligent speaker system 100, detailed description of common matters will be omitted.

As shown in FIG. 10, the artificial intelligence speaker system 100 according to the ninth embodiment of the present invention includes an artificial intelligence speaker terminal 110 and a server 120 having a database.
Further, it is freely configured to cooperate with the business card management application software as an example of predetermined application software.
Then, the artificial intelligence control means is configured to input on the application software based on the intention of the voice input person and the words meaningful to the intention.

The artificial intelligence speaker terminal 110 is installed in a company office as an example.
For example, after an employee calls with a predetermined keyword that the artificial intelligence speaker terminal 110 responds to, "Registration of a business card. △△ Food Co., Ltd. Sales Manager Ichiro Suzuki Address 1-2-3, Koto-ku, Tokyo Phone number 03-1234-5678 E-mail address suzuki@△△shokuhin.co.jp ".
Then, the artificial intelligence control means of the artificial intelligence speaker terminal 110 divides the input data from the microphone 111 into each phrase according to the division rule, grasps the intention of the voice input person, and grasps the words meaningful to the intention.

In the case of this example, the artificial intelligence control means grasps from the words "business card" and "registration" that the intent intended by the employee (voice input person) is "want to register the contents of the business card".
As a result, the operation of registering the contents of the business card and the operation of replying to the contents may be selected.
In addition, grasp the entity, which is a word that has meaning for the intent.
In the case of this example, it is necessary to know who specifically wants to register the business card, and the entities for the intent are "△△ Food Co., Ltd.", "Sales Manager", "Ichiro Suzuki", and "Telephone number". , "03-1234-5678", "email address", "suzuki@△△shokuhin.co.jp".

The artificial intelligence control means of the artificial intelligence speaker terminal 110 accesses the server 120 having a database by using a communication means, and from among several registered predetermined operations, "the contents of the business card on the business card management application software". Select the "Register" and "Reply" actions.
In the case of this example, the artificial intelligence control means may start the business card management application software to register (input) the contents of the voice input data, or may not start it and use the data in the data file related to the business card management application software. You may write and register.
Instead of the server 120, the personal computer terminal 130, which is a predetermined terminal, may be accessed, and text may be input to a CSV format file such as Excel to save the data.

Further, the artificial intelligence control means uses the speaker 112 to reply to the employee who input the voice to the effect that "the contents of the business card have been registered in the business card management application!".
As a result, the content that the user (voice input person) wants to register (record) in the application is input and registered (recorded) on the business card management application software by the artificial intelligence control means.
As a result, the user can connect and operate the business card management application software simply by speaking without moving his or her hand.
That is, the user can input (register) the contents of the business card without operating the mouse.
Although the business card management application software has been described as an example of the predetermined application software, other application software may be used.
For example, document creation software or spreadsheet software may be used.

The artificial intelligence speaker system 100 according to the ninth embodiment of the present invention thus obtained has a configuration that can be freely linked with a predetermined application software, and is a predetermined application based on the contents grasped by the artificial intelligence control means. Since the configuration is such that input is performed on the software, the user can operate by connecting to the desired application software simply by speaking without moving his / her hand, and the effect is enormous.

100 ・ ・ ・ Artificial intelligence speaker system 110 ・ ・ ・ Artificial intelligence speaker terminal (communication means, artificial intelligence control means)
111 ・ ・ ・ Microphone 112 ・ ・ ・ Speaker 120 ・ ・ ・ Server (database)
130 ・ ・ ・ Personal computer terminal (predetermined terminal)
140 ・ ・ ・ Other system server (database of other system)
150 ・ ・ ・ Illuminance sensor (sensor terminal)
160 ・ ・ ・ Digital signage terminal (predetermined device)

Claims (9)

An artificial intelligence speaker system including a microphone, a speaker, a communication means, an artificial intelligence control means having a learning function, and a database.
It has a configuration that can be freely linked with a digital signage terminal.
The artificial intelligence control means reads out the content of the current display content using the speaker based on the data of the current display content of the digital signage terminal.
The artificial intelligence control means grasps the intention of the voice input person by dividing the words of the input data from the microphone by morphological analysis or a division rule, grasps the words meaningful to the intention, and based on the grasped contents. A digital signage terminal using a communication means to access a database using a communication means, select a related one from the database, select and execute a predetermined operation, and select and execute a predetermined operation. An artificial intelligence speaker system characterized in that it is configured to send a display content change command to the control unit of . The contact information for the designated person is registered in advance in the database, and the contact information is registered in advance.
The artificial intelligence speaker system according to claim 1, wherein the artificial intelligence control means is configured to contact a predetermined person in charge based on the grasped contents. A plurality of predetermined informations are registered in the database.
The artificial intelligence control means according to claim 1 or 2, wherein the artificial intelligence control means is configured to select relevant information from a database and read it out using a speaker based on the grasped contents. Intelligent speaker system. The contact information for the designated person is registered in advance in the database, and the contact information is registered in advance.
Any of claims 1 to 3, wherein the artificial intelligence control means is configured to record input contents by voice in a database and contact a predetermined person in charge based on the grasped contents. The artificial intelligence speaker system described in one. It is a configuration that can be freely linked with other systems that are different from the database.
The artificial intelligence control means is characterized in that it has a configuration in which it accesses a database of another system, selects relevant information from the database of another system, and reads it out using a speaker based on the grasped contents. The artificial intelligence speaker system according to any one of claims 1 to 4. It has a configuration that can be freely linked with a predetermined sensor.
Any of claims 1 to 5, wherein the artificial intelligence control means is configured to notify the change of the sensing status by using the speaker when the sensing status by the predetermined sensor changes. The artificial intelligence speaker system described in one. It has a configuration that can be freely linked with the specified application software.
At least that the artificial intelligence control means inputs on the predetermined application software based on the grasped content, and the artificial intelligence control means notifies using the speaker based on the notification from the predetermined application software. The artificial intelligence speaker system according to any one of claims 1 to 6 , characterized in that it is configured to execute one of them. It also has artificial intelligence voice emotion recognition means provided in the server,
The artificial intelligence control means transmits the voice input data voiced from the microphone to the artificial intelligence voice emotion recognition means, receives the feedback information from the artificial intelligence voice emotion recognition means, and records the feedback information in the database. The artificial intelligence speaker system according to any one of claims 1 to 7 , wherein the artificial intelligence speaker system is provided. It is application software of an artificial intelligence speaker system including a microphone, a speaker, a communication means, an artificial intelligence control means having a learning function, and a database.
A reading step in which the artificial intelligence control means reads out the content of the current display content using the speaker based on the data of the current display content of the digital signage terminal that can be linked freely.
The artificial intelligence control means grasps the intention of the voice input person by dividing the words of the input data from the microphone by morphological analysis or a word-separation rule, and grasps the words meaningful to the intention, and the intention grasping step.
Based on the grasped contents, the artificial intelligence control means accesses the database by using a communication means, selects a related one from the database, selects and executes a predetermined operation, and performs a predetermined operation. The application software is characterized by including a selection execution step of transmitting a display content change command to a control unit of a digital signage terminal by using a communication means as a selection execution of an operation .

Images