JP5818271B2 - Information processing apparatus, information processing system, information processing method, and program - Google Patents

Description

  The present invention relates to an information processing apparatus, an information processing system, an information processing method, and a program.

  When an inquiry about a product, a failure recovery request, and the like are received from a customer by telephone, the telephone may be received at a base (so-called call center) that collectively receives calls from the customer. In that case, at the call center, an operator or the like asks the caller about information such as a customer name. In many cases, an operator or the like performs a telephone transfer or the like to a base in charge according to a customer. Therefore, in the telephone reception, an operator or the like is required to accurately acquire a customer name or the like.

  Japanese Patent Application Laid-Open No. 2004-151867 discloses a technique for analyzing a conversation between a user and an operator who performs telephone reception and supporting the operator's reception.

  Patent Document 2 discloses a technique for automatically selecting and dispatching an optimum maintenance person for maintenance inspection of each user terminal.

JP 2003-208439 A JP 2004-341964 A

  Each disclosure of the above prior art document is incorporated herein by reference. The following analysis has been made from the viewpoint of the present invention.

  As described above, when a customer inquires about a product or the like is received by telephone, first, information such as a customer name is required to be accurately acquired at a call center.

  However, when talking over the telephone, information may not be acquired correctly depending on the conversation environment of the interlocutor. For example, when a customer makes a call from a noisy environment, a call center operator or the like may not be able to hear the customer name accurately. Alternatively, depending on the loudness of the conversation person, the speaking speed, the tongue, etc., the call center operator or the like may not be able to hear the customer name accurately.

  In such a case, the call center operator or the like often requests the customer to speak the customer name again. For example, consider a case where a call center operator or the like has heard the customer's last name and has heard the name. In that case, the call center operator or the like often requests the interlocutor to utter the surname and first name again. However, asking the customer to speak the same information repeatedly can be detrimental to the customer.

  Here, in the technique disclosed in Patent Document 1, it is assumed that conversation can be accurately recognized. However, the technique disclosed in Patent Document 1 does not describe a case where conversation cannot be accurately recognized.

  In the technique disclosed in Patent Document 2, a user (customer) who requests maintenance using a homepage inputs information necessary for requesting maintenance, such as a product name to be maintained. However, Patent Document 2 does not describe a case where information such as a customer name and a product name is acquired in a conversation.

  Therefore, an object of the present invention is to provide an information processing apparatus, an information processing system, an information processing method, and a program that contribute to effectively utilizing information acquired in a conversation.

According to a first aspect of the present invention, an audio acquisition unit that acquires an audio signal, an input word information estimation unit that estimates one or more input word information based on the audio signal, and one or more A management information acquisition unit that acquires management information in which correspondence information is associated with the registered word information, and a correspondence information acquisition unit that acquires the correspondence information based on the management information and at least one of the input word information When the similarity between the registered word information and the one or more input word information exceeds a predetermined threshold, the correspondence information acquisition unit is associated information associated with the registered word information. Each registered word information is configured to include one or more words, and the correspondence information acquiring unit is configured so that the registered word information includes two or more words. Consist of registered word information, first A first portion included in the word, included in the second word following the first word, a combination of a second portion, the information processing apparatus is provided to match with the input word information.

According to the second aspect of the present invention, an audio acquisition unit that acquires an audio signal, an input word information estimation unit that estimates one or more input word information based on the audio signal, and one or more A management information acquisition unit that acquires management information in which correspondence information is associated with the registered word information, and a correspondence information acquisition unit that acquires the correspondence information based on the management information and at least one of the input word information , an information processing apparatus and a sound analysis device comprising a voice analyzer for analyzing the speech signal, have a, a management information database for storing the management information, the correspondence information acquisition unit, the registration word information When the similarity between the input word information and one or more input word information exceeds a predetermined threshold, correspondence information associated with the registered word information is acquired, and each registered word information is one or more Including the word The correspondence information acquisition unit includes, when the registered word information includes two or more words, a first portion included in the first word that constitutes the one registered word information; There is provided an information processing system for collating a combination with a second part included in a second word following the first word with the input word information .

According to a third aspect of the present invention, the information processing apparatus acquires an audio signal, an input word information estimation step that estimates one or more input word information based on the audio signal, Or a step of acquiring management information in which correspondence information is associated with two or more registered word information, and a correspondence information acquisition step of acquiring the correspondence information based on the management information and at least one of the input word information. , only contains, in the correspondence information acquisition process, and the registration word information, if the one or more of the input word information, the degree of similarity exceeds a predetermined threshold value, the corresponding associated with the registered word information Information is acquired, each of the registered word information includes one or more words, and in the correspondence information acquisition step, the registered word information includes two or more words, The registration unit Constituting the information, a first part included in the first word, it included in the second word following the first word, the information processing combination of the second part, which are matched to the input word information A method is provided.
Note that this method is linked to a specific machine called an information processing apparatus that acquires an audio signal.

According to a fourth aspect of the present invention, there is provided a program to be executed by a computer including a control unit, wherein the control unit acquires a sound signal and one or more inputs based on the sound signal. An input word information estimation process in which the control unit estimates word information, a process in which the control unit acquires management information in which correspondence information is associated with one or more registered word information, the management information, and based on at least one of said input word information, the correspondence information, the correspondence information acquisition process by the control unit acquires, to execute the said computer for controlling an information processing apparatus, in the correspondence information acquisition process, the When the similarity between the registered word information and the one or more input word information exceeds a predetermined threshold, correspondence information associated with the registered word information is acquired, and each registered word The information is configured to include one or more words, and in the correspondence information acquisition process, when the registered word information includes two or more words, the first registered word information is configured. A program is provided in which a combination of a first part included in one word and a second part included in a second word subsequent to the first word is collated with the input word information .
The program can be recorded on a computer-readable storage medium. The storage medium may be non-transient such as a semiconductor memory, a hard disk, a magnetic recording medium, an optical recording medium, or the like. The present invention can also be embodied as a computer program product.

  According to each aspect of the present invention, there are provided an information processing apparatus, an information processing system, an information processing method, and a program that contribute to effectively utilizing information acquired in a conversation.

It is a figure for demonstrating the outline | summary of one Embodiment. It is a figure showing an example of the whole composition of information processing system 1 concerning a 1st embodiment. 3 is a block diagram illustrating an example of an internal configuration of a voice analysis device 4. FIG. It is a block diagram which shows an example of an internal structure of the customer management apparatus 5. It is a figure which shows an example of management information. 3 is a block diagram illustrating an example of an internal configuration of an information processing device 3. FIG. It is a flowchart which shows an example of the process which acquires correspondence information. It is a flowchart which shows an example of a process when a customer cannot be specified. It is a figure which shows an example of the whole structure of the information processing system 1a which concerns on 2nd Embodiment. It is a block diagram which shows an example of the internal structure of the information processing apparatus 3a which concerns on 2nd Embodiment.

  First, an outline of an embodiment will be described with reference to FIG. Note that the reference numerals of the drawings attached to the outline are attached to the respective elements for convenience as an example for facilitating understanding, and the description of the outline is not intended to be any limitation.

  As described above, an information processing apparatus that contributes to the effective use of information acquired in conversation is desired.

  Therefore, as an example, the information processing apparatus 100 illustrated in FIG. 1 is provided. The information processing apparatus 100 includes a voice acquisition unit 101, an input word information estimation unit 102, a management information acquisition unit 103, and a correspondence information acquisition unit 104.

  The voice acquisition unit 101 acquires a voice signal. Then, the input word information estimation unit 102 estimates one or more input word information based on the audio signal. Here, the input word information means a word uttered by the source of the audio signal.

  Further, the management information acquisition unit 103 acquires management information in which correspondence information is associated with one or more registered word information. Here, the registered word information means a word registered in advance. Correspondence information means information associated with registered word information.

  Then, the correspondence information acquisition unit 104 acquires correspondence information based on the management information and at least one input word information.

  Here, an example will be described in which three types of registered word information (first registered word information, second registered word information, and third registered word information) are registered. First, it is assumed that the first registered word information is the name “Taro Tanaka” of customer A and the number “1001” for identifying customer A. The first management information is information in which the address of the sales office in charge of the customer A is associated as correspondence information with the first registered word information.

  Further, it is assumed that the second registered word information is the name “Jiro Tanaka” of customer B and a number “1002” for identifying customer B. The second management information is information in which the address of the sales office in charge of the customer B is associated as correspondence information with the second registered word information.

  Further, it is assumed that the third registered word information is the name “Saburo Nakata” of the customer C and a number “1003” for identifying the customer C. The third management information is information in which the address of the sales office in charge of the customer C is associated as correspondence information with the third registered word information.

  In this case, it is assumed that the sound acquisition unit 101 has acquired a sound signal indicating a sound “Nakata”. In that case, the input word information estimation unit 102 estimates “Nakata” as the input word information.

  Here, the input word information (“Nakata”) is insufficient information for specifying the customer A and the customer C. This is because the information processing apparatus 100 cannot determine whether the input word information (“Nakata”) is a part of the name of the customer A or the last name of the customer C. Therefore, in order to specify the customer A or the customer C from the audio signal, it is required that the name of the customer A or the name of the customer C is accurately uttered. Alternatively, in order to specify the customer A or the customer C, it is required that a number for identifying the customer A or the customer C is uttered.

  However, the correspondence information acquisition unit 104, based on the first management information, the second management information, the third management information, and the input word information (“Nakata”), the address of the sales office in charge of the customer A, and The address of the sales office in charge of the customer C can be acquired as correspondence information. Therefore, the information processing apparatus 100 contributes to effectively using the acquired information even when necessary information cannot be accurately acquired in a conversation.

[First Embodiment]
The first embodiment will be described in more detail with reference to the drawings. In the following description, the source of the audio signal is referred to as an inquiry source. In the following description, it is assumed that the registered word information described above is information registered for specifying a customer.

  FIG. 2 is a diagram illustrating an example of the overall configuration of the information processing system 1 according to the present embodiment. The information processing system 1 includes an exchange 2, an information processing device 3, a voice analysis device 4, a customer management device 5, and a mail server device 6. The exchange 2, the information processing device 3, the voice analysis device 4, the customer management device 5, and the mail server device 6 are connected via a network 7. 2 is not intended to limit the information processing system 1 to the form shown in FIG.

  The exchange 2 relays communication with an inquiry source and an operator who handles the customer. Specifically, the exchange 2 transfers the voice signal received from the inquiry source to the information processing device 3. Further, the exchange 2 relays the transmission of the voice message from the information processing apparatus 3 to a communication partner such as an inquiry sender. In the case of an IP (Internet Protocol) telephone network, the exchange 2 may be an IP telephone server.

  The information processing device 3 analyzes the audio signal received from the exchange 2 and executes processing according to the audio signal. Specifically, the information processing device 3 estimates one or more input word information from the audio signal. Here, the input word information means information for specifying a customer input using a voice signal. That is, the input word information means information such as a customer number, a customer name, and a contact address uttered by the customer.

  Then, the information processing apparatus 3 notifies the estimated input customer information and the like to the customer's responsible base based on the estimated input customer information. The information processing apparatus 3 may be a so-called CTI (Computer Telephony Integration) server apparatus.

  The voice analysis device 4 analyzes the voice signal and divides the voice signal into one or more words. Specifically, the information processing apparatus 3 transmits the voice signal received from the exchange 2 to the voice analysis apparatus 4. Then, the voice analysis device 4 analyzes the voice signal received from the information processing device 3.

  The customer management device 5 stores management information. Then, the customer management device 5 transmits management information to the information processing device 3 in response to a request from the information processing device 3.

  The mail server device 6 is a device that controls transmission and reception of electronic mail.

  The network 7 includes a network such as the Internet or a LAN (Local Area Network). There are various types of networks, but the details are not limited.

  FIG. 3 is a block diagram illustrating an example of the internal configuration of the voice analysis device 4. The voice analysis device 4 includes a voice analysis device communication unit 41 and a voice analysis unit 42. FIG. 3 mainly describes the voice analysis device 4 according to the present embodiment for the sake of simplicity.

  The voice analysis device communication unit 41 controls communication between the voice analysis device 4 and the information processing device 3. Specifically, the voice analysis device communication unit 41 receives a voice signal from the information processing device 3. Furthermore, the voice analysis device communication unit 41 transmits the analysis result of the received voice signal to the information processing device 3.

  The voice analysis unit 42 divides the voice signal into one or more words. Specifically, the voice analysis unit 42 analyzes the voice signal received by the voice analysis device communication unit 41 and divides it into one or more words. For example, the voice analysis unit 42 may analyze a voice signal by applying a technique using a hidden Markov model. There are various methods for analyzing the audio signal, but the details are not limited.

  Then, the voice analysis unit 42 outputs the divided words as a character string. Then, the voice analysis unit 42 transmits the output character string to the information processing device 3 via the voice analysis device communication unit 41.

  FIG. 4 is a block diagram illustrating an example of an internal configuration of the customer management device 5. The customer management device 5 includes a management information database 51 and a customer management device communication unit 52. For simplicity, FIG. 4 mainly describes modules related to the customer management apparatus 5 according to the present embodiment.

  The management information database 51 stores management information of each customer. As described above, the management information is information in which correspondence information is associated with one or more registered word information. For example, the registered word information may be information relating to a customer number, customer name, contact information, product name to be maintained, and the like. Further, the correspondence information may be an address (for example, an email address) of a correspondence base of each customer. In this case, the management information is information in which the address of each customer's corresponding base is associated with information such as a customer number.

  The customer management device communication unit 52 controls communication between the customer management device 5 and the information processing device 3. Specifically, the customer management device communication unit 52 transmits management information to the information processing device 3 that transmits the information in response to a request from the information processing device 3.

  FIG. 5 is a diagram illustrating an example of management information. In the case of FIG. 5, the registered word information is “customer number”, “customer name”, “contact”, and “product model number”. In the case of FIG. 5, the correspondence information is “responsible base” and “base address”. That is, the management information shown in FIG. 5 is information in which “customer number”, “customer name”, “contact”, “product name”, “product model number”, “responsible base”, and “base address” are associated with each other. is there. FIG. 5 shows the management information of the customer number “12345678”, the management information of the customer number “11223344”, and the management information of the customer number “556667788”. Note that FIG. 5 is not intended to limit the management information to the information shown in FIG.

  FIG. 6 is a block diagram illustrating an example of the internal configuration of the information processing apparatus 3. The information processing device 3 includes an information processing device communication unit 31, a voice acquisition unit 32, a management information acquisition unit 33, a priority order determination unit 34, a voice request unit 35, an input word information estimation unit 36, and correspondence information An acquisition unit 37 and a correspondence processing unit 38 are included. FIG. 6 mainly describes modules related to the information processing apparatus 3 according to the present embodiment for the sake of simplicity.

  The information processing device communication unit 31 controls communication with the exchange 2, the voice analysis device 4, the customer management device 5, and the mail server 6.

  The voice acquisition unit 32 acquires a voice signal. Specifically, the voice acquisition unit 32 acquires a voice signal received by the exchange 2.

  The management information acquisition unit 33 acquires management information in which correspondence information is associated with one or more registered word information. Specifically, the management information acquisition unit 33 accesses the management information database 51 and acquires management information.

  The priority order determination unit 34 determines the priority order for each type of registered word information.

  The voice request unit 35 requests voice input of registered word information for each type of registered word information. For example, consider a case where the voice request unit 35 requests input of a customer name. In this case, the voice request unit 35 transmits a voice message such as “Please say your name” to the inquiry source via the information processing device communication unit 31. Here, the voice request unit 35 may generate a voice synthesized voice. In that case, the voice request unit 35 outputs a voice message such as “Please say your name” using the voice synthesized voice. Alternatively, the voice request unit 35 may output a previously recorded voice message. The same applies to the case where the voice request unit 35 requests other types of registered word information, and detailed description thereof will be omitted.

  Also, consider a case where the priority order determination unit 34 determines the priority order for each type of registered word information. In that case, the voice request unit 35 may request voice input of the registered word information in the order of the registered word information having the highest priority. For example, it is assumed that the priority order determination unit 34 determines the priority order in the order of “customer number”, “customer name”, and “product number”. In this case, the voice request unit 35 may request voice input in the order of “customer number”, “customer name”, and “product number”. When the correspondence information acquisition unit 37 specifies one customer based on the customer number and the customer name, the voice request unit 35 preferably ends the voice input request.

  The input word information estimation unit 36 estimates one or more types of input word information based on the audio signal. Specifically, the input word information estimation unit 36 transmits an audio signal to the audio analysis device 4 via the information processing device communication unit 31. Then, the input word information estimation unit 36 receives the character string (word group) output from the voice analysis unit 42 from the voice analysis device 4 via the information processing device communication unit 31. And the input word information estimation part 36 estimates the word group which the audio | voice analysis part 42 outputs as 1 or 2 or more said input word information.

  The correspondence information acquisition unit 37 acquires correspondence information based on the management information and at least one input word information. Specifically, when the similarity between the registered word information and one or more input word information exceeds a predetermined threshold, the correspondence information acquisition unit 37 displays the correspondence information associated with the registered word information. You may get it. For example, the correspondence information acquisition unit 37 acquires the correspondence information associated with the registered word information when a predetermined ratio (for example, 90%) of the character string of the registered word information matches the input word information. Also good.

  Further, the correspondence information acquisition unit 37 may specify at least one customer based on the registered word information and at least one input word information.

  For example, consider a case where the management information database 51 stores registered word information shown in FIG. Then, it is assumed that the voice analysis unit 42 outputs “ABC” as a word corresponding to the customer name. In this case, the correspondence information acquisition unit 37 acquires the base address “aaa@co.jp” and the base address “bbb@co.jp” corresponding to the customer name “ABC” as notification destinations (corresponding information).

  The correspondence processing unit 38 performs processing according to the correspondence information. For example, when the base address corresponding to the customer is used as the correspondence information, the correspondence processing unit 38 may notify the base address of the inquiry. In this case, the notification method may include a telephone transfer process for inquiries, an e-mail transmission process, and the like.

  For example, when the correspondence information acquisition unit 37 specifies one customer based on the management information and at least one input word information, the correspondence processing unit 38 determines the source of the audio signal, the base in charge of the customer, May be in a communicable state. That is, the response processing unit 38 may transfer a telephone call from the inquiry source to the identified customer's base.

  In addition, when the correspondence information acquisition unit 37 specifies two or more customers based on the management information and at least one input word information, the correspondence processing unit 38 sends the corresponding customer's base to each customer Confirmation may be instructed. For example, the response processing unit 38 may notify the customer in charge of each customer using an e-mail or the like that the customer has made an inquiry. Alternatively, the response processing unit 38 may instruct the customer's responsible base so as to confirm whether or not the customer has been inquired using e-mail or the like. Of course, even when the correspondence information acquisition unit 37 specifies one customer, the correspondence processing unit 38 may instruct confirmation of the customer to the base in charge of each customer.

  Next, the operation of the information processing system 1 will be described. In the following description, for the purpose of explanation, information related to a customer among registered word information is referred to as registered customer information. Also, in the following description, for the sake of explanation, information related to a product among registered word information is referred to as registered product information. Moreover, in the following description, for description, information related to a customer among input word information is referred to as input customer information. Further, in the following description, for the purpose of explanation, information related to a product among input word information is referred to as input product information.

  FIG. 7 is a flowchart illustrating an example of processing for acquiring correspondence information.

  In step S1, the voice request unit 35 requests voice input of registered customer information.

  In step S2, the voice analysis unit 42 acquires one or more words based on the voice signal.

  In step S <b> 3, the correspondence information acquisition unit 37 determines whether registered customer information whose similarity with the acquired word exceeds a predetermined threshold is registered in the management information database 51.

  When registered customer information whose similarity to the acquired word exceeds a predetermined threshold is registered in the management information database 51 (Yes branch of step S3), the process proceeds to step S6. On the other hand, if registered customer information whose similarity to the acquired word exceeds a predetermined threshold is not registered in the management information database 51 (No branch of step S3), the process proceeds to step S4.

  In step S4, the voice request unit 35 determines whether or not a voice input of a predetermined type of registered customer information is requested. For example, it is assumed that the voice request unit 35 has determined in advance to request “customer number”, “customer name”, and “contact phone number”. In that case, the voice requesting unit 35 determines whether or not a voice input of “customer number”, “customer name”, and “contact phone number” has been requested to the inquiry source.

  When the voice request unit 35 requests voice input of a predetermined type of registered customer information (Yes branch in step S4), the voice request unit 35 proceeds to step S101 shown in FIG. On the other hand, if the voice request unit 35 does not request voice input of a predetermined type of registered customer information (No branch in step S4), the voice request unit 35 proceeds to step S5.

  In step S5, the voice request unit 35 changes the type of registered customer information to be requested. And it returns to step S1 and continues a process. Here, it is preferable that the voice request unit 35 changes the type of registered customer information that requests voice input based on the priority order determined by the priority order determination unit 34.

  On the other hand, in step S6, the voice request unit 35 requests voice input of registered product information. The input word information estimation unit 36 uses the product-related information input by voice as input product information. And it changes to step S7. For example, the voice request unit 35 transmits a voice message such as “Please say the product number” to the inquiry source via the information processing device communication unit 31. Here, the registered product information may be information such as “product number” and “product model number”.

  In step S <b> 7, the correspondence information acquisition unit 37 specifies a responsible base based on the input customer information and the input product information. Then, the response processing unit 38 executes processing such as telephone transfer and e-mail transmission to the base in charge.

  FIG. 8 is a flowchart showing an example of processing when a customer cannot be specified based on input customer information.

  In step S101, the voice request unit 35 requests voice input of registered product information. The input word information estimation unit 36 uses the product-related information input by voice as input product information.

  In step S102, the correspondence information acquisition unit 37 determines whether one customer is specified based on the input product information. When one customer is identified (Yes branch in step S102), the process proceeds to step S103. On the other hand, when one customer is not specified (No branch of step S102), the process proceeds to step S104.

  When one customer is identified based on the input product information (Yes branch in step S102), the correspondence information acquisition unit 37 acquires the customer's assigned base as the correspondence information based on the management information. Then, the response processing unit 38 executes processing such as telephone transfer and mail transfer to the responsible site (step S103).

  On the other hand, in step S104, the correspondence information acquisition unit 37 determines whether or not two or more customers are specified based on the input product information. When two or more customers are identified (Yes branch in step S104), the response processing unit 38 executes processing such as sending an e-mail to each responsible site of each identified customer. On the other hand, when two or more customers are not specified (No branch in step S104), the information processing apparatus 3 ends the process. In this case, the information processing apparatus 3 may notify the inquiry source that the customer has not been specified by a voice message or the like.

  As described above, the information processing system 1 according to the present embodiment requests the inquiry source to input one or more registered customer information by voice. The information processing system 1 according to the present embodiment estimates one or more input customer information based on the input audio signal. In particular, the information processing system 1 according to the present embodiment can estimate customers even when registered customer information registered in advance does not match two or more pieces of input customer information that have been input. And the information processing system 1 which concerns on this embodiment can perform a notification etc. to a customer's corresponding base quickly based on the acquired information. Therefore, the information processing system 1 according to the present embodiment contributes to effectively using information acquired in conversation.

  Further, in the information processing system 1 according to the present embodiment, when the information processing apparatus 3 specifies a customer, it is not necessary for the customer to utter other registered customer information. Further, in the information processing system 1 according to the present embodiment, when the information processing apparatus 3 cannot identify a customer, it requests other registered customer information from the inquiring customer. Therefore, in the information processing system 1 according to the present embodiment, the customer who is the inquiry source does not need to repeat the same information and speak. Therefore, the information processing system 1 according to the present embodiment contributes to reducing the burden on customers who make inquiries.

[Second Embodiment]
Next, a second embodiment will be described in detail with reference to the drawings.

  In the present embodiment, the information processing apparatus performs voice analysis. In the description of the present embodiment, the description of the same parts as those in the first embodiment is omitted. Further, in the description of the present embodiment, the same components as those in the first embodiment are denoted by the same reference numerals, and the description thereof is omitted.

  FIG. 9 is a diagram illustrating an example of the overall configuration of the information processing system 1a according to the present embodiment. The difference between the information processing system 1 shown in FIG. 2 and the information processing system 1 a shown in FIG. 9 is that the information processing system 1 includes a voice analysis device 4. Further, the information processing system 1a shown in FIG.

  FIG. 10 is a block diagram illustrating an example of an internal configuration of the information processing apparatus 3a according to the present embodiment. A difference between the information processing apparatus 3 illustrated in FIG. 6 and the information processing apparatus 3 a illustrated in FIG. 10 is that the information processing apparatus 3 a includes a voice analysis unit 42.

  The information processing apparatus 3a according to the present embodiment performs voice analysis. For example, in the case of the information processing system 1 according to the first embodiment, a communication delay between the information processing device 3 and the voice analysis device 4 may occur. However, in the case of the information processing system 1a according to the present embodiment, the information processing apparatus 3a does not cause a communication delay via the network 7 when performing voice analysis. Therefore, the information processing system 1a according to the present embodiment can further promptly notify the customer's corresponding base of the information processing system 1a.

  Further, the information processing system 1a according to the present embodiment can execute the same processing as the information processing system 1 with a smaller apparatus configuration. Therefore, the information processing system 1a according to the present embodiment can reduce the cost for system construction.

  In the above-described embodiment, the configuration in which the management information database is arranged outside the information processing apparatus has been described. However, the management information database may be arranged inside the information processing apparatus.

  A part or all of the above embodiments can be described as in the following supplementary notes, but is not limited thereto.

  (Additional remark 1) It is as the information processing apparatus which concerns on a said 1st viewpoint.

  (Additional remark 2) The said registration word information contains the information which specifies a customer, The said correspondence information acquisition part specifies at least 1 customer based on the said registration word information and at least 1 said input word information The information processing apparatus according to 1.

  (Additional remark 3) When the said correspondence information contains the information regarding a customer's correspondence base, and the said correspondence information acquisition part specifies two or more customers based on the said registration word information and at least one said input word information The information processing apparatus according to appendix 2, further comprising: a corresponding processing unit that instructs each customer in charge to confirm each customer.

  (Supplementary Note 4) When the correspondence processing unit identifies one customer based on the registered word information and at least one of the input word information, the correspondence information acquisition unit, The information processing apparatus according to appendix 3, wherein communication with the customer's assigned base is possible.

  (Supplementary note 5) The information processing apparatus according to any one of supplementary notes 1 to 3, wherein the registered word information includes at least one of customer number, customer name, and contact information.

  (Additional remark 6) The audio | voice analysis part which divides the said audio | voice signal into 1 or 2 or more word groups is provided, The said input word information estimation part estimates the said word group as 1 or 2 or more said input word information The information processing apparatus according to any one of 1 to 4.

  (Supplementary note 7) When the similarity between the registered word information and one or more of the input word information exceeds a predetermined threshold, the correspondence information acquisition unit is associated with the registered word information. The information processing apparatus according to any one of supplementary notes 1 to 6, wherein:

  (Additional remark 8) The information processing apparatus as described in any one of additional remarks 1 thru | or 7 provided with the audio | voice request | requirement part which requests | requires the audio | voice input of the said registered word information for every kind of the said registered word information.

(Supplementary Note 9) A priority order determining unit that determines a priority order for each type of the registered word information,
The information processing apparatus according to appendix 8, wherein the voice request unit requests voice input of the registered word information based on the priority order.

  (Supplementary Note 10) As in the information processing system according to the second viewpoint.

  (Supplementary Note 11) The speech analysis unit divides the speech signal into one or more word groups, and the input word information estimation unit estimates the word groups as one or more input word information. The information processing system according to attachment 10.

  (Additional remark 12) It is as the information processing method concerning the said 3rd viewpoint.

  (Additional remark 13) When the said registration word information contains the information which specifies a customer, in the said corresponding | compatible information acquisition process, at least 1 customer is specified based on the said registration word information and at least 1 said input word information. The information processing method according to attachment 12.

  (Additional remark 14) When the said correspondence information includes the information regarding a customer's corresponding base, 2 or more customers are specified based on the said registration word information and at least one said input word information, and the base in charge of each said customer The information processing method according to appendix 13, further comprising a corresponding processing step for instructing confirmation of each customer.

  (Supplementary Note 15) In the correspondence processing step, when one customer is specified based on the registered word information and at least one input word information, the source of the audio signal, the base in charge of the customer, 15. The information processing method according to appendix 14, wherein communication is performed in a communicable state.

  (Additional remark 16) The audio | voice analysis process which divides | segments the said audio | voice signal into 1 or 2 or more word groups, In the said input word information estimation process, the said word group is estimated as 1 or 2 or more said input word information The information processing method according to any one of 12 to 15.

  (Supplementary Note 17) In the correspondence information acquisition step, when the similarity between the registered word information and one or more input word information exceeds a predetermined threshold, the correspondence information associated with the registered word information The information processing method according to any one of appendices 12 to 16, wherein

  (Additional remark 18) The information processing method as described in any one of additional remarks 12 thru | or 17 including the audio | voice request | requirement process which requests | requires the audio input of the said registered word information for every kind of the said registered word information.

  (Supplementary note 19) In Supplementary note 18, which includes a priority order determining step for determining a priority order for each type of the registered word information, and in the voice request step, requests voice input of the registered word information based on the priority order. The information processing method described.

  (Additional remark 20) It is as the program which concerns on the said 4th viewpoint.

  (Additional remark 21) When the said registration word information contains the information which specifies a customer, in the said corresponding | compatible information acquisition process, at least 1 customer is specified based on the said registration word information and at least 1 said input word information The program according to appendix 20.

  (Additional remark 22) When the said correspondence information contains the information regarding a customer's corresponding base, based on the said registration word information and at least one said input word information, 2 or more customers are specified, The base in charge of each said customer The program according to appendix 21, which executes corresponding processing for instructing confirmation of each customer.

  (Supplementary Note 23) In the handling process, when one customer is specified based on the registered word information and at least one of the input word information, the source of the audio signal, the base in charge of the customer, The program according to appendix 22, which makes the communication possible state.

  (Additional remark 24) The audio | voice analysis process which divides | segments the said audio | voice signal into 1 or 2 or more word groups is performed, and the said word group is estimated as 1 or 2 or more said input word information in the said input word information estimation process The program according to any one of appendices 20 to 23.

  (Supplementary Note 25) In the correspondence information acquisition process, when the similarity between the registered word information and one or more input word information exceeds a predetermined threshold, the correspondence information associated with the registered word information The program according to any one of appendices 20 to 24, which acquires

  (Additional remark 26) The program as described in any one of additional marks 20 thru | or 25 which performs the audio | voice request | requirement process which requests | requires the audio input of the said registered word information for every kind of the said registered word information.

  (Additional remark 27) The priority determination process which determines a priority for every kind of the said registration word information is performed, In the said audio | voice request | requirement process, the audio | voice input of the said registration word information is requested | required based on the said priority. The program described in.

  In addition, each disclosure of the cited patent document is incorporated herein by reference. Within the scope of the entire disclosure (including claims) of the present invention, the embodiments and examples can be changed and adjusted based on the basic technical concept. In addition, various combinations of various indication elements (including each element of each claim, each element of each embodiment or example, each element of each drawing, etc.) within the scope of the claims of the present invention, Selection is possible. That is, the present invention of course includes various variations and modifications that could be made by those skilled in the art according to the entire disclosure including the claims and the technical idea. In particular, with respect to the numerical ranges described in this document, any numerical value or small range included in the range should be construed as being specifically described even if there is no specific description.

1, 1a Information processing system 2 Exchange 3, 3a, 100 Information processing device 4 Voice analysis device 5 Customer management device 6 Mail server device 7 Network 31 Information processing device communication unit 32, 101 Voice acquisition unit 33, 103 Management information acquisition unit 34 Priority order determination unit 35 Voice request unit 36, 102 Input word information estimation unit 37, 104 Corresponding information acquisition unit 38 Corresponding processing unit 41 Speech analysis device communication unit 42 Speech analysis unit 51 Management information database 52 Customer management device communication unit

Claims (10)

An audio acquisition unit for acquiring audio signals;
An input word information estimation unit that estimates one or more input word information based on the voice signal;
A management information acquisition unit that acquires management information in which correspondence information is associated with one or more registered word information;
A correspondence information acquisition unit that acquires the correspondence information based on the management information and at least one of the input word information;
Equipped with a,
The correspondence information acquisition unit acquires the correspondence information associated with the registered word information when the similarity between the registered word information and the one or more input word information exceeds a predetermined threshold,
Each of the registered word information includes one or more words,
When the registered word information includes two or more words, the correspondence information acquisition unit includes a first portion included in the first word and the first word constituting the one registered word information An information processing apparatus that collates a combination with a second part included in a second word subsequent to the input word information . The registered word information includes information for identifying a customer,
The information processing apparatus according to claim 1, wherein the correspondence information acquisition unit specifies at least one customer based on the registered word information and at least one input word information. The correspondence information includes information on a customer's correspondence base,
When the correspondence information acquisition unit specifies two or more customers based on the registered word information and at least one of the input word information, a correspondence instructing each customer to confirm the customer The information processing apparatus according to claim 2, further comprising a processing unit.   The correspondence processing unit, when the correspondence information acquisition unit identifies one customer based on the registered word information and at least one input word information, a source of the voice signal and a charge of the customer The information processing apparatus according to claim 3, wherein the base station is in a communicable state. A speech analysis unit that divides the speech signal into one or more word groups;
The information processing apparatus according to any one of claims 1 to 4, wherein the input word information estimation unit estimates the word group as one or more input word information.   The information processing apparatus according to any one of claims 1 to 5, further comprising: a voice request unit that requests voice input of the registered word information for each type of the registered word information. An audio acquisition unit for acquiring audio signals;
An input word information estimation unit that estimates one or more input word information based on the voice signal;
A management information acquisition unit that acquires management information in which correspondence information is associated with one or more registered word information;
A correspondence information acquisition unit that acquires the correspondence information based on the management information and at least one of the input word information;
An information processing apparatus comprising:
A voice analysis device comprising a voice analysis unit for analyzing the voice signal;
A management information database for storing the management information;
I have a,
The correspondence information acquisition unit acquires the correspondence information associated with the registered word information when the similarity between the registered word information and the one or more input word information exceeds a predetermined threshold,
Each of the registered word information includes one or more words,
When the registered word information includes two or more words, the correspondence information acquisition unit includes a first portion included in the first word and the first word constituting the one registered word information The information processing system characterized by collating the combination with the 2nd part contained in the 2nd word which follows to the said input word information . The speech analysis unit divides the speech signal into one or more word groups,
The information processing system according to claim 7, wherein the input word information estimation unit estimates the word group as one or more input word information. Information processing device
Obtaining an audio signal;
An input word information estimation step of estimating one or more input word information based on the voice signal;
Obtaining management information in which correspondence information is associated with one or more registered word information;
A correspondence information acquisition step of acquiring the correspondence information based on the management information and at least one of the input word information;
Only including,
In the correspondence information acquisition step, when the similarity between the registered word information and the one or more input word information exceeds a predetermined threshold, correspondence information associated with the registered word information is acquired,
Each of the registered word information includes one or more words,
In the correspondence information acquisition step, when the registered word information includes two or more words, the first part included in the first word and the first word constituting the one registered word information The information processing method characterized by collating with the said input word information the combination with the 2nd part contained in the 2nd word which follows . A program to be executed by a computer having a control unit,
A process in which the control unit acquires an audio signal;
An input word information estimation process in which the control unit estimates one or more input word information based on the voice signal;
A process in which the control unit acquires management information in which correspondence information is associated with one or more registered word information;
Based on the management information and at least one input word information, the correspondence information is acquired by the control unit ;
Was performed on the computer that controls the information processing apparatus,
In the correspondence information acquisition process, when the similarity between the registered word information and the one or more input word information exceeds a predetermined threshold, correspondence information associated with the registered word information is acquired,
Each of the registered word information includes one or more words,
In the correspondence information acquisition process, when the registered word information includes two or more words, the first part included in the first word and the first word constituting the one registered word information A program in which a combination with the second part included in the second word following is collated with the input word information .

Images