JP5814879B2 - Posted audio playback control system, posted audio playback control method, posted audio playback control program - Google Patents

Description

  The present invention relates to a posted audio playback control system, a posted audio playback control method, and a posted audio playback control program. Specifically, it efficiently and efficiently selects similar posted audio in a message service such as an audio SNS, The present invention relates to a technology that enables reproduction and good transmission of poster intentions.

  In recent years, in addition to the existing text-based SNS (Social Network Service), voice SNSs for posting and publishing voice messages have appeared and are spreading. In the voice SNS, a user's voice posting, that is, a real voice is heard by another user having a connection with the corresponding user in the SNS, so that emotional and realistic communication between the users is achieved. In such a voice SNS, it is assumed that various new services will be developed because the posting is voice. For example, as an existing technology for simultaneously playing back the same type of sound source, it has a sound storage unit consisting of multiple sound source boxes that individually store sound sources such as announcement sound or background music, and superimposes the sound content from multiple sound sources For example, a voice mail voice message superimposing method (see Patent Document 1) is proposed.

Japanese Patent Laid-Open No. 7-212475

  In the message service such as the above-described voice SNS, for example, in accordance with various events such as the user's birthday and ceremonial occasion, many other users connected to the user may post messages having similar contents. . In that case, the user repeatedly listens to the posted voice with similar contents for a long time. On the other hand, in each posted voice, the utterance pace and the appearance timing of a specific keyword in a message differ finely for each poster. For this reason, there is a concern that when the posted audios having similar contents are simultaneously reproduced, the user cannot hear the posted contents and the intention of the poster side is not transmitted well.

  In addition, the posted audio from other users played by the user includes not only those posted in accordance with a specific event, but also many daily irrelevant events. Therefore, it is necessary for the user to pick up only the posted audio related to a specific event from a huge number of posted audio, which may be a psychological burden when reproducing the posted audio. . In particular, as the user has more connections with other users on the voice SNS, such a burden becomes greater, and there is a concern that usability is reduced.

  SUMMARY OF THE INVENTION An object of the present invention is to provide a technology that enables efficient selection and reproduction of similar posted voices in a message service such as a voice SNS without trouble and enabling good transmission of poster intentions.

The posted audio reproduction control system of the present invention that solves the above problems includes a communication unit that communicates via a network with a user terminal used by a user of a social network service, event identification information, and a selection keyword that is selected in advance with respect to the event. And a storage unit that stores a determination table that associates with each other, and among the posted voice data received from the user terminal via the communication unit, the one to which the designation information of the same posting release destination is given is specified and specified Performs speech recognition processing on each posted voice data to generate text data, stores the generated text data in the storage unit for each posting publication destination, and determines each text data having a common posting publication destination against each selected keyword table, the text data contained identical selection keyword, the same Start of the process and, posts in the audio data, the same selection keyword of an audio signal included in the group of the simultaneous reproduction object to be stored in the storage unit as a specific group of co reproduced as relating draft published destination and the same event or searching the end, when the unwanted section from data head to the start point, or delete the audio signals of the unnecessary section up data end from the end, was regenerated each post audio data after the deletion execution time And a calculation unit that executes a process of transmitting data that can be output by the voice output unit to the user terminal.

In addition, the posted audio reproduction control method of the present invention corresponds to the communication unit that communicates via the network with the user terminal used by the user of the social network service, the identification information of the event, and the selection keyword selected in advance for the event. A computer having a storage unit for storing the attached determination table identifies the posted audio data received from the user terminal via the communication unit to which the same posting publication designation information is given, and Performs speech recognition processing on each identified posted voice data to generate text data, stores the generated text data in the storage unit for each posting publication destination, and each text data having a common posting publication destination. against each selected keyword of the determination table, the text data contained identical selection keywords A process of storing in the storage unit as a specific group of co reproduced as related to the same post disclosure destination and the same event, included in the group of the simultaneous reproduction object, beginning or end of the same selected keyword speech signal And delete the audio signal of the unnecessary section from the beginning of the data to the start time or the unnecessary section from the end time to the end of the data , A process of transmitting data that can be output by the output means to the user terminal is executed.

In addition, the posted audio reproduction control program of the present invention corresponds to a communication unit that communicates with a user terminal used by a user of a social network service via a network, event identification information, and a selection keyword selected in advance for the event. A computer having a storage unit for storing the attached determination table, and identifying the post audio data received from the user terminal via the communication unit to which the same post publishing destination designation information is given, Performs speech recognition processing on each identified posted voice data to generate text data, stores the generated text data in the storage unit for each posting publication destination, and each text data having a common posting publication destination. against each selected keyword of the decision table, it contained the same selection keyword text de The data, a process of storing in the storage unit as a specific group of co reproduced as related to the same post disclosure destination and the same event, included in the group of the simultaneous playback target, the start point of the same selected keyword speech signal or searching the end, when the unwanted section from data head to the start point, or delete the audio signals of the unnecessary section up data end from the end, was regenerated each post audio data after the deletion execution time And a process of transmitting data that can be output by the voice output means to the user terminal.

  According to the present invention, similar posted voices in a message service such as voice SNS can be efficiently selected and played back without any trouble, and good transmission of the poster intention can be achieved.

It is a network block diagram containing the contribution audio | voice reproduction | regeneration control system of 1st Embodiment. It is a figure which shows the hardware structural example of the SNS server of 1st Embodiment. It is a figure which shows the hardware structural example of the public Web server of 1st Embodiment. It is a figure which shows the hardware structural example of the posting recording apparatus of 1st Embodiment. It is a figure which shows an example of the determination table of 1st Embodiment. It is a flowchart which shows the process sequence example of the contribution audio | voice reproduction | regeneration control method in 1st Embodiment. It is a figure which shows Example 1 of the contribution audio | voice data of 1st Embodiment. It is a figure which shows Example 1 of the file for synthetic | combination reproduction | regeneration of 1st Embodiment. It is a figure which shows Example 2 of the file for synthetic | combination reproduction | regeneration of 1st Embodiment. It is a figure which shows Example 2 of the contribution audio | voice data of 1st Embodiment. It is a figure which shows Example 3 of the file for synthetic | combination reproduction | regeneration of 1st Embodiment. It is a figure which shows the example of a process result in 1st Embodiment. It is a figure which shows the hardware structural example of the SNS server of 2nd Embodiment. It is a figure which shows an example of the evaluation table of 2nd Embodiment. It is a figure which shows an example of the user table of 2nd Embodiment. It is a figure which shows an example of the contribution audio | voice data information table of 2nd Embodiment. It is a flowchart which shows the process sequence example of the music selection assistance method of 2nd Embodiment. It is a figure which shows the evaluation result example 1 in 2nd Embodiment. It is a figure which shows the evaluation result example 2 in 2nd Embodiment. It is a figure which shows the hardware structural example of the SNS server of 3rd Embodiment. It is a figure which shows an example of the grouping table of 3rd Embodiment. It is a figure which shows an example of the priority evaluation table of 3rd Embodiment. It is a figure which shows an example of the user table of 3rd Embodiment. It is a flowchart which shows the process sequence example of the contribution audio | voice reproduction | regeneration control method in 3rd Embodiment. It is a figure which shows the example of an evaluation result in 3rd Embodiment.

--- System configuration in the first embodiment ---
Embodiments of the present invention will be described below in detail with reference to the drawings. FIG. 1 is a network configuration diagram including a posted audio reproduction control system 1002 according to the first embodiment. A posted voice playback control system 1002 (hereinafter, system 1002) shown in FIG. 1 can efficiently select and play back similar posted voices in a message service such as a voice SNS without trouble, thereby enabling good transmission of poster intentions. Computer system.

  Note that the voice SNS is an SNS in which a voice message is posted and released, unlike a conventional text-based SNS. In the voice SNS, a user's voice posting, that is, a real voice is heard by another user having a connection with the corresponding user in the SNS, so that emotional and realistic communication between the users is achieved.

  A system 1002 illustrated in FIG. 1 includes an SNS server 150, a public Web server 160, and a posting recording device 170. The SNS server 150 is a main execution subject of various processes related to the voice SNS, manages authentication information related to users of the voice SNS, information of posted voice data of each user, and processes such as user authentication and published voice playback and playback. It becomes the server device which executes. The public Web server 160 is located between the user terminal 200 accessed via the Internet network 120 and the above-described SNS server 150. The user authentication process in the SNS server 150 and the output from the above-described SNS server 150 are output. The server device mediates exchange of various data such as reproduction data of posted audio data. The posting recording device 170 is an information processing device that stores posted voice data sent from the user terminal 200. In response to a request from the SNS server 150, the posted recording data 170 reads out the posted voice data specified by the request. This is sent to the server 150.

  Of course, in the SNS server 150, as a form of the social network service, for each user, a connection on the voice SNS (eg, friend, acquaintance, colleague, family, unilateral follower, hobby / preference group, etc.) ) Is managed for other users. Therefore, the posted voice that can be reproduced and heard by the user is that of another user having such a connection. Therefore, in the posting recording device 170, for each user, the posted audio data of other users posted to the corresponding user or the corresponding group is linked and managed.

  The public Web server 160 and the SNS server 150 specify an access user through a predetermined user authentication process when accessing from the user terminal 200 (the contributor terminal 220 and the browsing player terminal 240), and post it in association with the corresponding user. Information on posted audio data from other users managed by the recording device 170 (e.g., posting user name, posting date / time, title, recording length, etc.), a page for the corresponding user (so-called my page on the SNS site) Then, for example, the page data is set to be listed in order of posting date and time, and the page data is transmitted to the corresponding user terminal 200.

  When the public Web server 160 receives a playback instruction for a predetermined post from the user terminal 200 on the user page, the public Web server 160 sends information on the playback instruction regarding the post to the SNS server 150. The SNS server 150 receives this reproduction instruction information, reads the posted audio data related to the corresponding posting from the posting recording device 170 and reproduces it, and transmits the reproduced data to the user terminal 200 via the public Web server 160. The user terminal 200 receives this reproduction data via the Internet network 120 and outputs it through a speaker.

  On the other hand, the terminal used by the user of the voice SNS is the user terminal 200. For example, as shown in FIG. 1, the user terminal 200 can be classified into contributor terminals 220 and 230 and a browsing player terminal 240. The poster terminal 220 accesses the public Web server 160 via the Internet network 120, acquires and displays the data of the voice SNS website published on the public Web server 160, and the posted voice by the own user. Is input to the public Web server 160 by accepting the input by the microphone. Further, the browsing player terminal 240 is a terminal that accesses the public Web server 160 via the Internet network 120 and acquires and displays data of the website of the voice SNS published on the public Web server 160.

  In addition, when the contributor terminal 220 and the browsing player terminal 240 access the public Web server 160, of course, a user authentication process for logging in to a page for oneself in the voice SNS is necessary. Therefore, the contributor terminal 220 and the browsing / playback terminal 240 accept input of authentication information by a user in use, and transmit this to the SNS server 150 via the public Web server 160 together with an authentication request. In this case, the SNS server 150 performs user authentication by collating the authentication information with a database or the like that stores authentication information, and according to the authentication result, the corresponding contributor terminal 220 or the browsing player terminal. The access to the corresponding user page in the public Web server 160 from 240 is controlled. Further, the SNS server 150 transmits the authentication result to the poster terminal 220 and the browsing player terminal 240 via the public Web server 160.

  Further, as described above, in addition to the case where the posting voice data and its reproduction data are exchanged via the Internet network 120, the posting voice data and the like using the telephone function of the user terminal 200 and the public line network 122, etc. It is also possible to assume a form in which the reproduction data is exchanged. In this case, as shown in FIG. 1, the network configuration includes a telephone answering system 300 connected to the SNS server 150 and the post recording device 170 via the LAN line 121.

  The telephone response system 300 includes an exchange 310, an automatic voice response device 320, and a CTI (Computer Telephony Integration) device 330. Among them, the exchange 310 is an exchange for interconnecting telephone lines to form a telephone network, and the automatic voice response device 320 is a device that performs a telephone response and voice information input / output and dialogue with a computer, The CTI device 330 is a device that integrates a telephone or a fax into a computer system.

  In such a configuration, when an utterance is made from a contributor terminal 230, which is a user terminal, to a predetermined post acceptance telephone number, the contributor terminal 230 is connected to the exchange 310 via the public network 122, and this connection In response to this, an utterance number is acquired by the CTI device 330 and automatic voice guidance reproduction is performed by the automatic response device 320. Thereafter, in the above-described poster terminal 230, when the poster utters a message, the uttered message is recorded, that is, registered in the post recording device 170 as post voice data through the automatic voice response device 320. Also, in accordance with the posted voice data registration process, the automatic voice response device 320 uses the SNS to record the posted voice data information (poster, posted date, posted voice data identification information, etc.) registered in the posted recording device 170. The server 150 is notified. In response to this notification, the SNS server 150 stores the posted voice data information registered in the posting recording device 170 (poster, posted date and time, identification information of the posted voice data, etc.) in the storage unit.

  Next, the hardware configuration of the system 1002 will be described. As described above, the system 1002 according to the first embodiment includes the SNS server 150, the public Web server 160, and the posting recording device 170. First, the SNS server 150 that is the execution subject of processing in the system 1002 will be described.

  In this case, as illustrated in FIG. 2, the SNS server 150 configuring the system 1002 includes a storage unit 101 configured with an appropriate non-volatile storage device such as a hard disk drive, and a memory 103 configured with a volatile storage device such as RAM. The computer 102, which reads and executes the program 102 held in the storage unit 101, executes the overall control of the apparatus itself and performs various determinations, computations, and control processes, and the LAN unit 121, etc. A communication unit 105 connected and responsible for communication processing with other devices. In the storage unit 101, the program 102 for implementing the functions necessary as the posted audio reproduction control system of the first embodiment, the event identification information, and the selection keyword selected in advance for the corresponding event are associated with each other. The determination table 130 is stored at least.

  Similarly, as illustrated in FIG. 3, the public Web server 160 also includes a storage unit 111 configured with an appropriate non-volatile storage device such as a hard disk drive, a memory 113 configured with a volatile storage device such as RAM, and the storage. An arithmetic unit 114 such as a CPU, an Internet network 120, a LAN line 121, and the like that read and execute a program 112 held in the unit 111 to the memory 113 and execute overall control of the apparatus itself and perform various determinations, calculations, and control processes A communication unit 115 connected and responsible for communication processing with other devices. In the storage unit 111, a program 112 for implementing necessary functions in cooperation with the SNS server 150 as the posted audio reproduction control system of the first embodiment, and various Web page data 116 of the audio SNS site. Is at least remembered.

  Similarly, as illustrated in FIG. 4, the posting recording device 170 also includes a storage unit 11 configured with an appropriate non-volatile storage device such as a hard disk drive, a memory 13 configured with a volatile storage device such as RAM, and the storage. The program 12 held in the unit 11 is executed by reading the program 12 into the memory 13 to perform overall control of the device itself and perform various determinations, computations, and control processes, and the arithmetic unit 14 such as a CPU and the LAN 121 to connect with other devices. The communication part 15 which bears a communication process is provided. In the storage unit 11, the program 12 for implementing necessary functions in cooperation with the SNS server 150 as the posted audio reproduction control system of the first embodiment, and each user terminal 200 (the poster terminal 220). , 230) is at least stored. In the posted audio data 16, a file of each posted audio data (file name also serves as identification information) and data such as a contributor of the corresponding posted audio, a posting date and a publication destination, and the like are stored in association with each other (FIG. 4). ).

  Next, functions provided in the system 1002 of the first embodiment will be described. As described above, the system 1002 according to the first embodiment includes the SNS server 150, the public Web server 160, and the posting recording device 170. However, for the sake of simplification of explanation, the SNS server 150 is described below. The description will be made on the assumption that the functions of the public Web server 160 and the post recording device 170 are provided and the functions as the integrated system 1002 are achieved. In such a system 1002, data exchange with the user terminal 200 is executed via the public Web server 160, and post audio data management is executed via the post recording device 170.

  In this case, the system 1002 receives, via the communication unit 105, the post audio data received from the user terminal 200 and stored in the post recording device 170, to which the same post release destination designation information is assigned. The posting recording device 170 is accessed and specified, voice recognition processing is performed on each of the specified posted voice data to generate text data, and the generated text data is stored in the storage unit 101 for each posting publication destination. It has a function.

  Further, the system 1002 collates each text data having the same posting publication destination obtained above with each selection keyword of the determination table 130, and the text data including the common selection keyword is converted into the same posting publication destination and the same event. As a group to be simultaneously reproduced, and stored in the storage unit.

  Further, the system 1002 searches for the start time or the end time of the audio signal having the predetermined attribute (selected keyword) in the posted audio data included in the group to be synchronously reproduced, and an unnecessary section from the beginning of the data to the start time, In addition, it has a function of deleting an audio signal in an unnecessary section from the end point to the end of the data, and transmitting data obtained by simultaneously reproducing each posted audio data after execution of the deletion to the user terminal 200.

  In addition, the system 1002 may transmit, to the user terminal 200, data obtained by simultaneously reproducing each posted audio data after the above-described deletion execution from the top of the data. Alternatively, the system 1002 may transmit, to the user terminal 200, data that has been reproduced with the end of the data aligned so that the post-deletion post-deletion data ends at the same time.

  Further, the system 1002 calculates the average value of the reproduction time lengths between the respective posted audio data after execution of the deletion described above, and among the posted audio data, those whose reproduction time length is less than the average value are slower than the reference speed. If the playback time length exceeds the average value of each posted audio data, playback is performed at a speed higher than the reference speed, and a process for unifying the playback time length of each posted audio data is executed. Data obtained by simultaneously reproducing the posted audio data may be transmitted to the user terminal 200.

--- Example of data structure in the first embodiment ---
Next, an example of a data structure in a table used by the system 1002 of the first embodiment will be described. FIG. 5 is a diagram illustrating an example of the determination table 130 according to the first embodiment. The determination table 130 includes “congratulations congratulations”, “congratulations congratulations”, and “happy weddings” selected in advance with respect to the corresponding events using identification information of various events such as “marriage”, “birthday”, and “pass” as keys. It is an aggregate of records in which the selected keywords are associated with each other.

--- Example of processing procedure in the first embodiment ---
Hereinafter, the actual procedure of the posted audio reproduction control method in the first embodiment will be described with reference to the drawings. Various operations corresponding to the posted audio reproduction control method described below are realized by programs that are read into the memory and executed by each device constituting the system 1002. And this program is comprised from the code | cord | chord for performing the various operation | movement demonstrated below.

  FIG. 6 is a flowchart showing a processing procedure example of the posted audio reproduction control method according to the first embodiment. Here, the SNS server 150 receives, through the communication unit 105, the post audio data received from the user terminal 200 and stored in the post recording device 170, to which the same post release destination designation information is assigned. The post recording device 170 is accessed and specified (s100).

  Next, the SNS server 150 calls and executes the speech recognition program included in the program 102 for each of the posted speech data specified above, executes speech recognition processing (s101), generates text data, and generates The text data is stored in the storage unit 101 for each posting publication destination (s102).

  Here, the SNS server 150 collates the text data generated by the voice recognition processing with each selection keyword in the determination table 130, and the text data including the common selection keyword is related to the same posting publication destination and the same event. It identifies as a thing and memorize | stores in the memory | storage part 101 as a synthetic | combination reproduction | regeneration object group (s103). The SNS server 150 executes the process in step s103 for all the posted audio data obtained in step s102 (s104). By such processing, for example, it is assumed that posted audio data that has a certain user “U00001” as a disclosure destination and includes a selection keyword “congratulations” in common is specified. In the example of the determination table 130 shown in FIG. 5, the theme of the posted audio data in this case is the event “Marriage Celebration”. FIG. 12 shows an example of processing results in the first embodiment. In this example, “Post 1”, “Post 4”, and “Post 7” are specified as post voice data common to the post release destination “Taro” and the event “Birthday celebration”.

  Subsequently, the SNS server 150 searches for the starting time point or the ending time point of the audio signal having the predetermined attribute (selected keyword) in each posting audio data specified in the above-described step s103 and sharing the posting destination and the event (s105). ). In the above example, the SNS server 150 specifies the utterance start time or the utterance end time of the selected keyword “Congratulations” for each post voice data by the voice analysis processing. This voice analysis process is executed by executing a voice analysis program provided in the program 102 provided in the SNS server 150. An existing voice analysis program may be used.

  The SNS server 150 that has identified the utterance start time or utterance end time of the selected keyword of “Kekkon Congratulations” by voice analysis processing, from the beginning of the data in the corresponding posted voice data to the above-mentioned utterance start time, as illustrated in FIG. Of the unnecessary section Δt1 or the unnecessary section Δt2 from the end time of the utterance to the end of the data in the posted voice data is deleted (s106). The SNS server 150 executes the process of step s106 for all the posted audio data searched for the start time or end time in step s105 (s107).

  Next, after executing the unnecessary section deletion in step s106 described above, the SNS server 150 synthesizes each posted audio data by superimposing them from the top of the data to form one file (s108), and reproducing the file. Data is transmitted to the user terminal 200 (s109). As described above, each posted audio data is superimposed from the top of the data to be combined into one file, and by playing the file, each posted audio data is reproduced simultaneously. FIG. 8 shows an example 1 of a composite reproduction file according to the first embodiment. As shown in FIG. 8, the file obtained by synthesizing in the above step s108, that is, the synthetic reproduction file, is a file in which the contribution audio data of each contributor is multiplexed with the "Congratulations" section at the beginning. It has become.

  In addition, after execution of unnecessary section deletion, the SNS server 150 synthesizes each posted audio data by superimposing the data at the end so that the reproduction ends at the same time in the above-described step s108 to form one file. In s109, reproduction data obtained by reproducing the file may be transmitted to the user terminal 200. FIG. 9 shows a second example of the composite reproduction file of the first embodiment. As shown in FIG. 9, the synthetic reproduction file in this case is a file in which the contribution audio data of each contributor is multiplexed with the “Congratulations” part aligned at the rear end.

  In the above-described example, the post audio data is deleted as an unnecessary section from the beginning of the data to the start time of the utterance of the selected keyword or from the end time of the utterance of the selected keyword to the end of the data. As shown in FIG. 10, an unnecessary section Δt3 from the time when the utterance of the first selected keyword is ended to the time when the utterance of the second selected keyword is started may be assumed. In this case, for example, the SNS server 150 deletes the audio signals of the unnecessary section Δt1 from the data head to the above-described utterance start time and the unnecessary section Δt3 in each posted audio data to be processed, Each posted audio data after the deletion of Δt1 and Δt3 is combined from the top of the data to be combined into one file (FIG. 11). Alternatively, for example, the SNS server 150 deletes the unnecessary section Δt2 from the end time of the utterance to the end of the data and the unnecessary section Δt3 in the post data to be processed, and deletes the unnecessary section Δt2. , Δt3 may be combined into a single file by superimposing the post audio data after execution of deletion of Δt3 so that the end of the data is aligned.

  If the playback time length of the posted audio data obtained by deleting the unnecessary section in step s106 is greatly different between the posted audio data, the above-described synthetic playback file is generated. Even if it is played back, the user who listens to it may hear a message whose content is different from the timing of the utterance.

  Therefore, the SNS server 150 calculates the average value of the reproduction time lengths between the respective posted audio data after executing the unnecessary section deletion when superimposing the posted voice data after executing the unnecessary section deletion in the above-described step s108. (S108A) Among the posted audio data, those whose playback time length is less than the average value are playback speeds lower than the reference speed, and among each posted audio data, those whose playback time length exceeds the average value are faster than the reference speed. A process for setting the playback speed and unifying the playback time length of each posted audio data is executed (s108B). The SNS server 150 synthesizes each post audio data after the processing into one file.

  Although the best mode for carrying out the present invention has been specifically described above, the present invention is not limited to this, and various modifications can be made without departing from the scope of the invention.

  According to the present embodiment, it is possible to efficiently select and reproduce similar posted voices in the voice SNS without trouble and to transmit the poster intentions well.

  At least the following will be clarified by the description of the present specification. That is, in the posted sound reproduction control system according to the first embodiment, the calculation unit may transmit data obtained by simultaneously reproducing each posted sound data after the deletion execution from the top of the data to the user terminal. Good.

  Further, in the posted sound reproduction control system according to the first embodiment, the calculation unit transmits data reproduced by aligning the end of the data so that the posted sound data after the deletion is finished at the same time. It may be a thing.

  Further, in the posted audio reproduction control system according to the first embodiment, the calculation unit calculates an average value of reproduction time lengths between the respective post audio data after the execution of the deletion, and reproduces among the posted audio data. If the time length is less than the average value, a playback speed lower than the reference speed is set, and among the posted audio data, if the playback time length exceeds the average value, a playback speed higher than the reference speed is set. Then, a process for unifying the playback time length of each posted audio data may be executed, and data obtained by simultaneously reproducing each posted audio data after the processing may be transmitted to the user terminal.

--- System configuration in the second embodiment ---
Hereinafter, a second embodiment of the present invention will be described in detail with reference to the drawings. The network configuration including the music selection support system 1001 of the second embodiment is the same as the network configuration (FIG. 1) of the first embodiment. Therefore, only the configuration different from that of the first embodiment will be described below. A music selection support system 1001 (hereinafter, system 1001) according to the second embodiment efficiently selects music with respect to a posted voice in a voice SNS (Social Network Service), and thus improves usability in the voice SNS. It is a computer system that aims to.

  Next, the hardware configuration of the system 1001 will be described. A system 1001 according to the second embodiment includes an SNS server 150, a public Web server 160, and a post recording device 170, as in the first embodiment. Here, the SNS server 150 that is the execution subject of processing in the system 1001 will be described.

  In this case, as illustrated in FIG. 13, the SNS server 150 configuring the system 1001 includes a storage unit 101 including an appropriate non-volatile storage device such as a hard disk drive, and a memory 103 including a volatile storage device such as a RAM. The computer 102, which reads and executes the program 102 held in the storage unit 101, executes the overall control of the apparatus itself and performs various determinations, computations, and control processes, and the LAN unit 121, etc. A communication unit 105 connected and responsible for communication processing with other devices. The storage unit 101 stores at least a program 102 for implementing functions necessary for the music selection support system of the second embodiment, an evaluation table 125, a user table 128, and a posted audio data information table 129. Has been. The evaluation table 125 includes a primary evaluation table 126 and a secondary evaluation table 127.

  Next, functions provided in the system 1001 of the second embodiment will be described. As described above, the system 1001 according to the second embodiment includes the SNS server 150, the public Web server 160, and the posting recording device 170. However, for the sake of simplification of description, the SNS server 150 is described below. The description will be made on the assumption that the functions of the public Web server 160 and the post recording device 170 are provided and the functions of the integrated system 1001 are achieved. In such a system 1001, data exchange with the user terminal 200 is executed via the public Web server 160, and post audio data management is executed via the post recording device 170.

  In this case, the system 100 activates a speech recognition program included in the program 102 and executes speech recognition processing on the posted speech data (stored in the posted recording device 170) received from the user terminal 200, and the text It has a function to generate data. Here, it is assumed that the SNS server 150 includes a voice recognition program as part of the program 102 for the voice recognition processing.

  Further, the system 1001 collates the text data generated by the above-described voice recognition processing with each selected keyword group in the evaluation table 125, and specifies a selected keyword group whose degree of matching with the keyword included in the text data is a predetermined value or more. The music data identification information corresponding to the specified selected keyword group is transmitted to the user terminal 200 as recommended music information to be reproduced together with the posted voice data. On the other hand, the user terminal 200 receives the recommended information, displays it on the display, and allows the user to browse. Here, when specifying the selected keyword group, the system 1001 may specify the selected keyword group having the highest degree of matching with the keyword included in the text data.

  When the user accepts the music indicated by the recommended information, the user terminal 200 notifies the SNS server 150 via the public Web server 160. The SNS server 150 reproduces the music data (retained in the posting recording device 170 or its own storage unit 101) that has received the acceptance notification together with the corresponding posted voice data, and the reproduced data is displayed on the public Web server 160. To the user terminal 200. Alternatively, as described above, the system 1001 does not transmit the recommended information to the user terminal 200, but reproduces the music data corresponding to the specified selected keyword group together with the posted audio data, and the reproduced data is reproduced. It may have a function of transmitting to the user terminal 200.

  Further, when the system 1001 collates the above text data with each selected keyword group of the evaluation table 125 and specifies a plurality of selected keyword groups whose degree of matching with the keyword included in the text data is a predetermined value or more, for example, When the one with the highest matching degree coexists, the attribute information about the user of the user terminal 200 is read from the user table 128, the user attribute information is collated with each user attribute of the evaluation table 125, and the user attribute information It has a function of identifying the user attribute having the highest degree of match and transmitting the music data identification information corresponding to the identified user attribute to the user terminal 200 as recommended music information to be reproduced together with the posted audio data. It is good. Of course, also in this case, the system 1001 does not transmit the recommended information to the user terminal 200 as described above, but reproduces the music data corresponding to the specified user attribute together with the posted audio data, and the reproduced data. May be transmitted to the user terminal 200.

  Further, the system 1001 has a function of determining whether or not designation information of a public destination (such as a user or a group) in the social network service is given to the corresponding posted voice data when a plurality of selected keyword groups having the highest matching degree are specified. It is good also as having.

  In this case, when the system 1001 determines that the post publishing destination designation information is attached to the corresponding posted audio data as a result of the determination, the system 1001 determines from the user table 128 regarding the post publishing destination user indicated by the corresponding designation information. The attribute information is read out, the attribute information is compared with each user attribute in the evaluation table 125, the user attribute having the highest degree of matching with the attribute information of the posting destination user is identified, and the music corresponding to the identified user attribute The data identification information may be transmitted to the user terminal 200 as music recommendation information to be reproduced together with the posted audio data. Also in this case, the system 1001 does not transmit the recommended information to the user terminal 200 as described above, but reproduces the music data corresponding to the specified user attribute together with the posted audio data, and the reproduced data is reproduced. It may have a function of transmitting to the user terminal 200.

  On the other hand, as a result of the determination, when it is determined that the post publishing destination designation information is not given to the corresponding posted audio data, the system 1001 reads the attribute information from the user table 128 regarding the posting user of the corresponding posted audio data. The attribute information is collated with each user attribute of the evaluation table 125, the user attribute having the highest degree of matching with the attribute information of the posting user is identified, and the music data identification information corresponding to the identified user attribute is posted. A process of transmitting to the user terminal 200 as recommended information of music to be reproduced together with the audio data may be executed. Also in this case, the system 1001 does not transmit the recommended information to the user terminal 200 as described above, but reproduces the music data corresponding to the specified user attribute together with the posted audio data, and the reproduced data is reproduced. It may have a function of transmitting to the user terminal 200.

  In addition, when the system 1001 collates the above-described text data with each selected keyword group in the evaluation table 125 and specifies a plurality of selected keyword groups that have the highest degree of matching with the keyword included in the text data, the user of the user terminal 200 The latest posted voice data relating to the post-recording device 170 or the storage unit 101 is read out, the corresponding posted voice data is subjected to voice recognition processing similar to the above to generate text data, and the text data is stored in the evaluation table 125. Match each selected keyword group, identify the selected keyword group that has the highest degree of matching with the keyword included in the text data, and play the music data identification information corresponding to the identified selected keyword group together with the posted audio data A function to transmit to the user terminal 200 as recommended music information It may be used as is. Also in this case, the system 1001 does not transmit the recommended information to the user terminal 200 as described above, but reproduces the music data corresponding to the specified selected keyword group together with the posted audio data, and the reproduced data May be transmitted to the user terminal 200.

  In addition, when the system 1001 specifies a plurality of selected keyword groups having the highest degree of matching with the keyword included in the text data, each posted audio data for a period within a predetermined range from the most recent time related to the user of the user terminal 200 is recorded. Read from the device 170 or the storage unit 101, execute the speech recognition process similar to the above on each posted voice data to generate text data, extract keywords with a frequency of appearance above a certain level across each text data, The keyword is collated with each selected keyword group of the evaluation table 125, the selected keyword group having the highest degree of matching with the keyword having a certain appearance frequency or more is specified, and the identification information of the music data corresponding to the specified selected keyword group, It is transmitted to the user terminal 200 as recommended information of music to be reproduced together with the posted audio data. Functions may have. Also in this case, the system 1001 does not transmit the recommended information to the user terminal 200 as described above, but reproduces the music data corresponding to the specified selected keyword group together with the posted audio data, and the reproduced data May be transmitted to the user terminal 200.

--- Example of data structure in the second embodiment ---
Next, an example of a data structure in a table used by the system 1001 according to the second embodiment will be described. FIG. 14 is a diagram illustrating an example of the evaluation table 125 according to the second embodiment. The evaluation table 125 is a table in which identification information of music data is associated with a selection keyword group selected in advance for the corresponding music data. In the second embodiment, the evaluation table 125 includes a primary evaluation table 126 and a secondary evaluation table 127. It is composed. In the example shown in the figure, the primary evaluation table 126 uses “BGM name” as music data identification information as a key, and “musical information”, “basile”, “ha” selected in advance for the corresponding music data, that is, BGM. It is a collection of records in which selected keyword groups such as “ppy” are associated. Further, the secondary evaluation table 127 uses the BGM name as identification information of music data as a key, the user attributes (for example, birthday date, rock music enthusiast, 40s) selected in advance for the corresponding music data, that is, the BGM, and the latest It is a collection of records that associate keywords (eg, marriage, Christmas, etc.) included in writing.

  FIG. 15 is a diagram illustrating an example of the user table 128 according to the second embodiment. The user table 128 is a table in which attribute information of each user of the voice SNS is described. In the example of the figure, the user attribute values such as the birthday, music orientation, hobbies, and age of the corresponding user are associated with the user ID as a key. It is a collection of attached records.

  FIG. 16 is a diagram illustrating an example of the posted audio data information table 129 according to the second embodiment. The posted audio data information table 129 is a table in which information related to posted audio data stored in the posting recording device 170 is stored for each disclosure destination of the corresponding posted audio data. In the example of the figure, a user ID such as “U00001” is stored. Each is a set of records in which values such as a contributor of the corresponding posted audio data, a posting date and time, and a title (identification information) of the posted audio data are associated with the posted audio data ID as a key.

--- Example of processing procedure in the second embodiment ---
Hereinafter, the actual procedure of the music selection support method in the second embodiment will be described with reference to the drawings. Various operations corresponding to the music selection support method described below are realized by programs that are read into the memory and executed by the devices constituting the system 1001. And this program is comprised from the code | cord | chord for performing the various operation | movement demonstrated below.

  FIG. 17 is a flowchart illustrating a processing procedure example of the music selection support method according to the second embodiment. Here, the SNS server 150 acquires the posted voice data received from the user terminal 200 and stored in the posting recording device 170 from the posting recording device 170 (s200).

  Next, the SNS server 150 activates a speech recognition program included in the program 102 for the posted speech data acquired above, executes speech recognition processing, and generates text data (s201). Here, the SNS server 150 collates the text data generated by the speech recognition process with the selected keyword group of each BGM in the primary evaluation table 126, and calculates the degree of match between the keyword included in the text data and each BGM. (S202).

  As described above, the process for calculating the degree of matching between the keyword included in the text data and each BGM is, for example, the following processing procedure. When the keywords included in the text data are “Kekkon”, “Congratulations”, and “Happiness”, the SNS server 150 matches these keywords with the primary evaluation table 126, and for the keyword “Kekkon”, the score at the time of adaptation “10 points” is specified, “6 points” of the score for adaptation is specified for the keyword “congratulations”, and “6 points” of the score for adaptation is specified for the keyword “happy”. The process of specifying the score at the time of matching for each of the keywords “Kekkon”, “Congratulations”, and “happiness” is executed for each BGM record in the primary evaluation table 126 (s203), and the evaluation result example 1 shown in FIG. Thus, the score meter for each BGM is calculated. In the example of FIG. 18, the highest score “19 points” was calculated for “BGM2: wedding song”.

  As described above, only the keyword with the highest degree of matching with the keyword included in the text data, that is, the keyword group with the highest score = BGM is specified by the matching of the keyword of the text data to the primary evaluation table 126 and the score calculation process. If it is found (s204: No), the SNS server 150 designates the identified BGM, that is, the identification information of the music data, as the recommended information of the music to be reproduced together with the posted audio data, as the poster or publication destination of the corresponding posted audio data. It transmits to the user terminal 200 of the other user who is done (s205). The posting destination is specified by the contributor at the time of posting the posted audio data, as well as the poster information of the corresponding posted audio data, and the information of the user or group that became the publishing destination is attached to the corresponding posted audio data. It is assumed that they are stored in the posting recording device 170 and the posted audio data information table 129.

  Note that the user terminal 200 that has received the recommended information described above displays the recommended information on a display and allows the user to browse. When the user accepts the BGM indicated by the recommended information described above, the fact is notified from the user terminal 200 to the SNS server 150 via the public Web server 160.

  The SNS server 150 reproduces the BGM data (held in the posting recording device 170 or its own storage unit 101) that has received the acceptance notification from the user terminal 200 together with the corresponding posted audio data, and discloses the reproduced data. It transmits to the user terminal 200 via the Web server 160 (s212). Note that the SNS server 150 does not transmit the recommended information to the user terminal 200 as described above, but reproduces the BGM data corresponding to the specified selected keyword group together with the posted voice data, and reproduces the data. Data may be transmitted to the user terminal 200.

  On the other hand, when the matching of the keywords of the text data to the primary evaluation table 126 and the score calculation process specify a plurality of keywords having the highest degree of matching with the keywords included in the text data, that is, the highest score keyword group = BGM (s204). : Yes), the SNS server 150 determines whether or not the designated information of the disclosure destination (user, group, etc.) in the voice SNS is given to the corresponding posted voice data (s206).

  In this case, if the SNS server 150 determines that the post publishing destination designation information is added to the corresponding posted audio data as a result of the determination in step s206 described above (s206: Yes), the corresponding designation information indicates “ The attribute information is read from the user table 128 for the user of “post publication destination” (s207). In step s207, the SNS server 150 further reads the latest posted voice data related to the user of “post publication destination” from the posting recording device 170, executes voice recognition processing on the corresponding posted voice data, and performs text data processing. Is generated. When the SNS server 150 reads the latest posted voice data from the posting recording device 170, the SNS server 150 may read the posted voice data in a predetermined range from the latest. In that case, the SNS server 150 generates the text data by executing the same voice recognition processing as described above for each posted voice data in the period of the predetermined range, and selects a keyword having a certain appearance frequency across each text data. Extract.

  On the other hand, as a result of the determination in the above-described step s206, when it is determined that the post publishing destination designation information is not given to the corresponding posted audio data (s206: No), the SNS server 150 displays “post” of the corresponding posted audio data. ”Regarding the user, the attribute information is read from the user table 128 (s208). In step s208, the SNS server 150 further reads the latest posted voice data related to the “post” user from the posting recording device 170, executes voice recognition processing on the corresponding posted voice data, and generates text data. . When the SNS server 150 reads the latest posted voice data from the posting recording device 170, the SNS server 150 may read the posted voice data in a predetermined range from the latest. In that case, the SNS server 150 generates the text data by executing the same voice recognition processing as described above for each posted voice data in the period of the predetermined range, and selects a keyword having a certain appearance frequency across each text data. Extract.

  Subsequently, the SNS server 150 collates the user attribute information obtained in any of the above-described steps s207 and s208 and the keyword obtained from the latest writing with the secondary evaluation table 127, and the user defined for each BGM. The degree of matching with the attribute information and the keyword is calculated (s209).

  As described above, the process for calculating the match between the user attribute information and the keyword and each BGM is, for example, the following processing procedure. When the attribute information of the user is “age: 40”, “music-oriented: rock”, and the keywords are “futsal” and “good luck”, the SNS server 150 uses these values as the secondary evaluation table 127. For each value of “Age: 40” and “Music Orientation: Rock”, specify “10 points” at the time of adaptation, and for each keyword of “Futsal” and “Good luck” at the time of adaptation Specify no score. The process of specifying the matching score regarding the user attribute information and the keyword is executed for each BGM record in the secondary evaluation table 127 (s210), and the evaluation result example 2 shown in FIG. Calculate the score meter.

  In the example of FIG. 19, the evaluation using the secondary evaluation table 127 among “BGM4”, “BGM5”, and “BGM6” that has the highest score in the evaluation using the primary evaluation table 126 is changed to “BGM6”. A total of 20 points were calculated. In this way, by matching the user attribute information and keywords to the secondary evaluation table 127 and processing for score calculation, the BGM having the highest degree of match with the user attribute information and keywords, that is, the highest score BGM is specified.

  Subsequently, as in step s205 described above, the SNS server 150 uses the BGM identified in step s209, that is, music data identification information, as the recommended music information to be reproduced together with the posted audio data, It transmits to the user terminal 200 of a contributor (s211). Note that the user terminal 200 that has received the recommended information described above displays the recommended information on a display and allows the user to browse. When the user accepts the BGM indicated by the recommended information described above, the fact is notified from the user terminal 200 to the SNS server 150 via the public Web server 160.

  The SNS server 150 reproduces the BGM data (held in the posting recording device 170 or its own storage unit 101) that has received the acceptance notification from the user terminal 200 together with the corresponding posted audio data, and discloses the reproduced data. It transmits to the user terminal 200 via the Web server 160 (s212).

  According to such 2nd Embodiment, it becomes possible to select music efficiently with respect to the contribution sound | voice by audio | voice SNS, and, by extension, the usability improvement by audio | voice SNS can be aimed at.

--- System configuration in the third embodiment ---
Hereinafter, a third embodiment of the present invention will be described in detail with reference to the drawings. The network configuration including the posted audio reproduction control system 1003 of the third embodiment is the same as the network configuration (FIG. 1) of the first and second embodiments. Therefore, only the configuration different from that of the first embodiment will be described below. A posted voice reproduction control system 1003 (hereinafter, system 1003) in the third embodiment is a computer system that continuously reproduces a plurality of posted voices in the voice SNS without a sense of incongruity and enables good transmission of a poster's intention.

  Next, the hardware configuration of the system 1003 will be described. A system 1003 according to the third embodiment includes an SNS server 150, a public Web server 160, and a posting recording device 170, as in the first embodiment. Here, the SNS server 150 that is the execution subject of processing in the system 1003 will be described.

  In this case, as illustrated in FIG. 20, the SNS server 150 configuring the system 1003 includes a storage unit 101 including an appropriate non-volatile storage device such as a hard disk drive, and a memory 103 including a volatile storage device such as a RAM. The computer 102, which reads and executes the program 102 held in the storage unit 101, executes the overall control of the apparatus itself and performs various determinations, computations, and control processes, and the LAN unit 121, etc. A communication unit 105 connected and responsible for communication processing with other devices. The storage unit 101 stores at least a program 102, a grouping table 131, a priority evaluation table 132, and a user table 133 for implementing functions necessary for the posted audio reproduction control system of the third embodiment. ing. Details of these tables will be described later.

  Although not particularly illustrated, the posted audio data 16 stored in the storage unit 11 by the posting recording device 170 is associated with the identification information data of BGM to be reproduced together with the corresponding posted audio data.

  Next, functions provided in the system 1003 of the third embodiment will be described. As described above, the system 1003 according to the third embodiment is configured by the SNS server 150, the public Web server 160, and the posting recording device 170. However, for the sake of simplification of description, the SNS server 150 is described below. The description will be made on the assumption that the functions of the public Web server 160 and the post recording device 170 are provided and the functions of the integrated system 1003 are achieved. In such a system 1003, data exchange with the user terminal 200 is executed via the public Web server 160, and post audio data management is executed via the post recording device 170.

  In this case, the system 1003 has the same post release destination designation information (for example, identification information of the user or group as the release destination) in the post voice data obtained and stored by the post recording device 170 from the user terminal 200. What is given is accessed and specified via the communication unit 105 from the posting recording device 170, and if the music to be played back simultaneously is given to the corresponding posted voice data, the given posted voice data is given Identification information of music that should be played back simultaneously with the corresponding posted voice data, and if the music to be played back simultaneously is not given to the posted voice data, voice recognition is performed for each of the specified posted voice data The process is executed to generate text data, and the generated text data is collated with the grouping table 131 to obtain the theme ( : Birthday, identifies the wedding, etc.), and has a function of storing in the storage unit 101 posts the audio data et al themes the identified common with each other as a group to be continuously played back.

  In addition, the system 1003 has a function of sequentially reproducing each posted audio data included in the group to be continuously reproduced and transmitting the reproduced data to the user terminal 200.

  Note that the system 1003 reads attribute information (for example, birthday, music orientation, hobbies, age, etc.) related to the posting disclosure destination user in the group to be continuously reproduced from the user table 133, and evaluates the attribute information of this user on the priority evaluation. The reproduction priority level of the group corresponding to the attribute information of the user is identified with reference to the table 132, the reproduction order between the groups is determined according to the level of the reproduction priority level, and the group subject to continuous reproduction in the reproduction order May be provided from the storage unit 101, the posted audio data included in the group may be sequentially reproduced, and the reproduced data may be transmitted to the user terminal 200.

  In addition, the system 1003 displays the latest posted audio data 16 related to the user of the posting disclosure destination in the group to be continuously played back to the posting recording device 170 (or the storage unit 101 that has copied the posted audio data 16 from the posting recording device 170). Read out, execute speech recognition processing on the corresponding posted voice data to generate text data, collate the text data with the priority evaluation table 132, and set the playback priority level of the group according to the user's posted content. The playback order between the groups is determined in accordance with the level of the playback priority level, the group to be continuously played back is read from the storage unit 101 in the playback order, and each posted audio data included in the group is played back sequentially. A function of transmitting the reproduced data to the user terminal 200 may be provided.

  In addition, when the system 1003 receives a reproduction stop instruction from the user terminal 200 that has received the corresponding reproduction data via the communication unit 105 during the reproduction of the posted audio data, the system 1003 receives the group theme of the corresponding continuous reproduction target. With regard to the above, a function may be provided in which the storage unit 101 sets a flag for designating the exclusion of a reproduction target for a certain period. In this case, when the system 1003 sequentially plays back each posted audio data included in the group to be continuously played back, the system 1003 does not play back the group to be played back continuously corresponding to the theme for which the above flag is set. Priority is given to the playback of groups that are subject to continuous playback.

--- Example of data structure in the third embodiment ---
Next, an example of a data structure in a table used by the system 1003 of the third embodiment will be described. FIG. 21 is a diagram illustrating an example of the grouping table 131 according to the third embodiment. The grouping table 131 includes BGM names such as “birthday song” and “wedding song”, that is, text keywords generated by voice recognition using the identification information of music data as keys, “celebration”, “genki”, and the like. It is a collection of records in which the theme of the corresponding music or posted audio and the tone (musical tone) such as “fun” and “bright” are associated with each other.

  FIG. 22 is a diagram illustrating an example of the priority evaluation table 132 according to the third embodiment. In addition, the priority evaluation table 132 includes a collection of records in which user attribute information (eg, birthday, etc.) or post content (eg, marriage, match, etc.) is associated with a playback priority level to be continuously played back. It has become. In the example of the priority evaluation table 132 in FIG. 22, the attribute information (eg, birthday) of the user who is the disclosure destination of the group to be continuously played or the latest posted content (eg, marriage, match, etc.) This table defines a predetermined evaluation score value to be given to the group to be subjected to continuous reproduction when the user attribute or the post content item value in the degree evaluation table 132 is matched.

  FIG. 23 is a diagram illustrating an example of the user table 133 according to the third embodiment. Further, the user table 133 is a table describing attribute information of each user of the voice SNS. In the example of the figure, user attribute values such as the birthday, music orientation, hobbies, and age of the corresponding user using the user ID as a key. It is a collection of records that correspond to each other.

--- Example of processing procedure in the third embodiment ---
The actual procedure of the posted audio reproduction control method in the third embodiment will be described below with reference to the drawings. Various operations corresponding to the posted audio reproduction control method described below are realized by programs that are read out from a memory or the like and executed by each device constituting the system 1003. And this program is comprised from the code | cord | chord for performing the various operation | movement demonstrated below.

  FIG. 24 is a flowchart showing a processing procedure example of the posted audio reproduction control method according to the third embodiment. Here, the SNS server 150 specifies the same posting publication destination designation information (for example, identification information of a user or a group serving as a publication destination) in the posted voice data 16 obtained and stored by the posting recording device 170 from the user terminal 200. ) Is specified from the posting recording device 170 via the communication unit 105 (s300).

  In addition, the SNS server 150 determines whether or not music to be simultaneously reproduced is added to the posted audio data specified in step s300 described above (s301). The identification information of the music to be reproduced simultaneously with the corresponding posted audio data, which is given to the data, is collated with the grouping table 131, and the music theme to be reproduced simultaneously with each posted audio data (eg birthday celebration, wedding celebration) Etc.) and a tone are specified (s302). In this case, the SNS server 150 reads the BGM identification information such as “birthday song” given to the corresponding posted audio data 16 in the posting recording device 170 and collates the BGM identification information with the grouping table 131. The music theme to be played simultaneously with the corresponding posted audio data is specified as “celebration”, the tone as “fun / bright”, and the like. Note that the identification information of the music to be played back simultaneously with the corresponding posted voice data, which is given to each posted voice data, is specified by the music selection support system 1001 in the second embodiment to be described later, and is posted by the posting recording device 170. Assume that it is given to the posted audio data.

  If the music to be played back simultaneously is not given to the posted audio data specified in step s300 described above, a speech recognition process is performed on each of the specified posted audio data to generate text data, The generated text data is collated with the grouping table 131, and the theme (for example, birthday celebration, wedding celebration, etc.) of each posted audio data is specified (s303).

  Subsequently, the SNS server 150 stores, in the storage unit 101, the theme specified in the above-described step s302 or s303, preferably the posted audio data having the same tone, as a group to be continuously reproduced (s304). The grouping process of the posted voice data in the SNS server 150 is repeatedly executed until the process is completed for all the posted voice data specified in step s300 described above (s305). In the example of the evaluation result shown in FIG. 25, seven posts from “Post 1” to “Post 7” are specified as post voice data of the same publication destination, and the identification information of the BGM linked to each post is shown. “BGM1: Birthday Song”, “BGM2: Support Song”, “BGM3: Graduation Song”, “BGM4: Birthday Song”, “BGM5: Graduation Song”, “BGM6: Valentine Song”, “BGM7: No BGM” The groups based on these themes are “Post 1: Celebration”, “Post 2: Energetic”, “Post 3: Farewell”, “Post 4: Celebration”, “Post 5: Farewell” , “Post 6: Congratulatory”, “Post 7: Congratulatory”.

  Next, the SNS server 150 reads attribute information (eg, birthday, music orientation, hobbies, age, etc.) regarding the posting disclosure destination user in the group to be continuously reproduced from the user table 133 (s306). In addition, the SNS server 150 obtains the latest posted audio data 16 (may be a plurality of items retroactive for a certain period from the latest) from the posting recording device 170 (or the posting recording device 170). The storage unit 101) that has copied the posted voice data 16 in advance is read out, the voice recognition program included in the program 102 is activated for the corresponding posted voice data, voice recognition processing is executed, and text data is generated (s307). Here, it is assumed that the SNS server 150 includes a voice recognition program as part of the program 102 for the voice recognition processing.

  The SNS server 150 collates the user attribute information and text data (that is, the latest post content) obtained in the above steps s306 and s307 with the priority evaluation table 132, and the user attribute information and the latest post According to the content, the playback priority level of the corresponding group is specified (s308).

  In the case of the evaluation result example shown in FIG. 25, the attribute information of the posting release destination user is “birthday: February”, and the latest posted content by the user is “birth tomorrow after a soccer game, "It was a party!", "Valentine on the weekend", "Graduated next month. Therefore, among the posts from “Post 1” to “Post 7”, “Post 1” has a post content of “Happy Birthday for 7 years old”. ”And add these 10 points to the“ festive ”group. For “Post 2”, the content of the post is “Let's do our best tomorrow's game”, so “10 points” are acquired for the keyword “Game”, and these 10 points are added to the “Genki” of the corresponding group. To do. In addition, as for “Post 3”, the content of the post is “Soon graduation ceremony, high school is separate and lonely”, so we get “10” for the keyword “Graduation” and “Farewell” of the corresponding group Add these 10 points to. Also, for “Post 4”, the content of the post is “Happy Birthday. Already 7 years old. You ’ve grown up”, so earned “10 points” for the keyword “Birthday” and made it a “Celebration” for that group. Add these 10 points. Also, for “Post 5”, the content of the post is “Let's play together even after graduation”, so “10 graduation” is obtained for the keyword “Graduation”, and it becomes “Farewell” of the corresponding group. Add these 10 points. Also, for “Post 6”, the content of the post is “It seems to be busy with Valentine's day chocolate making”, so “10 points” are obtained for the keyword “Valentine”, and this 10 points are given to the “festive group” of the corresponding group. to add. Also, for “Post 7”, the content of the post is “Today ’s birthday party was fun to be celebrated by everyone”, so “10 points” were obtained for the keyword “Birthday” and These 10 points are added to the “celebration”.

  The score of each group is 40 points in total for 10 points from “Post 1”, “Post 4”, “Post 6”, “Post 7”, and 10 points from “Post 2”. The total was 10 points, and the farewell system obtained 10 points from “Post 3” and “Post 5” was 20 points in total. Accordingly, the SNS server 150 determines that the higher the total score of each group obtained in this way is, the higher the playback priority level is. Accordingly, the playback order between the groups is set as the playback order first: festive system, playback order. 2nd place: Farewell system, reproduction order 3rd place: Energetic system is determined (s309).

  Subsequently, the SNS server 150 reads the corresponding continuous playback target group from the posting recording device 170 (or the storage unit 101 that has copied the posted audio data from the posting recording device 170) in the playback order determined in step s309 described above, Each posted audio data included in the group is sequentially reproduced, and the reproduced data is transmitted to the user terminal 200 (s310).

  Note that the SNS server 150 receives a playback stop instruction from the user terminal 200 that has received the corresponding playback data via the communication unit 105 during playback of the posted audio data in step s310 (s311: Yes). For the theme of the group to be continuously reproduced, the storage unit 101 may set a flag for designating the exclusion of the reproduction object for a certain period (s312). When the SNS server 150 after the processing of step s312 later executes step s310 again, the SNS server 150 is within the effective period indicated by the corresponding flag for the group to be continuously played back corresponding to the theme for which the flag is set. Does not reproduce, but prioritizes the reproduction from the group with the highest reproduction order among the other groups subject to continuous reproduction. If such processing is performed, the playback order determined on the system 1003 side is based on the fact that the user did not like it, and it is possible to continuously play back the posted audio data more in line with the user's intention and mood. It becomes possible.

  The SNS server 150 may store the flag setting history in the storage unit 101 in association with the corresponding group for each user who has given a playback stop instruction that is the origin of the flag. In this case, the SNS server 150 calculates the flag setting frequency in each group for each user for a certain period, and when the flag setting frequency is highest among the groups, the flag is set again thereafter. Performs a process of extending the effective period of the flag, that is, the period of exclusion of the reproduction target by a certain period from the normal period. By performing such processing, it is possible to continuously reproduce the posted audio data more in line with the user's intention and mood, more reliably based on the fact that the user did not like.

  Although the best mode for carrying out the present invention has been specifically described above, the present invention is not limited to this, and various modifications can be made without departing from the scope of the invention.

  According to the third embodiment, a plurality of posted voices in the voice SNS can be continuously reproduced without a sense of incongruity, and a good transmission of the poster intention can be achieved.

  At least the following will be clarified by the description of the present specification. That is, in the posted audio reproduction control system according to the third embodiment, the storage unit includes a user table describing attribute information of each user of the social network service, user attribute information, and a reproduction priority level to be continuously reproduced. An associated priority evaluation table, wherein the calculation unit reads attribute information related to a posting release destination user in the group to be continuously reproduced from the user table, and the attribute information of the user is read from the priority evaluation table. The playback priority level of the group according to the attribute information of the user is determined, the playback order between the groups is determined according to the level of the playback priority level, and the continuous playback target in the playback order is determined. Read the group from the storage unit, play each post audio data included in the group sequentially, Data is the one that transmits to the user terminal may be.

  In the posted audio playback control system according to the third embodiment, the storage unit stores posted audio data received from each user terminal, and describes attribute information of each user of the social network service. A user table, and a priority evaluation table that associates the user's posted content with the playback priority level of the continuous playback target, and the calculation unit includes the latest user related post posting destination in the group of the continuous playback target Read the posted voice data from the storage unit, execute voice recognition processing on the corresponding posted voice data to generate text data, check the text data against the priority evaluation table, and according to the user's posted content The playback priority level of the group is specified, and the playback order between groups is determined according to the level of the playback priority level. The continuous playback target group is read from the storage unit in the playback order, each posted audio data included in the group is sequentially played back, and the played back data is transmitted to the user terminal. Good.

1001 Music selection support system (second embodiment)
1002 Posted audio playback control system (first embodiment)
1003 Posted audio playback control system (third embodiment)
11, 101, 111 Storage unit 12, 102, 112 Program 13, 103, 113 Memory 14, 104, 114 Calculation unit 15, 105, 115 Communication unit 16 Posted audio data 120 Internet network (network)
121 LAN line (network)
122 Public network (network)
125 Evaluation table 126 Primary evaluation table 127 Secondary evaluation table 128 User table 129 Posted audio data information table 130 Determination table 131 Grouping table 132 Priority evaluation table 133 User table 150 SNS server 160 Public Web server 170 Post recording device 200 User terminal 220 , 230 Contributor terminal (user terminal)
240 Browsing player terminal (user terminal)
300 Telephone response system 310 Exchange 320 Automatic voice response device 330 CTI device

Claims (6)

A communication unit that communicates with a user terminal used by a user of a social network service via a network;
A storage unit for storing a determination table in which identification information of an event and a selection keyword selected in advance for the event are associated;
Among the posted voice data received from the user terminal via the communication unit, the one to which the specified posting publication destination designation information is assigned is specified, and the voice recognition processing is performed on each of the specified posted voice data to obtain the text Processing to generate data and store the generated text data in the storage unit for each posting publication destination;
Collate each text data with a common posting publication destination against each selection keyword in the judgment table, specify the text data containing the same selection keyword as related to the same posting publication destination and the same event, Processing to store in the storage unit as
Search the start time or end time of the audio signal of the same selected keyword in the posted audio data included in the group to be simultaneously played, and search the unnecessary section from the start of the data to the start time, or the end of the data from the end The processing unit that deletes the audio signal of the unnecessary section up to and transmits the data that can be output by the audio output means to the user terminal when the posted audio data after the deletion is simultaneously reproduced When,
A posted voice reproduction control system comprising: The said calculating part transmits the data which can be output by an audio | voice output means to the said user terminal at the time of reproducing simultaneously each contribution audio | voice data after the said deletion execution from the data head. 2. The posted audio reproduction control system according to 1. The calculation unit is configured to transmit, to the user terminal, data that can be output by the audio output unit when the post-deletion-executed post-voice data is reproduced with the end of the data aligned so as to end simultaneously. The posted voice reproduction control system according to claim 1, wherein The calculation unit calculates an average value of playback time lengths between the respective posted audio data after execution of the deletion, and those of the posted audio data whose playback time length is less than the average value are slower than a reference speed If the playback time length of each posted audio data exceeds the average value, the playback speed higher than the reference speed is set, and the process of unifying the playback time length of each posted audio data is executed. 2. The posted voice reproduction control according to claim 1, wherein data that can be output by the voice output means when the post-voice data after the processing is simultaneously reproduced is transmitted to the user terminal. system. A communication unit that communicates via a network with a user terminal used by a user of a social network service, and a storage unit that stores a determination table in which event identification information and a selection keyword selected in advance for the event are associated with each other Computer
Among the posted voice data received from the user terminal via the communication unit, the one to which the specified posting publication destination designation information is assigned is specified, and the voice recognition processing is performed on each of the specified posted voice data to obtain the text Processing to generate data and store the generated text data in the storage unit for each posting publication destination;
Collate each text data with a common posting publication destination against each selection keyword in the judgment table, specify the text data containing the same selection keyword as related to the same posting publication destination and the same event, Processing to store in the storage unit as
The start time or end time of the audio signal of the same selected keyword included in the group to be simultaneously played is searched, and an unnecessary section from the beginning of the data to the start time, or an unnecessary section from the end time to the end of the data. Deleting the audio signal, and transmitting to the user terminal data that can be output by the audio output means when simultaneously reproducing each posted audio data after execution of the deletion,
A method for controlling the reproduction of posted audio, comprising: A communication unit that communicates via a network with a user terminal used by a user of a social network service, and a storage unit that stores a determination table in which event identification information and a selection keyword selected in advance for the event are associated with each other Computer
Among the posted voice data received from the user terminal via the communication unit, the one to which the specified posting publication destination designation information is assigned is specified, and the voice recognition processing is performed on each of the specified posted voice data to obtain the text Processing to generate data and store the generated text data in the storage unit for each posting publication destination;
Collate each text data with a common posting publication destination against each selection keyword in the judgment table, specify the text data containing the same selection keyword as related to the same posting publication destination and the same event, Processing to store in the storage unit as
The start time or end time of the audio signal of the same selected keyword included in the group to be simultaneously played is searched, and an unnecessary section from the beginning of the data to the start time, or an unnecessary section from the end time to the end of the data. Deleting the audio signal, and transmitting to the user terminal data that can be output by the audio output means when simultaneously reproducing each posted audio data after execution of the deletion,
A post voice reproduction control program characterized by causing

Images