JP2013118488A - Audio data utilization system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an audio data utilization system in which conversations or the like of each user are recorded and accumulated at all the time and, based on the accumulated audio data, information processing including communications with other users is performed.SOLUTION: An audio data utilization system 1 comprises a recorder 20 which records voices at all the time as digital data while separating the voices for the unit of a predetermined length, and an audio data accumulation server 10 which accumulates audio data transmitted from the recorder 20 into an audio data DB 16 for each user. The recorder 20 transmits audio data to the audio data accumulation server 10 as occasion demands, and the audio data accumulation server 10 converts the audio data accumulated in the audio data DB 16 into text data and acquires dictated audio data. According to contents of conversations in the dictated audio data of a first user, contents of audio data of the first user and/or of dictated audio data of the first user within a predetermined range can be shared with another second user.

Description

  The present invention relates to a technique for using voice data using an information processing apparatus, and more particularly to a technique effective when applied to a voice data using system that uses voice data accumulated by continuous recording.

  In recent years, like a so-called life log, for example, personal action contents are recorded and accumulated as digital data over a long period of time, and past actions are confirmed in a diary by searching for it later. And mechanisms and services have been provided that enable analysis and analysis to investigate behavioral trends.

  In general, the action log recording method includes manual recording, which records information that the user wants to actively and actively record, and automatic recording device regardless of the user's intention. There is automatic recording that records action contents. The manual recording method can reflect the user's subjectivity in the recorded content, but there is a problem that the load on the user such as an operation for recording becomes high. On the other hand, in the automatic recording method, only objective data can be recorded, but the user can normally always record data related to action contents with a small load.

  As data of action contents to be recorded, there is audio data including user conversations and the like that can be recorded relatively easily even in the case of manual recording. In recent years, many individuals often carry portable devices capable of recording voice as digital data, such as mobile phones, so-called smartphones, IC recorders, and the recording environment can be easily realized. In addition, such a recording device does not require any user operation during recording (automatic recording is possible), and unlike a video camera or the like, has little directivity, so that it can record a wide range of sounds around the user. (In the case of video, only a certain range of video in the direction in which the video camera is facing can be recorded).

  As a mechanism for using the recorded voice data, there is mainly a mechanism for analyzing the voice data using a voice recognition technique or the like and using it as text data. For example, in Japanese Patent Application Laid-Open No. 2009-170953 (Patent Document 1), a call center device analyzes recorded data obtained by recording the contents of a call and determines that the recorded data contains a specific word. A call recording device that transmits the recorded data and an administrator terminal that receives and reproduces the recorded data from the call recording device. When a trouble or communication failure occurs with a customer, the administrator Describes a technology that can verify the contents of a call without burdening the user.

  Further, for example, in Japanese Patent Laid-Open No. 7-177237 (Patent Document 2), an electronic trunk is connected to an incoming trunk, a speech path switch, a voice mail device, a voice recognition device, an incoming call register, and a computer. A computer which has a central processing unit and a text data storage device, and can analyze the contents of voice mail even by a hearing-impaired person by analyzing voice mail by voice recognition and converting it into text data The technology of the linked voice mail system is described.

JP 2009-170953 A JP-A-7-177237

  As described above, by recording and accumulating audio data, it can be used as audio data, but it can also be converted into text data and analyzed to perform information processing and information transmission according to the content of the conversation. The usage form is possible. However, in these usage methods, it is premised that only a conversation or the like necessary for processing is designated and recorded manually (or automatically).

  In this regard, in recent years, the capacity and price of storage media and storage devices represented by hard disks and the like have greatly increased, and it is relatively easy to configure a large-capacity recording device. For example, when conversational voice is stored at a low bit rate of about 9.6 kbps and used as voice data, even if recording is continued for 24 hours 365 days for 100 years, the amount of data is about 3.8 TB, which is currently about this level. It is possible to purchase a hard disk device with a capacity of about 10,000 yen. In other words, it is also possible to continuously record a person's lifetime conversation from the viewpoint of the capacity of the recording device.

  Such low-priced, large-capacity storage devices are already used effectively in devices such as security cameras, voice recorders, and drive recorders, for example, and always record (automatically) audio and video regardless of content. Is also possible. However, these devices are mainly intended for direct use of the data itself for subsequent verification / confirmation purposes, evidence, etc., and it is assumed that some information processing is performed based on the contents of the data. Not.

  In particular, considering the construction of an environment where each individual unit can continuously record and store conversations for about a lifetime, there is a new situation among multiple users using these audio data. It is also possible to realize communication methods such as information sharing and transmission. In addition, since recording can be performed at any time without worrying about storage capacity, for example, it is easy to store audio data without the need for cumbersome processing such as selecting and specifying only the conversation to be processed. Can be performed.

  SUMMARY OF THE INVENTION Accordingly, an object of the present invention is to provide a voice data utilization system that records and accumulates each user's conversations 24 hours a day, 365 days a day, and performs information processing including communication with other users based on the accumulated voice data. There is to do. The above and other objects and novel features of the present invention will be apparent from the description of this specification and the accompanying drawings.

  Of the inventions disclosed in this application, the outline of typical ones will be briefly described as follows.

  A voice data utilization system according to a typical embodiment of the present invention is held by a plurality of users, and the voices around the users are always recorded as digital data, and the recorded voice data is divided into predetermined lengths. An audio data utilization system comprising a recording device for recording and an audio data storage server for storing the audio data transmitted from the recording device in an audio data recording unit for each user, and has the following characteristics: .

  That is, the recording device transmits the voice data to the voice data storage server as needed, and the voice data storage server converts the voice data stored in the voice data recording unit into text data and converts the voice data into text voice Data is acquired, and the voice data of the first user and / or a predetermined range with another second user according to the content of the conversation in the text voiced data of the first user and / or The contents of the text-formatted voice data of the first user can be shared.

  Among the inventions disclosed in the present application, effects obtained by typical ones will be briefly described as follows.

  That is, according to a typical embodiment of the present invention, it is possible to easily perform a 24 hour 365 operation without requiring a troublesome process such as selecting and specifying only a conversation to be processed as a conversation of each user. It is possible to record and accumulate daily and perform information processing including communication with other users based on the accumulated audio data.

It is the figure which showed the outline | summary about the structural example of the audio | voice data utilization system which is one embodiment of this invention. It is the figure which showed the outline | summary about the example of the service which becomes possible by utilizing the audio | voice data recorded constantly in one embodiment of this invention. It is the figure which showed the outline | summary about another example of the service which becomes possible by utilizing the audio | voice data recorded constantly in one embodiment of this invention. It is the figure shown about the example of the data structure of user DB in one embodiment of this invention. It is the figure shown about the example of the data structure of audio | voice data DB in one embodiment of this invention.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. Note that components having the same function are denoted by the same reference symbols throughout the drawings for describing the embodiment, and the repetitive description thereof will be omitted.

  The voice data utilization system according to an embodiment of the present invention records voice data such as conversations of each user using a portable terminal or the like, and transmits / stores the voice data to a server via a network. The server secures a storage capacity capable of continuous recording for 24 hours 365 days for each user by using a storage device with a large capacity and a low price. Voice data stored in the storage device for each user is converted to text data by voice recognition technology, and the voice data that has been converted to text by each user is collated and analyzed, allowing synchronization between users independent of time and space A system that can provide services including information processing such as asynchronous communication.

<System configuration>
FIG. 1 is a diagram showing an outline of a configuration example of an audio data utilization system according to an embodiment of the present invention. The voice data utilization system 1 includes, for example, a voice data storage server 10 connected to a network 40 such as the Internet or an intranet, and a recording device 20 and a user terminal 30 that can be connected to the voice data storage server 10 via the network 40. .

  The recording device 20 is an information processing device or device that is held and used by each user, and can record surrounding sounds as digital data. Considering the use of constantly recording user conversations and the like, it is desirable to be a portable device such as a mobile phone, a smartphone, a tablet terminal, a notebook PC (Personal Computer), and an IC recorder. In addition, it may be a stationary device such as a desktop PC, or may be configured such that the user can always record by switching and using a plurality of different types of recording devices 20 for each situation.

  The recording device 20 includes, for example, a data acquisition unit 21 that is a device for acquiring external voices such as user conversations and other various data, and a software program that operates on an OS (Operating System) and middleware (not shown). In addition, each unit includes a hashing unit 26, a mode management unit 27, a communication unit 29, and the like implemented by a circuit or the like.

  The data acquisition unit 21 constantly acquires audio data and divides it into a predetermined length, for example, into a file format. Also, other various external environment data are always acquired, and the audio data and these data are combined and recorded in a storage device such as a hard disk or a memory (not shown).

  The data acquisition unit 21 includes a microphone 22 as a device for acquiring audio data. As other devices for acquiring various external environment data, direct wireless communication is performed with other recording devices 20 such as Bluetooth (registered trademark), infrared communication, and WiFi (registered trademark). A short-range wireless communication unit 23 capable of grasping the presence of these devices, a GPS (Global Positioning System) sensor 24 that receives radio waves from a satellite and acquires position information of the recording device 20, and other environmental information You may have the various sensors 25 which acquire. The various sensors 25 include, for example, a sensor that measures temperature and pressure, a gyro sensor that acquires information related to the direction and movement of the recording device 20, a geomagnetic sensor, an acceleration sensor, and the like. In the case of a stationary apparatus such as a desktop PC, fixed position information may be manually set in advance instead of having the GPS sensor 24.

  When recording the surrounding voice acquired by the microphone 22 as voice data, a process such as deleting the silent part (or not recording the silent part) may be performed as necessary. Moreover, you may enable it to change the implementation presence or absence of such a process according to the mode mentioned later.

  The hashing unit 26 generates a hash value for the audio data divided by a certain length acquired by the data acquisition unit 21. The generated hash value is recorded in the storage device of the data acquisition unit 21 in association with the corresponding audio data. When the audio data acquired by the data acquisition unit 21 is transmitted to the audio data storage server 10, the corresponding hash value is also transmitted.

  In the audio data storage server 10 that has received the audio data, as described later, the hash value is generated by the same method as that of the recording device 20, and the hash value transmitted from the recording device 20 is compared and verified. It is possible to verify whether or not the audio data has been tampered with. The hashing unit 26 has, for example, a secret key, and can generate and return a hash value for the target data using a known hash algorithm. Note that the hashing unit 26 may be implemented as hardware such as a micro device having the above functions, for example.

  The mode management unit 27 switches the mode of the recording device 20 when acquiring audio data or the like automatically or manually. Here, the mode defines the contents of the recording conditions for recording the voice data and the usage conditions for the acquired voice data.

  Of course, there are conversations in audio data that must be protected as privacy, so only 24 hours 365 days of regular recording is known only to the minimum necessary range of users. It may happen that you don't want to. On the other hand, there may be a case where a third party should compulsorily understand the content of the user's conversation, such as in the case of an administrator such as a senior manager in the user's organization.

  Therefore, as a mode of the recording apparatus 20, for example, an office mode in a state where the user is in the office (may be further subdivided according to locations such as a plurality of work places and conference quality), home, etc. (other than the office) The private mode in the state of being in the mobile phone is defined in advance, and the mode is switched automatically or manually according to the location, time zone, etc. of the recording device 20 (and the user holding it). For example, the office A mode is detected when arrival at the office A is detected based on position information acquired by the GPS sensor 24 or network information of an in-house LAN (Local Area Network) detected by the short-range wireless communication unit 23. You can switch to Even in the same office A, the lunch mode may be switched to the private mode.

  Depending on the mode in which the audio data or the like is recorded, it is possible to set, for example, the owner of the data when the data is transmitted to the audio data storage server 10, the disclosure range, access authority, and the like. Also, depending on the mode, for example, it is possible to perform control such as changing the sensitivity and quality at the time of recording such as conversation by the microphone 22 or adjusting the data acquisition frequency by other sensors. In addition, the presence or absence of the process of excluding the silent portion during recording such as conversation with the microphone 22 may be changed according to the mode.

  Note that the types of modes that can be set and the settings in each mode are stored in the recording device 20 as a mode profile 28, for example. Each mode profile 28 can download and hold necessary ones from the audio data storage server 10, for example.

  The communication unit 29 performs communication processing for connecting to the audio data storage server 10 via the network 40. As the communication means, general wireless communication or wired communication can be used as appropriate according to the device of the recording device 20, and the means can be shared with the short-range wireless communication unit 23, such as WiFi. Also good. The communication unit 29 stores the audio data and the like recorded in the form of a file or the like by the data acquisition unit 21 at a certain length and the hash value data corresponding to each audio data in the audio data storage server 10 as needed. Send to (upload).

  The voice data storage server 10 is a server device that provides information processing services including communication between users by collecting, storing, and analyzing voice data recorded by each recording device 20. The audio data storage server 10 includes, for example, an authentication unit 11, a data collection unit 12, a hashing unit 13, and an analysis implemented by a software program operating on middleware such as an OS (not shown), a database management system, and a Web server program. Each part such as the part 14 is included. In addition, it has a user database (DB) 15 and an audio data database (DB) 16 implemented in the form of a database, a file table, or the like.

  The authentication unit 11 uses the user DB 15 when each recording device 20 uploads voice data or the like, or when each user uses voice data or the like stored in the voice data DB 16 via the user terminal 30 or the like. User authentication. The data collection unit 12 accepts uploading of audio data or the like from each recording device 20, and records and accumulates it in the audio data DB 16 for each user.

  The hashing unit 13 generates a hash value for the audio data acquired by the data collection unit 12 and responds. Similar to the hashing unit 26 in the recording device 20, for example, it has a secret key or the like, and generates a hash value for the target audio data using a hash algorithm equivalent to the hashing unit 13 and responds. The data collection unit 12 that has acquired the hash value can verify whether or not the audio data has been tampered with on the communication path by comparing the hash value acquired together with the audio data or the like from the recording device 20. Note that it is possible to verify the presence or absence of tampering by verifying the continuity of audio data or the like divided by a certain length.

  The analysis unit 14 analyzes the voice data stored in the voice data DB 16 by, for example, a known voice recognition technique to obtain text data, and further uses a known sentence structure analysis technique such as morphological analysis as necessary. Then, the conversation structure and the like are analyzed, and a process such as specifying a speaker and extracting topics and keywords is performed. The acquired text data is recorded in the voice data DB 16. This process may be performed asynchronously with the process of recording the voice data or the like in the voice data DB 16 by the data collection unit 12.

  In addition, a “place” (for example, a meeting) in which a plurality of users are working together by collating text data about each user and associating and grasping them based on time zones and places. Analyzing the situation. At this time, the number of combinations that match the text data of each user can become enormous as the number of users increases, so the position information and time information about the voice data, and other recording devices 20 in the vicinity By narrowing down the data to be collated based on the relationship or the like, analysis in a realistic processing time is made possible.

  In the analysis of the situation of “place”, for example, when the schedule information of each user is held in the form of the schedule database (DB) 17 or the like in the voice data storage server 10 or another system, the schedule information It is also possible to provide services such as automatic creation of minutes and distribution to participants by associating information with “place” information.

  Also, by analyzing the voiced text data, as described later, for example, when a word corresponding to a specific keyword or command appears in the conversation, the text data (or voice data) of the conversation content is changed. Transfer or share it with the required users for reference. As a result, it is also possible to realize information transmission / sharing and communication based on explicit / implicit instructions by voice.

  The user terminal 30 is a client terminal such as a PC that is held and used by each user. For example, the user terminal 30 accesses the voice data storage server 10 using a web browser (not shown) and stores the data stored in the voice data DB 16. Processing such as analysis, search, and inquiry can be performed. If the recording device 20 is an information processing device having the above functions, it is not particularly necessary.

<Usage form>
As a basic usage mode, for example, the user can appropriately retrieve and refer to text data of each user stored in the voice data DB 16 of the voice data storage server 10 by searching for the voice data. . By utilizing this, for example, the user can immediately record the idea by murmuring, etc., so that the information can be accumulated by a very simple method and can be retrieved later.

  The data stored in the audio data DB 16 is disclosed not only to the user but also to the disclosure range set by the mode. Therefore, for example, an administrator such as the manager of the organization to which the user belongs refers to and analyzes the contents of the voice data and the voice data made available to the user by agreeing with the user. Can do. This makes it possible for the administrator to understand the information transmission route within the organization. For example, when confidential information is leaked in the company, the administrator can track the leakage route or check the communication status between users in the organization. It is possible to grasp and to activate the organization.

  Also, since it is guaranteed that the voice data stored in the voice data DB 16 has not been tampered with, for example, the user made a specific statement at a specific date and time, or was located in a specific “place” It is also possible to use for the purpose of proving etc.

  FIG. 2 is a diagram showing an outline of an example of a service that can be performed by using voice data that is always recorded in the present embodiment. Here, since each user individually records voice data such as conversations individually, by providing these data, for example, providing a proof service that each user was located in the same space Indicates that it is possible.

  The example of FIG. 2 shows a case where the user A and the user B are located in the same space and are having a conversation at a meeting or the like. The user A and the user B are recorded by the recording device 20a and are stored in the audio data storage server 10. And the audio data recorded by the recording device 20b of the user B and uploaded to the audio data storage server 10 are respectively shown.

  Here, since user A and user B exist in the same space such as a conference room, the same conversation in which user A and user B are speakers is recorded in both voice data. become. Therefore, for example, even if only the voice data of user A is recorded, since conversations in which user A and user B are speakers are recorded, it is estimated that user A and user B were in the same space. However, it is possible to further increase the proof of being in the same space by collating the voice data of both and verifying that the same conversation is recorded in any data.

  As described above, in this case, for example, it is possible to grasp that the same space is a meeting or the like by matching the schedule information of the user A and the user B in the schedule DB 17 with the time zone as a key. . As a result, for example, by automatically summarizing the voice data that has been converted into text using a well-known sentence structure analysis technology, the minutes of the meeting are automatically generated, and further specified from the conversation content and schedule information. It is possible to realize services such as delivery and notification to meeting attendees.

  FIG. 3 is a diagram showing an outline of another example of a service that can be performed by using constantly recorded audio data according to the present embodiment. Here, speech data such as conversation is converted into text using speech recognition technology, and the speech data that has been converted into text is further analyzed using sentence structure analysis technology, etc., as necessary. Is included. In the case where a target word is included, an example in which transmission and sharing of information stored in the voice data DB 16 and communication using the target word are realized using this as a trigger is shown.

  For example, at the base α, the user A and the user B have a meeting or the like, and the content of the conversation is recorded and uploaded and stored in the voice data storage server 10 as in the example of FIG. Here, for example, as the utterance “10:16”, the user B utters and records a command by voice, and as a result of analysis by the analysis unit 14 of the voice data storage server 10, the utterance is a command. It is recognized that there is, and it is possible to execute processing according to the command. In the example of FIG. 3, according to the instructed command, the content of the past conversation between the user “10:00” to “10:15” and the user B is transferred to the user C located in the remote base β. In the example of FIG. 3, the content of the conversation to be processed is specified according to the time zone, but it may be possible to specify the most recent conversation or a conversation with a specific speaker as a condition.

  The transfer means is not particularly limited, and may be a known means such as e-mail, or is recorded as voice data associated with the user C in the voice data DB 16, and that fact is used by the user C. The user terminal 30c or the like may be notified to enable browsing. The data to be transferred may also be voice data, text data, or both.

  The user C who has received the voice data and / or voiced text data can reproduce / display the voice data and send a reply thereto. As a replying method, the contents can be spoken and recorded by the recording device 20 to reply as voice data (or data obtained by converting the data into text), or a known means such as an electronic mail can be used.

  Thus, for example, as in the case of the user B at the base α, a call (communication) with the user C at the base β is started without processing of an explicit call such as making a call or sending an email. Can do. In the example of FIG. 3, a command to transfer data is specified by voice utterance, but a corresponding process (information transmission, sharing, etc.) is automatically triggered by a specific keyword during conversation. You may make it perform. Further, although not an explicit call, for example, a recorded utterance may be handled as a command while a predetermined button or the like of the recording device 20 is pressed.

  Furthermore, the content of the past conversation can be traced back, and the content can be shared with a specific user, and an asynchronous conversation-like communication means can be realized. Further, such a communication means can realize a working environment as a virtual team integrated by sharing voice data (or text data) between remote bases.

  For example, just as if you were gathering at one base and working as a team, just say “Mr. C, what was that?” To a user C at a remote base Thus, it is possible to realize a communication in which an inquiry is automatically sent and the user C responds to this by searching for past conversation contents as necessary. Further, such communication can be started / executed in the same manner as a normal conversation without an explicit process or operation such as recording of a conversation or command input by a user.

<Data structure>
FIG. 4 is a diagram showing an example of the data configuration of the user DB 15 in the audio data storage server 10. The user DB 15 is a table that holds account information, attribute information, setting information for each user, and the like regarding users who can receive the service provided by the voice data utilization system 1. The user DB 15 includes items such as user ID, name, department, e-mail address, voiceprint information, mode setting, and the like. The key item is a user ID.

  The item of user ID holds ID information for uniquely identifying each user in the voice data utilization system 1. The name, department, and e-mail address items are the attribute information of the target user, the name, the department to which they belong (other groups such as groups and projects, to which the target user belongs), and contact information. Holds email address information.

  The voiceprint information item holds, for example, data relating to a voiceprint for identifying the voice of the target user. When analyzing the voice data in the voice data DB 16 by the analysis unit 14, it is possible to identify each speaker in the conversation by referring to the information. The mode setting item holds information on setting contents (preferences) for each user in each mode that can be specified by the target user. By referring to this information, it is possible to control / limit the disclosure range of voice data, the processing content, and the like according to the mode specified for the voice data of the target user stored in the voice data DB 16. For example, in the office mode, the user may not be allowed to change the setting contents such as the disclosure range, and may be restricted to be disclosed to the range determined by the organization or the like.

  FIG. 5 is a diagram showing an example of the data configuration of the audio data DB 16 in the audio data storage server 10. The voice data DB 16 is a table that holds voice data recorded by the recording device 20 and related environment information for each user. The voice data DB 16 includes items such as voice data ID, voice data, text data, user ID, acquisition time, mode, access right information, speaker user ID, position information, atmospheric pressure information, temperature information, geomagnetic information, and the like. Have. The key item is an audio data ID.

  The audio data ID item holds ID information for uniquely identifying each audio data in the audio data utilization system 1. The audio data item holds information on audio data uploaded from the recording device 20. Since the audio data is uploaded in a predetermined length from the recording device 20, the value of the audio data ID is, for example, a serial number for each user so that it is easy to grasp the order relationship of the audio data. As such, the data collection unit 12 may perform numbering. In addition, the audio data item may hold the audio digital data itself, or the audio data may be held in the audio data storage server 10 as a file, and index information such as the file name may be stored in the audio data item. You may make it hold | maintain.

  The text data item holds the contents of the target voice data converted into text data by the analysis unit 14. You may make it hold | maintain together the result information of the sentence structure analysis process by the analysis part 14. FIG. The user ID item holds information on a user ID that identifies the user who recorded the target audio data. Each audio data is managed collectively for each user ID. The item “acquisition time” holds information on a time stamp of recording / recording the target audio data. By referring to this information, it is possible to grasp the order relationship of each audio data for each user.

  The mode item holds information for identifying the mode of the recording device 20 when the target audio data is recorded. In accordance with the value of this mode, the disclosure range of the target data is set according to the setting contents (preference) of the mode in the mode setting item of the user DB 15. The access right information item holds access right information such as reference and copy for the target audio data. As for the access right, the default access right may be set according to the above mode, or the user can access the access right information item individually for each audio data by adding or overwriting it. The right may be specified.

  The item of the speaker user ID holds information of a user ID that identifies the speaker who is grasped by the analysis by the analysis unit 14 with respect to the target voice data. In the case of conversation, information of a plurality of speakers appearing may be held. Each item of position information, atmospheric pressure information, air temperature information, and geomagnetic information holds environment information acquired by each sensor of the data acquisition unit 21 of the recording device 20 when the target audio data is recorded. Accordingly, the item type and the like are appropriately set according to information that can be acquired by each sensor of the data acquisition unit 21.

  Note that the data configuration (items) of each table shown in FIGS. 4 and 5 is merely an example, and other table configurations and data configurations may be used as long as similar data can be held and managed. It may be.

  As described above, according to the voice data utilization system 1 according to an embodiment of the present invention, voice data such as conversations of each user is recorded using the recording device 20, and this is recorded via the network 40. Are transmitted to and stored in the voice data storage server 10. The voice data storage server 10 uses a storage device with a large capacity and a low price, thereby ensuring a storage capacity capable of continuous recording for 24 hours and 365 days for each user to configure the voice data DB 16. Further, the voice data stored in the voice data DB 16 for each user is converted into text data by voice recognition technology, and the voice data converted into text of each user is collated and analyzed.

  As a result, services that include information processing such as synchronous / asynchronous communication between users, regardless of time and space, require active user operations and processing both during recording and when using audio data. It becomes possible to provide in a form that does not.

  As mentioned above, the invention made by the present inventor has been specifically described based on the embodiment. However, the present invention is not limited to the embodiment, and various modifications can be made without departing from the scope of the invention. Needless to say.

  The present invention is applicable to a voice data utilization system that uses voice data accumulated by continuous recording.

1 ... voice data utilization system,
DESCRIPTION OF SYMBOLS 10 ... Voice data storage server, 11 ... Authentication part, 12 ... Data collection part, 13 ... Hashing part, 14 ... Analysis part, 15 ... User database (DB), 16 ... Voice data database (DB), 17 ... Schedule database (DB),
20, 20a, 20b ... recording device, 21 ... data acquisition unit, 22 ... microphone, 23 ... short-range wireless communication unit, 24 ... GPS sensor, 25 ... various sensors, 26 ... hashing unit, 27 ... mode management unit, 28 ... mode profile, 29 ... communication part,
30, 30c ... user terminal,
40 ... Network.

Claims (7)

A recording device that is held by each of a plurality of users, continuously records voices around the users as digital data, and records the recorded voice data divided into predetermined lengths; and
A voice data use system having a voice data storage server that stores the voice data transmitted from the recording device in a voice data recording unit for each user;
The recording device is
Sending the voice data to the voice data storage server as needed;
The voice data storage server is
The voice data stored in the voice data recording unit is converted into text data to obtain text voice data, and another second user according to the content of the conversation in the text voice data of the first user The voice data utilization system can share the contents of the voice data of the first user and / or the text voice data of the first user within a predetermined range. The voice data utilization system according to claim 1,
The contents of the voice data of the first user and / or the text-voiced voice data of the first user stored in the voice data recording unit are disclosed to a third user within a predetermined range, and 3. A voice data utilization system that can be referred to by three users. In the voice data utilization system according to claim 2,
The recording device is
When recording the audio data, a mode for specifying recording conditions and / or usage conditions of the audio data is switched according to the location and / or time zone of the recording device, and the mode information is changed to the audio data. And record with
The voice data storage server is
A voice data utilization system, wherein a public disclosure range of the contents of the voice data and / or the text-voiced voice data is set according to the contents of the mode of the voice data. The voice data utilization system according to any one of claims 1 to 3,
The recording device is
An audio data utilization system that acquires environmental information at the time of recording including position information and time of the recording device together with the recording of the audio data, and records it together with the audio data. In the voice data utilization system according to any one of claims 1 to 4,
The recording device is
Generating a first hash value for the audio data, sending the first hash value together with the audio data to the audio data storage server;
The voice data storage server is
Generating a second hash value for the audio data acquired from the recording device and comparing the first hash value with the second hash value to detect whether the audio data has been tampered with; Voice data utilization system characterized by In the voice data utilization system according to any one of claims 1 to 5,
The text-formed voice data of the fourth user stored in the voice data recording unit includes conversations of the fourth user and the fifth user, and the voice is recorded in the same time zone as the conversation. When the fourth user and the fifth user have the conversation included in the text-voiced voice data of the fifth user stored in the data recording unit, the fourth user and the fifth user The voice data utilization system, wherein the five users are treated as if they were located at the same place in the time period. The voice data utilization system according to claim 6,
The voice data storage server is
The schedule information of the fourth user or the fifth user in the time zone was acquired, and a meeting including the fourth user and the fifth user was performed in the time zone in the same place. In this case, the audio data utilization system is characterized in that the minutes of the conference are generated based on the contents of the conversation in the text-formatted audio data of the fourth user or the fifth user in the time period.

Images