JP2007164725A - Event determination method, voice data processor, event determination system and computer program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an event determination method, capable of easily determining an event only by inputting voice data through portable terminals by a plurality of users. <P>SOLUTION: The voice data processor 1 stores voice data transmitted from the plurality of users 0001-0003 in association with identification information of the users. The processor generates a plurality of search data based on the stored voice data. The processor determines weights of the voice data based on the generated search data, and extracts voice data corresponding to identification information the determined weight of which is a predetermined weight or more. The processor extracts and determines an event using the search data corresponding to the extracted voice data from an event database storing search data in association with events. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention relates to an event determination method, an audio data processing device, an event determination system, and a computer program for causing a computer to function as an audio data processing device.

  In recent years, mobile terminals such as mobile phones have been used as communication tools. The user can use the mobile terminal to contact other users and determine an event or the like to be performed in the future. In determining an event, an action plan providing system for supporting the event is known (for example, Patent Document 1). In this action plan providing system, the user inputs time, place and budget, and the center provides the action plan to the user in consideration of the inputted time, place and budget.

In addition, the agent device disclosed in Patent Document 2 is installed in an automobile, acquires information about the vehicle, time, place, and the like, and recommends a sightseeing spot or a restaurant. Patent Document 3 is known as a technique related to speech recognition.
JP 2003-6365 A JP 2000-266551 A JP 2003-44498 A

  However, the techniques disclosed in Patent Documents 1 and 2 both require time, place, budget, and the like to be input to the device to obtain the result, which has a problem of complicated processing. In particular, as the number of users increases, the event determination process becomes more complicated. Therefore, it has been requested to create an event determination method that reflects the intentions of a plurality of users by a simple method.

  Also, when determining an event that reflects the will of multiple users, it is necessary to consider the convenience of the majority user most, but it is necessary to determine the event also considering the convenience of the minority .

  The present invention has been made in view of such circumstances, and by analyzing and weighting audio data transmitted from a plurality of users and determining an event in accordance with the result, the plurality of users can make a portable terminal. Provided are an event determination method, an audio data processing device, an event determination system, and a computer program for causing a computer to function as an audio data processing device, which can easily determine an event simply by inputting audio data respectively on a machine There is.

  Another object of the present invention is to acquire user position information, and by considering the acquired position information in weighting, audio data capable of determining an event related to a region that is convenient for a plurality of users. It is to provide a processing apparatus and the like.

  Another object of the present invention is to provide an audio data processing device and the like that can facilitate participation in a minority event by determining a priority order for the event based on position information.

  Another object of the present invention is to provide an event determination system capable of easily grasping an event determined by a plurality of users by transmitting the determined event to the user's portable terminal.

  Another object of the present invention is to provide an event determination system capable of reliably executing an event by transmitting state information indicating the determined event state to a portable terminal.

  The event determination method according to the present invention is an event determination method in which received audio data is processed to determine an event, and audio data transmitted from a plurality of users is stored in an identification information storage unit in association with user identification information. A step of generating a plurality of search data by the control unit based on the stored voice data, a weight determination step of determining a weight of the voice data by the control unit based on the generated search data, and a predetermined step Using the search step corresponding to the extracted voice data from the extraction step of extracting the voice data corresponding to the identification information equal to or greater than the weight by the control unit, and the event database storing the search data corresponding to the event, An event determination step of determining an event by the control unit

  The voice data processing device according to the present invention is a voice data processing device for processing received voice data, and stores voice data transmitted from a plurality of users in association with user identification information in an identification information storage unit. Generating means for generating a plurality of search data based on the stored voice data; weight determining means for determining the weight of the voice data based on the generated search data; and voice data corresponding to identification information greater than a predetermined weight And an event determining means for determining an event using search data corresponding to the extracted voice data from an event database storing search data in association with the event.

  The voice data processing device according to the present invention includes means for receiving position information of a user who has transmitted voice data, means for storing the received position information in the identification information storage unit in association with the identification information and voice data, and The weight determination means is configured to determine the weight of the audio data based on the search data generated by the generation means and the stored position information.

  In the audio data processing device according to the present invention, the event database stores search data and position information in association with an event, and reads position information corresponding to the event determined by the event determination means from the event database. And a priority order determining means for determining the priority order of the event determined by the event determining means based on the read position information.

  The audio data processing apparatus according to the present invention is configured such that the weight determining means determines the weight of the audio data based on the volume level of the audio data stored in the identification information storage unit and the search data generated by the generating means. It is characterized by being.

  In the audio data processing device according to the present invention, the weight determining means reads a weight corresponding to the search data generated by the generating means from a weight database storing weights in association with the search data, and the read weight and The weight is determined based on the voice data stored in the identification information storage unit.

  The event determination system according to the present invention is an event determination system comprising a mobile terminal and any one of the above-described audio data processing devices connected to the mobile terminal via a communication network. And a means for transmitting the event to the portable terminal.

  The event determination system according to the present invention is an event determination system including the mobile terminal and the audio data processing apparatus connected to the mobile terminal via a communication network. And a means for rearranging according to the priority order of the event determined by the priority order determining means, and a means for transmitting the rearranged event to the portable terminal.

  In the event determination system according to the present invention, the event database stores state information indicating an event state, and the audio data processing device reads out state information corresponding to the event determined by the event determination means and The apparatus further comprises means for transmitting to the terminal.

  The computer program according to the present invention is a computer program that causes a computer to process received audio data and determine an event, and associates audio data transmitted from a plurality of users with user identification information in a computer control unit. And generating a plurality of search data based on the read voice data, and generating a plurality of search data on the basis of the generated search data. A weight determination step for determining the weight of the voice data, an extraction step for causing the computer control unit to extract voice data corresponding to identification information having a predetermined weight or more, and a control unit for the computer in association with the event. The extracted voice from the event database storing the search data Using the search data corresponding to the over data, characterized by comprising an event determining step of determining an event.

  In the present invention, the voice data processing apparatus stores voice data transmitted from a plurality of users in the identification information storage unit in association with the user identification information. Based on the stored voice data, the voice data processing device generates a plurality of search data. Then, the weight of the voice data is determined based on the generated search data. The voice data corresponding to the identification information whose determined weight is equal to or greater than the predetermined weight is extracted. Finally, the event is determined using the search data corresponding to the extracted voice data from the event database storing the search data in association with the event. That is, by analyzing the voice data and the search data generated from the voice data, the weight of the voice data of the plurality of users is determined, and the event is determined according to this weight. An event that reflects the will of each user is determined simply by inputting.

  In the present invention, the audio data processing device receives the position information of the user who transmitted the audio data. The received position information is stored in the identification information storage unit in association with the user identification information and voice data. Then, the weight of the voice data is determined based on the generated search data and the stored position information. In other words, in addition to the search data, the event is determined in consideration of the user position information obtained from the mobile terminal, so it is possible to determine an event that is convenient for a plurality of users.

  In the present invention, since the weight of the voice data is determined based on the volume level of the voice data stored in the identification information storage unit and the generated search data, the opinion of the user who claimed the voice loudly is reflected more. As a result, more detailed event determination is possible.

  In the present invention, the weight corresponding to the generated search data is read from the weight database that stores the weight in association with the search data. That is, a weight is assigned to each of a plurality of search data generated from voice data, and the corresponding weight is read out. Since the weight is determined based on the read weight and the voice data stored in the identification information storage unit, fine event determination according to the search data can be performed.

  In the present invention, the event determination system includes a plurality of portable terminals and an audio data processing apparatus connected to each portable terminal via a communication network. Since the determined event is transmitted from the voice data processing apparatus to each portable terminal, each user can easily know the result of the event determination through the portable terminal that has input the voice data.

  In the present invention, the event database stores search data and position information in association with events. When the event is determined, position information corresponding to the determined event is read from the event database. Then, the priority order of the determined event is determined based on the read position information, and the event is rearranged according to the priority order. Thereafter, since the result is transmitted to the mobile terminal in the order of the rearranged events, the events considering the position information are displayed in order. As a result, information related to the event taking into account the convenience of the user in the remote location is provided to the portable terminal.

  In the present invention, the event database stores state information indicating the state of the event. Since the audio data processing device reads out the state information corresponding to the determined event and transmits it to the mobile terminal, the user can grasp the state of the event before executing the event.

  In the present invention, the weight of the voice data of a plurality of users is determined by analyzing the search data generated from the voice data, and the event is determined according to this weight. By simply inputting data, an event reflecting the will of each user is determined.

  In the present invention, events are determined in consideration of user location information obtained from the mobile terminal in addition to the search data, so it is possible to determine events that are convenient for multiple users. It becomes.

  In the present invention, since the weight of the voice data is determined based on the volume level of the voice data stored in the identification information storage unit and the generated search data, the opinion of the user who claimed the voice loudly is reflected more. As a result, more detailed event determination is possible.

  In the present invention, a weight is assigned to each of a plurality of search data generated from voice data, and the corresponding weight is read out. Since the weight is determined based on the read weight and the voice data stored in the identification information storage unit, fine event determination according to the search data can be performed.

  In the present invention, since the determined event is transmitted from the voice data processing device to each portable terminal, each user can easily know the result of the event determination through the portable terminal that has input the voice data. .

  In the present invention, the rearranged events are rearranged according to the priority order of the determined events, and the rearranged events are transmitted to the mobile terminal, so that the events considering the position information are arranged in order. As a result, information related to the event taking into account the convenience of the user in the remote location is provided to the portable terminal.

  In the present invention, the event database stores state information indicating the state of the event. Since the audio data processing device reads out the state information corresponding to the determined event and transmits it to the mobile terminal, the user can grasp the state of the event before executing the event. In addition, the present invention has an excellent effect that the event can be confirmed or stopped depending on the state, and the event can be easily managed among a plurality of users.

Embodiment 1
FIG. 1 is a schematic diagram showing an outline of an event determination system according to the present invention. In FIG. 1, S is an event determination system, which includes an audio data processing device 1, portable terminals 2, 2, 2 and a communication network. In the present embodiment, it is assumed that the event to be determined is a restaurant determination. Hereinafter, the event determination system S will be described as the restaurant determination system S. The determination of the event is not limited to the determination of the restaurant desired by each user, but the determination of the sport (soccer, tennis or golf) desired by each user, or the destination desired by each user (tourist destination, accommodation) Etc.).

  In FIG. 1, reference numeral 1 denotes an audio data processing apparatus, for example, a server computer. In the following description, it is assumed that the audio data processing device 1 is the server computer 1. Mobile terminals 2, 2, and 2 are connected to the server computer 1 through a communication network N composed of the Internet or a mobile phone network so that they can communicate wirelessly. The mobile terminal 2 is a mobile phone, a PDA (Personal Digital Assistance), a game machine, or the like. In the following description, it is assumed that the mobile terminal 2 is the mobile phone 2. A plurality of users use the mobile phone 2 to input the current mood by voice when determining a restaurant. Audio data input from the mobile phone 2 is transmitted to the server computer 1. In this embodiment, each user inputs a voice using each mobile phone 2. However, a plurality of users may input voices to one mobile phone 2 separately. .

  The mobile phone 2 transmits position information based on a GPS (Global Positioning System) function or position information related to the base station to the server computer 1. In this embodiment, an example is shown in which a user 0001 and a user 0002 communicate in the same area, and a user 0003 starts communication in different areas. The server computer 1 determines the optimum restaurant by the process described later using the transmitted audio data and position information, and transmits the determined restaurant information to the mobile phone 2.

  FIG. 2 is a block diagram showing a hardware configuration of the server computer 1. The server computer 1 includes a CPU (Central Processing Unit) 11, a RAM (Random Access Memory) 12, an input unit 13, a display unit 14, a communication unit 16, and a storage unit 15 as control units. The CPU 11 is connected to each hardware unit of the server computer 1 via the bus 17 and controls them, and executes various software functions according to a control program stored in the storage unit 15. The control program is described in a programming language such as C language.

  The display unit 14 is, for example, a liquid crystal display, and the input unit 13 includes a keyboard and a mouse. The communication unit 16 is a modem or a LAN card and transmits / receives information to / from the mobile phone 2. The storage unit 15 is constituted by, for example, a hard disk, and stores therein the above-described control program, the identification information storage unit 151, the restaurant database 152 (event database 152), and the weight database 153. Details of the identification information storage unit 151, the restaurant database 152, and the weight database 153 will be described later. The identification information storage unit 151, the restaurant database 152, and the weight database 153 stored in the storage unit 15 are not necessarily provided in the server computer 1 and may be stored in a database computer (not shown).

  FIG. 3 is a block diagram showing a hardware configuration of the mobile phone 2. The cellular phone 2 includes a CPU 21, a RAM 22, an input unit 23, a display unit 24, a communication unit 26, a microphone 28, a speaker 29, a GPS receiver 210, and a storage unit 25 as control units. The CPU 21 is connected to the hardware units of the mobile phone 2 via the bus 27, controls them, and executes various software functions according to the control program stored in the storage unit 25.

  The display unit 24 is, for example, a liquid crystal display, and the input unit 23 is configured by a push button or the like. In addition, you may make it comprise the display part 24 and the input part 23 integrally like a touchscreen. The speaker 29 outputs audio data. The microphone 28 converts an audio signal input from the user into an electric signal. The converted electrical signal is converted into digital data by an A / D converter (not shown) and output to the CPU 21. The communication unit 26 includes a high-frequency transmission / reception unit, an antenna, and the like, and performs transmission / reception of various data including voice data and character data. The GPS receiver 210 receives position information such as a coordinate value of the current location transmitted from a GPS satellite.

  FIG. 4 is an explanatory diagram showing a record layout of the identification information storage unit 151. When communication is established between the mobile phone 2 and the server computer 1, transmitted / received data and audio data are stored in the identification information storage unit 151. The identification information storage unit 151 includes a group ID field, a user ID field, a mail address field, a voice data field, a search data field, a volume level field, a position information field including a coordinate field and an area field, and a weight field. The group ID field stores identification information for specifying a group of a plurality of users, and a specific number is assigned to each group. In the user ID field, identification information (hereinafter referred to as a user ID) for specifying a user who inputs voice is stored for each user. In the present embodiment, the user IDs “0001”, “0002”, and “0003” belong to the group ID “1” participate in the restaurant determination system S for restaurant determination.

  FIG. 5 is an explanatory diagram showing an image of a screen displayed on the display unit 24 of the mobile phone 2. When the user participates in the restaurant determination system S, the user operates the input unit 23 of the mobile phone 2 to establish communication with the server computer 1 and accesses the top page related to the event determination system S. FIG. 5A is an explanatory diagram showing an image of the top page. The screen of FIG. 5A is stored in the storage unit 15 of the server computer 1 in association with a URL (Uniform Resource Locator), and is in cHTML (Compact Hyper Text Markup Language) format according to a request from the mobile phone 2. Or the like is transmitted to the mobile phone 2. The CPU 21 of the mobile phone 2 displays the transmitted screen on the display unit 24.

  As shown in FIG. 5A, a screen for inputting a user ID and a password is displayed on the top page. In the present embodiment, the restaurant determination system S is a membership system, and a user ID, a password, a group ID, a mail address, and the like are associated with each other and stored in advance in the identification information storage unit 151 of the storage unit 15. The user inputs the user ID and password and logs in to the restaurant determination system S. The CPU 11 of the server computer 1 performs authentication based on the transmitted user ID and password. In addition, although the password is not illustrated in the identification information storage unit 151 of FIG. 2, the password of each user is stored in association with the user ID.

  The CPU 11 searches the identification information storage unit 151 based on the transmitted user ID, and reads the group ID and mail address to which the user belongs. Then, a cHTML document in which the read group ID, mail address, and user ID are described is created and transmitted to the mobile phone 2. The CPU 21 of the mobile phone 2 displays the transmitted cHTML as shown in FIG. In FIG. 5B, information for specifying the user 0001 such as the group ID “1”, the user ID “0001”, and the mail address “0001@XYX.com” is displayed. In this group, there are a user 0002 and a user 0003. Similarly, by logging in from the mobile phone 2, the user can participate in the restaurant determination system S.

  As shown in FIG. 5 (b), the display unit 24 displays characters prompting voice input such as "Welcome, click on voice input start and talk about your present feeling." 23 is clicked and the voice input start button 51 is clicked. When receiving a voice input start signal from the input unit 23, the CPU 21 of the mobile phone 2 starts collecting sound from the microphone 28. The sound input from the microphone 28 is converted into an electric signal, amplified, and then output to the CPU 21 as digitized sound data through an A / D converter (not shown). The CPU 21 transmits the output audio data to the server computer 1. The user appropriately operates the input unit 23 to stop sound collection.

  In the audio data field of FIG. 4, audio data transmitted from the mobile phone 2 is stored in association with the user ID. The CPU 11 of the server computer 1 stores the transmitted voice data in association with the user ID. The user 0001 inputs a voice saying “I don't like sweet food!”, The user 0002 inputs a voice saying “I want a quiet shop”, and the user 0003 inputs a voice saying “Japanese food is good”. In the mail address field, the mail address of each user is stored in association with each user ID.

  In the search data field, a plurality of search data generated from the voice data is stored in association with the user ID. The CPU 11 performs the following processing to generate search data. In other words, the CPU 11 that has received the voice data activates a voice recognition program and converts the voice data into text data. Then, comparison is made with search data stored in a weight database 153 (see FIG. 7), which will be described later, and when there is matching search data, each search data is generated from the text data. For example, in the case of voice data “I don't like sweet things!”, The text data is converted to “I do n’t like sweet things”, and after matching with “sweet”, “things” and “dislikes” existing in the weight database 153, “ A plurality of search data consisting of “sweet”, “thing” and “dislike” are extracted. The voice recognition process is described in Patent Document 3.

  A volume level corresponding to each search data is stored in the volume level field. The CPU 21 measures the volume level of the audio data corresponding to each search data and stores it in the volume level field corresponding to the search data. In this example, “sweet” has a volume level “1.0”, “mono” has a volume level “1.0”, and “dislike” has a volume level “1.5”. The higher the numerical value, the higher the level. In this embodiment, the volume level of audio data is measured. However, the present invention is not limited to this. For example, the frequency of audio data is analyzed by fast Fourier transform or the like to measure the intensity of audio. You may make it do.

  The position information field stores information related to the position at which the user is communicating. In this embodiment, the position information field includes a coordinate field indicating a two-dimensional coordinate value on the map and an area field indicating an area near the coordinate value. Composed. The GPS receiver 210 of the mobile phone 2 outputs the received coordinate data to the CPU 21, and the CPU 21 transmits the coordinate data to the server computer 1 with the start of the restaurant determination system S described with reference to FIG. The CPU 11 of the server computer 1 stores the transmitted coordinate data in the coordinate field. For example, the coordinates of the user 0001 are (Xa-1, Yb-1). In the case of the mobile phone 2 having no GPS function, the coordinate data of the radio base station used at the time of logging in to the restaurant determination system S may be used instead.

  The CPU 11 has a map database (not shown) in the storage unit 15. This map database stores area data such as the nearest station, expressway exit, and nearest building in association with the coordinate data. The CPU 11 searches the map database based on the coordinate data, reads the corresponding area data, and stores it in the area field. In this embodiment, it is determined that the user 0001 and the user 0002 are located in the same area “JR Shibuya Station”, and the user 0003 is determined to be located in the area “Subway Shimbashi Station” that is one person apart. .

  In the weight field, the weight for the voice input by each user is determined in consideration of the voice data, the search data, and the position information. The procedure of the weight determination process will be described later. The determined weight is stored in association with the user ID. For example, the weight of the user 0001 is stored as 8.2, the weight of the user 0002 is stored as 7.2, and the weight of the user 0003 is 4 .3 is stored.

  FIG. 6 is an explanatory diagram showing a record layout of the restaurant database 152. The restaurant database 152 includes a search data field including a restaurant field, a genre field, and an adjective field, a position information field including a coordinate field, an area field, and an access field, and a state information field. These various types of information are created based on information provided by each restaurant, and the operator inputs information from the input unit 13 or receives information transmitted from a computer (not shown) from the communication unit 16 and receives information from the CPU 11. You may make it write in the restaurant database 152 of the memory | storage part 15 by instruction | indication.

  In the restaurant field, restaurant names that can be selected by the user are stored. In the search data field, search data used when searching for a restaurant is stored, and in this embodiment, the genre and adjective of the restaurant are used as search data. For example, the genre field stores restaurant genres such as “Japanese food”, “Asia”, “ice cream”, etc., and the adjective field has the adjectives “spicy”, “high, refreshing”, “sweet” "Cold" is stored. These search data are only given as examples to simplify the explanation, but in addition, the presence / absence of non-smoking seats, type (for families, couples, banquets, etc.), budget (up to 3000 yen, 5000 yen) The data for searching various restaurants such as up to etc. may be used.

  Information indicating the location of the restaurant is stored in the position information field, and in the present embodiment, the position of the restaurant is specified by coordinates, area, and access information. In the coordinate field, coordinate values on a two-dimensional map of the restaurant are stored, and the coordinate field and the coordinate axis center described in FIG. 4 are the same. Information on the area where the restaurant is located is stored in the area field, and the nearest station and line, landmark points (hotels, famous buildings, sightseeing spots, various facilities), expressway interchange names, etc. are stored. ing. The access field stores the required time from the area stored in the area field. For example, “Spicy Curry Shop” is located 1 minute from “JR Shibuya Station”.

  Information on whether or not the restaurant is available is stored in the state information field. In the present embodiment, a circle indicates that the corresponding restaurant can be reserved on the search day, or a business day, and a cross indicates that the corresponding restaurant cannot be reserved due to fullness on the search day. It indicates that it cannot be used due to regular holidays. The state information may be stored in the restaurant database 152 by the operator from the input unit 13 upon receiving a notification from the restaurant, or from the computer (not shown) that manages the restaurant reservation status and the store opening status to the server computer 1. The status information may be transmitted and sequentially stored in the restaurant database 152. In the present embodiment, the status information for each day is shown, but the status information may be managed finely every hour (from 18:00 to 19:00, from 19:00 to 20:00, etc.). It is also possible to manage the restaurant status information over a plurality of days, not just on the search day.

  FIG. 7 is an explanatory diagram showing a record layout of the weight database 153. The weight database 153 includes a search data field, a classification field, a condition field, and a weight field. The search data field stores search data that is a glossary for detecting search data related to voice data input by the user. For example, “noisy”, “red light”, “store”, “eat”, “delicious”, etc. are stored. Note that the search data shown in FIG. 7 is an example, and other search data may be prepared. The classification field stores the classification of search data such as parts of speech in association with the search data. For example, a classification “adjective” is stored in the search data “noisy”, a classification “noun” is stored in the search data “tea”, and a classification “claim” is stored in the search data “dislike”.

  In the condition field, search conditions are stored in association with the search data. For example, the search data “dislike” stores the condition “extract previous and next adjectives or antonyms of nouns”. In the present embodiment, as an example, “condition” is set for a specific term belonging to the classification “claim”. This is because, for example, a term intended to claim "dislike", "no use", etc. means denial of a term intended to claim "good", "kana", etc. Or, "Extract nouns for nouns" is set. For example, if the user 0001 utters "I don't like sweet things", search data "sweet", "things", and "dislike" are generated, and the adjective "sweet" and the noun "things" that exist before "dislike" Is extracted from a dictionary database (not shown). It is determined that an antonym of “thing” does not exist, and it is determined that the user 0001 desires “spicy” “thing”. The weight field stores a weight corresponding to predetermined search data. For example, search data “dislike” is stored as weight “4”, and search data “kana” is stored as weight “2”.

  FIG. 8 is an explanatory diagram for explaining the procedure of search data generation and weight determination processing. When the user inputs voice data “I don't like sweet things” through the microphone 28, the voice data is received by the server computer 1, and the CPU 11 generates search data from the voice data “I don't like sweet things”. The CPU 11 recognizes “sweet”, “thing”, “ha”, and “dislike” by using voice recognition software, and converts it into text data. Based on the text data “sweet”, “thing”, “ha”, “dislike”, the search data field of the weight database 153 is searched, and the search data “sweet”, “thing”, and “dislike” are extracted. Then, the generation of the search data is finished. The CPU 11 stores the generated search data in the search data field of the identification information storage unit 151 in association with the user ID.

  Subsequently, the CPU 11 extracts the corresponding weight from the weight database 153 based on the generated search data. In this example, the weight “4” corresponding to the search data “dislike” is extracted. The CPU 11 multiplies the weight related to the extracted search data by the volume level with reference to the identification information storage unit 151 in order to calculate the weight in consideration of the volume level. In this example, the weight “6.0” is obtained by multiplying the weight level “1.5” of “dislike” by the weight 4 of “dislike”. Similarly, the CPU 11 refers to the weight database 153 for the voice data “Is quiet store good?”, Generates search data “quiet”, “store”, “good”, “kana”, and corresponding search data. , “3” for “good” and “2” for “kana”. The CPU 11 refers to the volume level stored in the volume level field of the identification information storage unit 151 and adds “3 × 1.0” related to “good” and “2 × 1.1” related to “kana”. A weight of 5.2 is obtained.

  For the audio data example “Japanese food is good”, search data “Japanese food” and “good” are generated, and the weight “3.3” is obtained by multiplying the weight “3” of the search data “good” by the volume level 1.1. Get. In this way, the weight can be calculated based on the volume level of the search data and the voice data generated by the user, the weight of the user 0001 is “6.0”, the weight of the user 0002 is “5.2”, and The weight of the user 0003 is “3.3”.

  Subsequently, a weight calculation process taking position information into consideration will be described. In the present embodiment, processing is performed so as to increase the weight of an area where there are many users. The CPU 11 refers to the area field of the identification information storage unit 151, sorts in order of areas with the largest number of users, and performs processing of adding higher weights in the order of areas with the larger number of users. In this example, two users 0001 and 0002 are the area “JR Shibuya Station”, and one user 0003 is “Subway Shimbashi Station”. In this case, for example, a weight “2” is added to an area “JR Shibuya Station” where many users are located, and a weight “1” is added to an area “Subway Shimbashi Station” where there is only one user. As a result, the weight of the user 0001 is “6.0 + 2.0 and 8.0”, the user 0002 is “5.2 + 2.0 and 7.2”, and the user 0003 is “3.3 + 1.0 and 4”. .3 ". This addition example is an example, and conversely, the weight of an area where a large number of users are located may be set low, and this weight may be added or multiplied.

  The CPU 11 compares the finally determined weights, and extracts search data relating to the user's voice data having the largest weight, for example, the user having the largest weight. In this embodiment, “sweet”, “thing”, and “dislike” are extracted. Then, the CPU 11 refers to the condition field of the weight database 153 and extracts an antonym as necessary. In this example, since the condition “extract the adjectives before and after the adjectives or nouns” is extracted, the search data finally becomes “spicy” “thing”. Then, the CPU 11 searches the search data field and the area field of the restaurant database 152 based on the search data and the user position information, and extracts the corresponding restaurant. In this example, the restaurants “Spicy Curry”, “A Korean Restaurant”, “D Dandan Noodle” and “F Thai Cuisine” that satisfy the search data “Spicy” and the area “JR Shibuya Station” under the AND condition are extracted. When the weight of the user 0003 is the largest, the restaurant “C Izakaya” that satisfies the search data “Japanese food” “Good” and the area “Subway Shimbashi Station” under the AND condition is extracted.

  The CPU 11 sorts the restaurants extracted based on the position information in consideration of the access of minority users located outside the area. This sorting is performed based on the access field of the restaurant database 152. The CPU 11 rearranges the restaurants extracted in descending order of the access field values in the restaurant database 152. In this example, access “1 minute” “very spicy curry restaurant”, access “3 minutes” “D Tandan noodles”, access “5 minutes” “F Thai food”, access “7 minutes” “A Korean restaurant” Sorted in order. The CPU 11 transmits the restaurant and access information extracted in this sort order to the mobile phone 2 of each user. This information may be transmitted by referring to the e-mail address stored in the identification information storage unit 151 by e-mail carrying.

  FIG. 9 is an explanatory diagram showing an image of a search result list displayed on the display unit 24 of the mobile phone 2. As shown in the figure, the restaurants “very spicy curry restaurant”, “D Dandan noodles”, “F Thai food” and “A Korean restaurant” searched in the order sorted by the CPU 11 of the server computer 1 are displayed. Access information is written in association with the restaurant name. As a result, the restaurants are displayed in the order in which they are easily accessible, and it is possible to construct a system in consideration of a small group of users in remote locations.

  The storage unit 15 of the server computer 1 is provided with a database (not shown) in which business hours, telephone numbers, maps, budgets, recommended menus, etc. of each restaurant are stored. You may make it transmit the hyperlink for accessing the information of each restaurant of this. The CPU 11 of the server computer 1 transmits these pieces of information in the cHTML format, and the CPU 21 of the mobile phone 2 analyzes this information and lists restaurant and restaurant hyperlinks and access information as shown in FIG.

  Further, status information such as whether each restaurant is full may be provided. The CPU 11 extracts “state information” corresponding to the extracted restaurant from the restaurant database 152, and for those in which the state information is stored as “x”, the text data of “full” is listed together with the restaurant name. Describes cHTML. The CPU 11 transmits restaurant information including the state information to the mobile phone 2, and the CPU 21 of the mobile phone 2 analyzes the information and displays the state information as shown in FIG. In the example of FIG. 9, “F Thai food” whose status information is “×” is displayed as “full”. In the present embodiment, only “full” is displayed as the status information. However, “reservation possible” or “usable” etc. are stored for those stored in the status information field as “O”. Information may be added. Further, the state information may be defined more finely, and information such as “Closed” and “During special service” may be provided. As a result, it is possible to avoid the problem of being unable to use due to full seats despite the search.

  FIG. 10 is a flowchart showing a processing procedure when audio data is stored. When the user's cellular phone 2 requests the server computer 1 to use the restaurant determination system S, the CPU 11 reads the login screen stored in the storage unit 15 and transmits it to the cellular phone 2. A login screen is displayed on the display unit 24 of the mobile phone 2 as shown in FIG. When the user ID and password are transmitted from the mobile phone 2, the CPU 11 of the server computer 1 accepts the transmitted user ID and password (step S101). The CPU 11 determines whether or not the transmitted user ID and password match the user ID and password stored in advance in the storage unit 15 (step S102). If the CPU 11 determines that it is not valid (NO in step S102), the process ends. If the CPU 11 determines that it is valid (YES in step S102), the group ID corresponding to the user ID stored in the identification information storage unit 151 and the voice input screen stored in the storage unit 15 are read and transmitted to the mobile phone 2. (Step S103).

  A voice input screen including the transmitted group ID and the voice input start button 51 is displayed on the display unit 24 of the mobile phone 2 as shown in FIG. The user operates the voice input start button 51 from the input unit 23 of the mobile phone 2 and inputs voice through the microphone 28. The audio signal collected from the microphone 28 is digitized by the CPU 21, and the audio data is transmitted to the server computer 1. The server computer 1 accepts the transmitted audio data (step S104). The CPU 11 extracts the volume level from the transmitted audio data. The CPU 11 stores the transmitted audio data and the extracted volume level in the identification information storage unit 151 in association with the user ID (step S105).

  The CPU 11 requests the mobile phone 2 to transmit position information. In response to this acquisition request, the CPU 21 of the mobile phone 2 transmits information on the current coordinates of the mobile phone 2 obtained from the GPS receiver 210 as position information. The CPU 11 of the server computer 1 receives the transmitted position information (step S106). The CPU 11 stores the received coordinate information, which is position information, in the coordinate field of the identification information storage unit 151 in association with the user ID (step S107). Further, the CPU 11 refers to a map database (not shown) in the storage unit 15 to search for an area corresponding to the transmitted coordinates, and associates the searched area information with the user ID in the area field of the identification information storage unit 151. Remember. Through the above processing, various types of information such as voice data, volume level, coordinates, and area are stored in the identification information storage unit 151 in association with the user ID.

  The CPU 11 reads out another email address in the group stored in the identification information storage unit 151 (step S108). In this embodiment, the e-mail addresses of the users 0002 other than the user 0001 who started the event determination system S and the user 0003 are read. The CPU 11 generates and transmits an e-mail calling for participation in the restaurant determination system S to the read e-mail address (step S109).

  FIG. 11 is an explanatory diagram showing an example of an e-mail calling for participation. The CPU 11 of the server computer 1 reads the text calling for participation stored in the storage unit 15 and transmits an e-mail to the user 0002 and the user 0003 in the cHTML format. The text and voice input start button 51 shown in FIG. 11 is displayed on the display unit 24 of the mobile phone 2 of the user 0003. The user 0003 operates the voice input start button 51 through the input unit 23 and inputs voice from the microphone 28. In the present embodiment, an HTML-format e-mail including a text and a voice input start button 51 is transmitted to each user. However, a text-format e-mail including a predetermined URL is transmitted to access this URL. By doing so, the voice input start button 51 may be displayed to input voice.

  The CPU 11 accepts audio data transmitted from another user (step S1010), and stores the audio data and the volume level of the transmitted audio data in the identification information storage unit 151 in association with the user ID of the other user ( Step S1011). Further, the CPU 11 requests the other user's mobile phone 2 to transmit the position information. In response to this acquisition request, the CPU 21 of the mobile phone 2 transmits information on the current coordinates of the mobile phone 2 obtained from the GPS receiver 210 as position information. The CPU 11 of the server computer 1 receives the transmitted position information, and stores the position information including the coordinates and the area in the identification information storage unit 151 in association with the user IDs of other users in the same manner as in the above-described process (step S1). S1012). In this way, the voice data, volume level, coordinates, and various types of area information of other users who wish to participate in the restaurant determination system S are stored in the identification information storage unit 151.

  The CPU 11 determines whether or not a predetermined time has elapsed (step S1013). If the CPU 11 determines that the predetermined time has not elapsed (NO in step S1013), the CPU 11 proceeds to step S1010 and waits to accept voice data from other users in the group. On the other hand, if the CPU 11 determines that the predetermined time has elapsed (YES in step S1013), the process ends to further proceed with the process of the restaurant determination system S. When a plurality of users share one mobile phone 2, the process proceeds to step S101 when the storage of the voice data, volume level, and position information (steps S105 and 107) of one user is completed. The reception of the voice data of other users, that is, the processing after step S104 may be performed.

  FIG. 12 is a flowchart showing a procedure of search data generation processing. The CPU 11 of the server computer 1 reads the audio data stored in the identification information storage unit 151 (step S121). CPU11 starts the speech recognition software memorize | stored in the memory | storage part 15, and converts audio | voice data into text data (step S122). The CPU 11 refers to the weight database 153 based on the converted text data and generates search data (step S123). Specifically, the CPU 11 compares the text data text and the search data stored in the search data field of the weight database 153, and if there is matching search data, extracts it as search data. The CPU 11 stores the generated search data in the identification information storage unit 151 in association with the user ID (step S124). The above processing is repeated for audio data related to all user IDs existing in the same group.

  FIG. 13 is a flowchart showing the procedure of the weight determination process. The CPU 11 of the server computer 1 reads the search data from the search data field of the identification information storage unit 151 in order to determine the weight (step S131). The CPU 11 refers to the weight database 153 and determines whether there is a weight corresponding to the read search data (step S132). When the CPU 11 determines that there is no weight (NO in step S132), for example, it is determined that there is no corresponding weight for the search data “quiet”, and the processing of steps S133 to S135 is skipped and the process proceeds to step S136. .

  If the CPU 11 determines that there is a weight (YES in step S132), the weight corresponding to the search data is read (step S133). For example, the weight “3” is read for the search data “good”. The CPU 11 reads the volume level corresponding to this search data with reference to the identification information storage unit 151 in order to consider the volume level in the weight determination process (step S134). The CPU 11 multiplies the read sound volume level by the weight corresponding to the search data (step S135). For example, the weight “3” of the search data “good” is multiplied by the volume level “1.0”, and the weight becomes “3.0”. In this embodiment, the sound volume level is multiplied, but it may be added.

  The CPU 11 determines whether or not weights have been calculated for all search data (step S136). If the CPU 11 has not calculated all the search data (NO in step S136), the CPU 11 proceeds to step S131 and repeats the processes in steps S131 to S136. For example, the weight calculation process for the search data “Kana” is subsequently performed. When the CPU 11 determines that the calculation has been performed for all the search data (YES in step S136), the CPU 11 calculates all the weight total values calculated in step S135 (step S137). For example, the search data “good” and “kana” have the weight “5.2”.

  Thus, the calculation of the weight based on the search data related to the audio data and the sound volume level is executed. Subsequently, a procedure of weight calculation processing in consideration of position information will be described. The CPU 11 refers to the identification information storage unit 151 and calculates the number of the same areas (step S138). In the example of FIG. 4, the area “JR Shibuya Station” is calculated as the same area number “2”, and the area “Subway Shimbashi Station” is calculated as the same area number “1”. The CPU 11 adds a weight according to the number of areas (step S139). That is, in the case of the user 0001 and the user 0002, the same area number is “2”, and the area number “2” is added to the weight obtained in step S137 to calculate the final weight. By executing this process for each user, the weights of all users are calculated. In the case of the user 0003, the number of identical areas is “1”, and the final weight is calculated by adding the number of areas “1” to the weight obtained in step S137. These calculated weights are stored in the weight field of the identification information storage unit 151 in association with the user ID. The weight may be determined based on at least the search data, and the volume level or the position information may be appropriately combined to improve the accuracy.

  FIG. 14 is a flowchart showing the procedure of the event determination process. CPU11 reads the weight of the user in the group which determines a restaurant from the identification information memory | storage part 151 (step S141). CPU11 extracts the audio | voice data corresponding to user ID more than predetermined weight (step S142). In this process, for example, a threshold value is set in advance and voice data of a user having a weight exceeding the threshold value is extracted, voice data of a user having the largest weight is extracted, or voice data of the top few percent of users is extracted. You may make it extract. In this example, the voice data of the user 0001 having the largest weight is extracted.

  The CPU 11 reads the search data corresponding to the extracted voice data from the identification information storage unit 151 (step S143), searches the weight database 153, and determines whether there is a condition corresponding to the search data (step S144). . If the CPU 11 determines that a condition corresponding to the search data exists (YES in step S144), the CPU 11 extracts an antonym of the search data according to the condition (step S145). The extraction of the opposite word is performed with reference to a dictionary database (not shown). Then, search data is regenerated according to the extracted antonym (step S146). In this example, a condition is described in the search data “dislike”, the antonym “spicy” of the previous search data “sweet” is extracted, and the search data “spicy” “thing” is regenerated.

  After the process of step S146 or in step S144, if the CPU 11 determines that there is no condition corresponding to the search data (NO in step S144), the weight field and area field of the identification information storage unit 151 are searched and the weight is The maximum user area is read (step S147). In the present embodiment, the user with the largest weight is the user 0001, and the area is “JR Shibuya Station”.

  The CPU 11 determines a restaurant from the restaurant database 152 based on the search data read in step S143 or the search data regenerated in step S146 and the area read in step S147 (step S148). Specifically, the CPU 11 extracts a restaurant that satisfies the search data and the area under the AND condition in the restaurant database 152. As a result, in this example, the restaurants “Spicy Curry”, “A Korean Restaurant”, “D Dandan Noodles”, and “F Thai Cuisine” that satisfy the search data “Spicy” and the area “JR Shibuya Station” under AND conditions are extracted. Is done.

  Further, the CPU 11 reads out access information corresponding to the determined restaurant from the access field of the restaurant database 152 (step S149). The CPU 11 determines the priority order of the restaurants determined in step S148 in ascending order of read access information (step S1410). In accordance with the determined priority order, the CPU 11 rearranges the restaurants determined in step S148 (step S1411). In this example, “very hot curry restaurant (1 minute)”, “D Dandan noodles (3 minutes)”, “F Thai food” (5 minutes) "and" A Korean restaurant (7 minutes) ".

  FIG. 15 is a flowchart showing a procedure for transmitting the determined restaurant information to the mobile phone 2. First, the CPU 11 reads out the restaurant determined in step S148 (step S151), and rearranges the restaurants according to the priority order in the same manner as the processing performed in step S1411 (step S152). The CPU 11 describes, for each restaurant, a hyperlink for accessing the Web page storing the detailed information (map, business hours, menu, etc.) of the rearranged restaurants (step S153).

  The CPU 11 reads position information (access information) and state information corresponding to the restaurant from the restaurant database 152 (step S154), and creates cHTML text including the sorted restaurant, hyperlink, position information, and state information (step S155). ). In this example, when the state information is “x”, a cHTML sentence in which the state information is displayed as “full” is described. The CPU 11 transmits cHTML text including the created restaurant and status information to the mobile phone 2 to the mail address of each user in the group (step S156). In the present embodiment, rearrangement processing is performed. However, in the case of a simple system, information on the determined restaurant may be transmitted without rearranging.

  The mobile phone 2 receives the transmitted cHTML text (step S157), and the CPU 21 of the mobile phone 2 displays the received cHTML text on the display unit 24 (step S158). As described above, when a plurality of users input their current feelings from the mobile phone 2 by voice, the server computer 1 displays the optimum restaurant including whether or not reservation is possible in consideration of the voice and position of the user, It is possible to display a restaurant determined in consideration of minority users.

Embodiment 2
FIG. 16 is a block diagram showing a configuration of the server computer 1 according to the second embodiment. The computer program for operating the server computer 1 according to the second embodiment can be provided by a portable recording medium 1A such as a CD-ROM, MO, or DVD-ROM as in the second embodiment. It is. Further, the computer program can be downloaded from a server computer (not shown) via the communication network N. The contents will be described below.

  A portable computer recorded with a computer program for storing voice data in a reader / writer (not shown) of the server computer 1 shown in FIG. 16, generating search data, determining weight, extracting voice data, and determining an event. The recording medium 1A (CD-ROM, MO, DVD-ROM or the like) is inserted, and this program is installed in the control program of the storage unit 15. Alternatively, such a program may be downloaded from an external server computer (not shown) via the communication unit 16 and installed in the storage unit 15. Such a program is loaded into the RAM 12 and executed. Thereby, it functions as the server computer 1 of the present invention as described above.

  The second embodiment is configured as described above, and the other configurations and operations are the same as those of the first embodiment. Therefore, corresponding parts are denoted by the same reference numerals, and detailed description thereof is omitted.

It is a schematic diagram which shows the outline | summary of the event determination system which concerns on this invention. It is a block diagram which shows the hardware constitutions of a server computer. It is a block diagram which shows the hardware constitutions of a mobile telephone. It is explanatory drawing which shows the record layout of an identification information storage part. It is explanatory drawing which shows the image of the screen displayed on the display part of a mobile telephone. It is explanatory drawing which shows the record layout of a restaurant database. It is explanatory drawing which shows the record layout of a weight database. It is explanatory drawing explaining the procedure of the production | generation of search data, and a weight determination process. It is explanatory drawing which shows the image of the search result list displayed on the display part of a mobile telephone. It is a flowchart which shows the process sequence at the time of memorize | storing audio | voice data. It is explanatory drawing which shows the example of the email which invites participation. It is a flowchart which shows the procedure of the production | generation process of search data. It is a flowchart which shows the procedure of a weight determination process. It is a flowchart which shows the procedure of an event determination process. It is a flowchart which shows the procedure at the time of transmitting the information of the decided restaurant to a mobile telephone. 6 is a block diagram illustrating a configuration of a server computer according to Embodiment 2. FIG.

Explanation of symbols

1 Server computer (voice data processing device)
1A Recording medium 2 Mobile phone (mobile terminal)
11 CPU (control unit)
13 Input unit 14 Display unit 15 Storage unit 16 Communication unit 21 CPU (Control unit)
23 Input Unit 24 Display Unit 25 Storage Unit 26 Communication Unit 28 Microphone 29 Speaker 151 Identification Information Storage Unit 152 Restaurant Database (Event Database)
153 Weight database 210 GPS receiver N Communication network S Restaurant determination system (event determination system)

Claims (10)

In the event determination method that processes received audio data and determines an event,
Storing voice data transmitted from a plurality of users in the identification information storage unit in association with the identification information of the users;
A generation step of generating a plurality of search data by the control unit based on the stored voice data;
A weight determination step of determining a weight of the voice data by the control unit based on the generated search data;
An extraction step of extracting voice data corresponding to identification information of a predetermined weight or more by the control unit;
An event determination method comprising: an event determination step of determining an event by the control unit using search data corresponding to the extracted voice data from an event database storing search data in association with an event. . In an audio data processing device that processes received audio data,
Means for storing voice data transmitted from a plurality of users in the identification information storage unit in association with the identification information of the users;
Generating means for generating a plurality of search data based on the stored voice data;
Weight determining means for determining the weight of the voice data based on the generated search data;
Extraction means for extracting voice data corresponding to identification information having a predetermined weight or more;
An audio data processing apparatus comprising: event determination means for determining an event from an event database storing search data in association with an event, using search data corresponding to the extracted audio data. Means for receiving location information of the user who transmitted the audio data;
Means for storing the received position information in the identification information storage unit in association with the identification information and the voice data;
3. The audio data processing apparatus according to claim 2, wherein the weight determination unit is configured to determine a weight of the audio data based on the search data generated by the generation unit and the stored position information. . The event database stores search data and position information in association with events,
Means for reading position information corresponding to the event determined by the event determination means from the event database;
The audio data processing apparatus according to claim 3, further comprising priority order determining means for determining a priority order of the event determined by the event determining means based on the read position information.   The weight determination unit is configured to determine a weight of the voice data based on a volume level of voice data stored in the identification information storage unit and search data generated by the generation unit. The audio data processing device according to any one of 2 to 4.   The weight determination means reads a weight corresponding to the search data generated by the generation means from a weight database storing weights in association with the search data, and the read weight and voice data stored in the identification information storage unit The audio data processing apparatus according to claim 2, wherein the weight is determined based on the frequency. In the event determination system comprised by the audio | voice data processing apparatus of Claim 2 or 3 connected to a portable terminal and this portable terminal via a communication network,
An event determination system comprising: means for transmitting an event determined by the event determination means to the portable terminal. In the event determination system comprised by the audio | voice data processing apparatus of Claim 4 connected to a portable terminal device and this portable terminal device via a communication network,
Means for rearranging the events determined by the event determining means according to the priority order of the events determined by the priority determining means;
Means for transmitting the rearranged event to the portable terminal. The event database stores state information indicating an event state,
9. The event determination system according to claim 7, wherein the audio data processing device further includes means for reading out state information corresponding to the event determined by the event determination means and transmitting the state information to the portable terminal. In a computer program that causes a computer to process received audio data and determine an event,
The control unit of the computer is caused to read the audio data from the identification information storage unit that stores the audio data transmitted from the plurality of users in association with the user identification information, and based on the read audio data, A generation step for generating search data;
A weight determination step of causing a control unit of a computer to determine a weight of the voice data based on the generated search data;
An extraction step for causing the control unit of the computer to extract audio data corresponding to identification information of a predetermined weight or more;
An event determination step of causing the control unit of the computer to determine an event from an event database storing the search data in association with the event, using the search data corresponding to the extracted voice data. program.

Images