Social network system

Description

CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims the priority benefit of U.S. provisional application No. 62/023,355, filed on Jul. 11, 2014 and titled “Active Social Network Football Helmet,” the disclosure of which is incorporated herein by reference.

BACKGROUND OF THE INVENTION

1. Field of the Invention

The present invention is generally related web publishing. More specifically, the present invention is related to modifying received audio speech data for automatic text publication on social media.

2. Description of the Related Art

Players, teams, and businesses currently use social media to increase their reach and communicate with fans to promote themselves, their views, products, and brands. Social media messages are commonly integrated into television broadcasts through commentary or displayed alongside live broadcasts in a portion of the display.

It is difficult, however, for athletes to send messages through social media during the course of a game because athletes do not have free use of their hands. An athlete cannot send, for example, a live comment regarding an event during the game because the athlete cannot leave the game to send a message through a phone. This limitation makes it difficult for players, teams, and businesses to fully leverage social media.

There is a need in the art for improved systems and methods for delivering real-time game commentary from players through social media.

SUMMARY OF THE PRESENTLY CLAIMED INVENTION

One exemplary method for sending social media messages describes receiving audio speech data through one or more microphones. The method also describes processing the audio speech data at a processing unit. The processing unit converts the audio speech data to text speech data. The method also describes comparing the text speech data to one or more databases. The one or more databases include one or more code words. The method also describes sending the processed speech data for output through social media. The processing unit routes text speech data for output through social media according to code words included in the text speech data.

One exemplary system for sending social media messages provides one or more microphones, a processing unit, and a processor. The one or more microphones receive audio speech data through one or more microphones. The processing unit processes the audio speech data and compares the text speech data to one or more databases. The processing unit converts the audio speech data to text speech data. The one or more databases include one or more code words. Execution of instructions stored in the memory by the processor performs a set of operations. The operations include sending the processed speech data for output through a social media interface. The processing unit routes text speech data for output through the social media interface according to code words included in the text speech data.

One exemplary non-transitory computer-readable storage medium is also described, the non-transitory computer-readable storage medium having embodied thereon a program executable by a processor to perform an exemplary method for sending social media messages. The exemplary program method describes receiving audio speech data. The program method also describes processing the audio speech data. The program method also describes converting the audio speech data to text speech data. The program method also describes comparing the text speech data to one or more databases. The one or more databases include one or more code words. The program method also describes sending the processed speech data for output through social media. The processing unit routes text speech data for output through social media according to code words included in the text speech data.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 illustrates a system for sending social media messages.

FIG. 2 illustrates database tables in a player data database, a catchword database, and a product insert database.

FIG. 3 illustrates a method for processing speech data.

FIG. 4 illustrates a method for processing text data.

DETAILED DESCRIPTION

The present invention includes systems and methods for sending social media messages without the need for keyboard inputs. A microphone captures live audio speech data and transmits the audio data to a processing unit. The processing unit converts the audio to speech data. The processing unit also removes censored words, emphasizes key words, and edits that data to include product and promotional messages where appropriate. The processing unit then uses code words contained in the speech data to send the speech data to the appropriate social media outlets for output.

Social messages can be sent from entertainment or cultural events that are presented at a theatre, gymnasium, stadium, or other facility to a group of people. Such events include a wide variety of sporting events such as football (American and Global), baseball, basketball, soccer, ice hockey, lacrosse, rugby, cricket, tennis, track and field, golf, cycling, motor sports such as automobile or motorcycle racing, horse racing, Olympic games, and the like; cultural events such as concerts, music festivals, plays, the opera, and the like; religious events; and more permanent exhibitions such as museum, historic home, and the like.

FIG. 1 illustrates a system 100 for sending social media messages. The system 100 includes a wearable item 105, a processing unit 130, the Internet 195, an internet server 190, and three databases 175, 180, and 185. As illustrated in FIG. 1, a microphone 120, radio transmitter 115, and an antenna 110 are connected to the helmet 105. The processing unit includes a radio receiver 135 and a text processing application 155. The radio receiver 135 includes an analog-to-digital converter 140 and a means for receiving one or more channels 145. The text processing application 155 includes a speech recognition unit 160, a player identification detection unit 165, and a catchword detection unit 170. The three databases 175, 180, and 185 include code words (not shown).

The microphones 120 can be acoustic-to-electric transducers for converting audio data into an electrical signal. The microphones 120 can be used with a wireless transmitter. The microphones can be wearable. The radio transmitter 115 is in communication with the microphone 120. The wearable items 105 can be sporting equipment used in the course of playing a sport, including protective equipment or non-protective equipment. The wearable items 105 can include helmets, protective padding, uniforms, jerseys, footwear, eyewear (e.g. glasses, face shields), or balls (e.g. football, baseball, soccer ball).

The processing unit 130 is in communication with the radio transmitter 115 through the antenna 110, wherein the radio transmitter 115 produces a radio transmission 125 for delivery to the processing unit 130. The processing unit 130 can be a personal computer, a desktop computer, or a server. The radio transmission 125 is a radio frequency signal carrying audio data. The radio transmitter 115 converts an electrical signal from the microphone 120 into a radio signal for transmission to the antenna 110. The radio transmitter 115 can be a one-way radio transmitter. The radio transmitters 115 can include at least one power source, a radio oscillator, a signal modulator, and a radio frequency amplifier. The radio transmitter 115 can be wireless or wearable. The antenna 110 can convert an electrical signal into radio waves for transmitting a radio-frequency audio signal. The processing unit is in communication with the server 190 through the Internet 195. The system 100 can automatically publish digital speech data to a website through the Internet 195. The server 190 is connected to the Internet 195 and hosts one or more remotely accessible web pages. The server can publish content received via the Internet 195 to social media websites such as Twitter or Facebook. The digital speech data can be representative of verbal commentary during a sporting event.

The radio receiver sends a digital audio signal 150 to the text processing application 155. The analog-to-digital converter 140 converts analog radio signal to digital audio signal. The radio receiver 135 receives radio transmissions 125 through one or more channels 145. The radio receiver 135 is a radio frequency receiver for receiving the radio transmission 125 from the radio transmitter 115. The one or more channels 145 are data parameters defining the channel through which the radio receiver 135 receives the radio transmission 125. The data parameters control or change the frequency monitored by the radio receiver 135. The one or more channels 145 are identified with a speaker, such as an athlete.

The speech recognition unit 160 includes a software program for translating spoken words to text. The speech recognition unit 160 may be an automatic speech recognition program. The speech recognition unit 160 converts the digital audio signal into text. The player identification detection unit 165 is a software program for determining the identity of a sports player by the channel associated to each of the one or more athletes. The catchword detection unit 170 is a software program for recognizing code words in the speech recognition unit output, wherein code words include catchwords and product words. The catchword detection unit modifies the speech recognition unit output.

The player data database 175, the catchword database 180, and the product insert database 185 may be relational databases such as Microsoft Access or Microsoft SQL Server or flat files, such as comma-separated value text files, where the flat files are compatible with applications such as Microsoft Office applications. The player data database 175 is a database of player speech data produced by the text processing application 155. The player data database 175 is a relational database with one or more data tables. Each of the one or more player data database data tables contains the speech recognition unit output and metadata associated with the speech recognition unit output. The catchword database 180 is a database of catchwords provided to the catchword detection unit 170. Each of the one or more catchword database data tables contains catchwords used to modify the text data. The product insert database 185 is a database of product words and sponsored words, wherein the sponsored words are associated with product words and the sponsored words are used to replace associated product words in the text data.

FIG. 2 illustrates database tables 200 in the player data database 175, the catchword database 180, and the product insert database 185. The processing unit 130 uses the player data database data table 210 to organize text speech data. The player data database table 210 organizes text data 225 according to time 215 and player identification 220. The timestamp for each text data record corresponds to when the system 100 created the text data record. Player identification 220 provides the identity of the speaker associated with the text data record. The player identification 220 can be the name of the sports player, the jersey number of the sports player, the channel identification associated with the speaker, or the frequency associated with the speaker. The speech recognition unit 160 outputs the text data 225.

The processing unit uses the catchword database 180 to modify text speech data. The catchword database table 230 includes product words 235, censor words 240, key words 245, and code words 250. The processing unit modifies the text speech data to remove censor words 240 listed in the database. Censor words 240 include obscene language and content prohibited by government agencies (such as the Federal Communications Commission). The processing unit modifies the text speech data to replace product words 235 with corresponding sponsored words 265 listed in the product insert table 255. Product words 235 include specific products, words associated with specific brands, or words associated with specific products. The processing unit further modifies the text speech data to emphasize key words 245 listed in the database. Key words include interjections and words that convey excitement. The processing unit routes modified speech data for output through social media according to code words 250 listed in the database. Code words 250 include words associated with posting messages to particular social media forums, as well as words indicating the beginning and end of messages.

The processing unit uses the product insert database 185 to modify text speech data. The product insert database table 255 includes product words 235 and sponsor words 265. The processing unit modifies the text speech data to replace product words 235 listed in the database with sponsored words 265 listed in the database. Product words 235 include specific products, words associated with specific brands, or words associated with specific products. Sponsored words 265 include words associated with advertising, endorsements, or promotional deals, as well as words for specific brands or marketing campaigns.

FIG. 3 illustrates a method 300 for processing speech data. The method begins at block 305, where the radio receiver 135 receives the radio transmission 125. The radio receiver 135 may receive radio transmissions 125 through multiple channels, and wherein the channels may be predefined and changed. At block 315, the radio receiver processes the radio transmission 125 using the analog-to-digital converter 140 to convert the radio transmission 125 into digital audio signal. At block 320, the text processing application 155 uses the speech recognition unit 160 to convert the digital audio signal to text data. The text processing application 155 may use a standard input/output stream. At block 310, the text processing application 155 uses the digital audio signal 150 and channel 145 information to identify the player. The player identification unit 165 then associates the text data with a player based on player information associated with the channel. The player identification unit 165 can compare the frequency of the digital audio signal with information regarding each player and the channel associated with each player. The text processing application 155 stores the text data produced by the speech recognition unit 160, player identity data produced by the player identification detection unit 165, and the current time in the player data database 175. At block 325, the text processing application 155 uses the catchword detection unit 170 to examine the text data for words stored in the catchword database 180 and product insert database 185 and process the text data according to the detected words. The method goes back to block 305 if the text data does not include code words used to route the text data for output through social media. If the text data includes one or more code words used to route the text data for output through social media, the method moves to block 330. The text processing application 155 can use a loop construct to compare each word of the text data to the code words 250. At block 330, the text processing application 155 extracts the text data for output. The text processing application 155 can select a series of words for extraction based on the code word used and the location of the code word. The text processing application 155 can select a series of words or characters starting with a code word 250 and a ending with code word 250. The text processing application can also select a series of words or characters between a first occurrence of a code word 250 and a second occurrence of a code word 250 in the text data. At block 335, the text processing application outputs the text data together with the player identification for publication through social media.

FIG. 4 illustrates a method 400 for processing text data. The method begins at block 410, where catchword detection unit 170 examines a record from the player database table 210.

At block 415, the catchword detection unit determines whether the text data contains censored words 240 listed in the catchword database table 230. The catchword detection unit can compare each word in the record with each censored word 240 listed in the catchword database table 230.

If the text data does not contain censored words 240, the method continues to block 408. If the text data contains censored words 240 listed in the catchword database table 230, the method continues to block 420. At block 420, censored words contained in the text data are replaced with redacted text or a placeholder. The method then continues to block 425.

At block 425, the catchword detection unit determines whether the text data contains product words 235 listed in the catchword database table 230. The catchword detection unit can compare each word in the record with each product word 235 listed in the catchword database table 230.

If the text data does not contain product words 235, the method continues to block 435. If the text data contains product words 235 listed in the catchword database table 230, the method continues to block 430. At block 430, product words contained in the text data are replaced with sponsored words listed in the product insert table 255. The method then continues to block 435.

At block 435, the catchword detection unit determines whether the text data contains key words 245 listed in the catchword database table 230. The catchword detection unit can compare each word in the record with each key word 245 listed in the catchword database table 230.

If the text data does not contain key words 245, the method continues to block 445. If the text data contains key words 245 listed in the catchword database table 230, the method continues to block 440. At block 440, key words contained in the text data are emphasized in the text data. The text processing application may insert markup language formatting commands before and after each key word to emphasize the key word. The method then continues to block 445.

At block 445, the processing unit 130 uploads the text data to the internet server 190 via the Internet 195. The processing unit 130 can upload the text data using a content submission application programming interface (API) provided by an operator of the internet server 190 to allow for direct publishing to a social media website. At block 450, the catchword detection unit increments to the next record in the player database table 210 and repeats the method, beginning again at block 304.

While various embodiments have been described above, it should be understood that they have been presented by way of example only, and not limitation. The present descriptions are not intended to limit the scope of the presently claimed invention or to limit the scope of embodiments of the presently claimed invention. The present descriptions are intended to cover alternatives, modifications, and equivalents consistent with the spirit and scope of the disclosure.