Apple's Siri may offer crowd-sourced answers to user queries
Apple's Siri may soon get more of a human touch as the Cupertino company is investigating the viability of using crowd-sourced information to broaden the virtual assistant's answer database.
Source: USPTO
Currently, Siri relies on data pulled from the Web and other online services, like Yahoo!, WolframAlpha and Bing, to answer user queries. While their databases are extensive, these partner services may not be able to handle nuanced or uncommon questions.
A patent filing published by the U.S. Patent and Trademark Office on Thursday reveals Apple is looking into the viability of crowd sourcing answers for certain questions that Siri fails to answer. Titled "Crowd sourcing information to fulfill user requests," the application is a primer on how the virtual assistant can request, gather and store data from a number of crowd sourcing, or "CS," information services.
As explained by the document, the a digital assistant requires a natural language processing system, knowledge base and artificial intelligence to function satisfactorily. Any of these facets can hinder operation and, in some cases, produce unsatisfactory answers. It is in these scenarios that a CS information service can be deployed.
For example, the CS module can be invoked as part of response failure mechanism that can be updated over a period of time to remedy a speech recognition problem. More commonly, the CS module can query a CS knowledge base to address questions previously unanswerable in real time.
According to the patent language, the external sources of information can include services that compile data from experts, general information sources found on the Web and various question-and-answer forums.
In some embodiments, the CS module provides a knowledge base filled with responses to questions that the system previously failed to answer correctly, thus building out an existing response database. Databases can include information from a single CS service, or an aggregate from multiple sources.
A variety of knowledge base types are mentioned, such as forums where a question can be posed to the general public. In other cases, specialized sources can be pinged with a question, examples of which include "expert forums, technical support forums, [and] fan-sites for particular subject matter."
Interestingly, the invention allows for both automated and manual invocation of the CS feature. For example, if the system detects a failure to respond, it can send the query off to generate answers over an extended period of time. On the other hand, a user can specifically request that a CS knowledge base be tapped for a specific answer.
As in existing Web-based CS databases, like Quora or Answers.com, individuals can identify themselves as experts and lend answers to queries posed by the CS module. Question handling may take place through a third party, or by the CS module itself. One embodiment even describes an "answer arena" where players win points or credits for providing correct answers to a user's questions.
As the technology deals with rare or personalized queries, users may have to wait some time for the system to return an answer as it collects the appropriate data. In some cases, the length of time could be weeks. When a satisfactory response is found, the digital assistant can relay that information to the user at an appropriate time, such as in between meetings.
Finally, feedback can be provided as to whether the response generated from the CS module was correct. If a user was satisfied with the information, it can be stored in the CS knowledge base, to be retrieved when a similar question is asked. If the CS module determines the user is not pleased with the response, it can either stop looking for an answer or escalate the question to another source, such as a human representative.
The rest of the filing details backend operations and a run down of virtual assistant technology, including natural speech recognition and reporting. In addition, privacy concerns are addressed regarding uploading of questions to the CS module.
It is unclear if Apple will implement the invention as part of Siri. Since its launch in 2011, each iteration of the virtual assistant has added a greater range of abilities and tie-ins with third-party services, though none have as direct a human element as described in Thursday's filing.
Apple's crowd sourcing patent application was first filed for in March and credits Thomas R. Gruber, Adam J. Cheyer and Donald W. Pitschel as its inventors.
Source: USPTO
Currently, Siri relies on data pulled from the Web and other online services, like Yahoo!, WolframAlpha and Bing, to answer user queries. While their databases are extensive, these partner services may not be able to handle nuanced or uncommon questions.
A patent filing published by the U.S. Patent and Trademark Office on Thursday reveals Apple is looking into the viability of crowd sourcing answers for certain questions that Siri fails to answer. Titled "Crowd sourcing information to fulfill user requests," the application is a primer on how the virtual assistant can request, gather and store data from a number of crowd sourcing, or "CS," information services.
As explained by the document, the a digital assistant requires a natural language processing system, knowledge base and artificial intelligence to function satisfactorily. Any of these facets can hinder operation and, in some cases, produce unsatisfactory answers. It is in these scenarios that a CS information service can be deployed.
For example, the CS module can be invoked as part of response failure mechanism that can be updated over a period of time to remedy a speech recognition problem. More commonly, the CS module can query a CS knowledge base to address questions previously unanswerable in real time.
According to the patent language, the external sources of information can include services that compile data from experts, general information sources found on the Web and various question-and-answer forums.
In some embodiments, the CS module provides a knowledge base filled with responses to questions that the system previously failed to answer correctly, thus building out an existing response database. Databases can include information from a single CS service, or an aggregate from multiple sources.
A variety of knowledge base types are mentioned, such as forums where a question can be posed to the general public. In other cases, specialized sources can be pinged with a question, examples of which include "expert forums, technical support forums, [and] fan-sites for particular subject matter."
Interestingly, the invention allows for both automated and manual invocation of the CS feature. For example, if the system detects a failure to respond, it can send the query off to generate answers over an extended period of time. On the other hand, a user can specifically request that a CS knowledge base be tapped for a specific answer.
As in existing Web-based CS databases, like Quora or Answers.com, individuals can identify themselves as experts and lend answers to queries posed by the CS module. Question handling may take place through a third party, or by the CS module itself. One embodiment even describes an "answer arena" where players win points or credits for providing correct answers to a user's questions.
As the technology deals with rare or personalized queries, users may have to wait some time for the system to return an answer as it collects the appropriate data. In some cases, the length of time could be weeks. When a satisfactory response is found, the digital assistant can relay that information to the user at an appropriate time, such as in between meetings.
Finally, feedback can be provided as to whether the response generated from the CS module was correct. If a user was satisfied with the information, it can be stored in the CS knowledge base, to be retrieved when a similar question is asked. If the CS module determines the user is not pleased with the response, it can either stop looking for an answer or escalate the question to another source, such as a human representative.
The rest of the filing details backend operations and a run down of virtual assistant technology, including natural speech recognition and reporting. In addition, privacy concerns are addressed regarding uploading of questions to the CS module.
It is unclear if Apple will implement the invention as part of Siri. Since its launch in 2011, each iteration of the virtual assistant has added a greater range of abilities and tie-ins with third-party services, though none have as direct a human element as described in Thursday's filing.
Apple's crowd sourcing patent application was first filed for in March and credits Thomas R. Gruber, Adam J. Cheyer and Donald W. Pitschel as its inventors.
Comments
Might go some way to making Siri genuinely useful for the average person, I wish they'd implement crowd sourcing in their maps app.
The POI data that they have is absolutely pitiful, at least in the UK.
I can imagine Siri dispensing advice on home remedies or some half-baked advice that results in embarrassment or worse. What if the crowd one is sourcing from is popular but wrong?
"My sources tell me the best thing to do is amputate immediately." ...or... "My sources indicate 9/11 was an inside job."
Ok, not bad. Could improve services yet further.
But I think personally Siri needs to prioritize a little. Start with bringing more languages as promised.
Sweden would very much like this!!
Also, I wonder how Siri results can be improved when the answer given results in a negative result long after the initial query? Context is everything in terms of forming a positive feedback loop. At what point will Siri retain a Time Machine-like record of our questions and answers so a user could say, "Siri, remember that address you gave me last week? It's been changed."
Siri: "Perhaps I misunderstood you"
Waiting for chinese spammers to leverage this ^^
Ha ha. True. But, that's the crowd part with some weighted authority. Should handle this situation for the largest questions. I look forward to naming myself the greatest mambo dancer in southern England. That would probably go uncorrected for a while.
Funny you say that ... My first reaction was to think ... 'yeah, great, because crowds always get it right ...' :rolleyes:
Having said that there are some uses of it. As you say, consultation with authoritative sources, say like 99% of scientist ... might be a good idea. 8-)
If this helps make Siri faster, then I'll actually start using the thing!
Apple should really be working hard in making Siri a WHOLE lot faster. Like Google or not, their Now service responds *instantly*, Apple should be reaching for that level of interaction. Without it, Siri is useless for me. I can't wait all day for it to respond.
Apple please make Siri faster!
If the wildly erroneous crowdsourced data in Gracenote and CDDB (and therefore, iTunes) are any example of crowdsourcing info, I want no part of it. When anyone with inaccurate information, whether of benevolent or malicious intent, lack of knowledge or lack of skill communicating (i.e., typing/spelling accurately) can easily contaminate a database, there are going to be huge problems.
Crowdsourcing could certainly be useful, but isn't it wide open to manipulation, hacking, and open warfare by opposing-opinion factions? Ever seen the back-and-forth warfare on Wikipedia, the ostensibly crowdsourced but "moderated" reference? Look at decades-old music on iTunes having the titles mangled, when they used to be correct and accurate. Same for cover art. At some point, someone has to be the ultimate arbiter of information accuracy. Who is that going to be?
An eight-year-old with an iDevice or computer can put up questionable "data." Is that appropriate? Is it helpful? Is it accurate and true? Remember that old rule of data processing: garbage in, garbage out.
Crowdsourcing reminds me of that old experiment where a chain of people repeat a phrase, whispered ear to ear, down the line, one person to the next, and the first person's version is compared with what version the last person heard/perceived. And there's generally some mismatch.
Even if crowdsourcing isn't a strictly linear flow of information, I don't trust the "crowd."