1. An interactive voice response (IVR) system configured to service calls from a plurality of callers, the IVR system comprising:
a dialog module configured to gather information for the IVR system,
wherein for a call from a caller, the dialog module is configured to gather at least some of the information used by the IVR system to service the call, wherein for an item of information in the at least some of the information used by the IVR system to service the call, the dialog module is configured to determine whether to gather the item of information from the caller or a source other than the caller based at least in part on data reflecting behavior by the caller in one or more prior calls with the IVR system, the IVR system further comprising:
a predictor module configured to predict, from the data, the item of information used by the IVR system to service the call, wherein the predictor module is further configured to output a confidence value associated with the item of information predicted by the predictor module.
2. The IVR system of claim 1,
wherein the dialog module is further configured to determine whether to gather the item of information from the caller or the source other than the caller based at least in part on output of the predictor module.
3. The IVR system of claim 2,
wherein the dialog module is further configured to determine whether to gather the item of information from the caller or the source other than the caller based at least in part on the confidence value.
4. The IVR system of claim 3, wherein:
when the confidence value is in a predetermined range, the dialog module is configured to gather the item of information from the output of the predictor module and prompt the caller to confirm the item of information.
5. The IVR system of claim 3, wherein:
when the confidence value is above a predetermined threshold, the dialog module is further configured to gather the item of information from the output of the predictor module and not prompt the caller.
6. The IVR system of claim 3, wherein:
when the confidence value is below a predetermined threshold, the dialog module is further configured to gather the item of information from the caller by prompting the caller to input the item of information.
7. The IVR system of claim 6, wherein the IVR system comprises an automatic speech recognition (ASR) engine,
wherein the ASR engine is configured to recognize speech, inputted by the caller in response to the prompting by the dialog module, based at least in part on the output of the predictor module.
8. The IVR system of claim 1, wherein the call is a telephone call.
9. A method for gathering information for an interactive voice response (IVR) system, wherein the IVR system is configured to service calls from a plurality of callers, the method comprising:
gathering, for a call from a caller, at least some of the information used by the IVR system to service the call, wherein for an item of information in the at least some of the information used by the IVR system to service the call, the method comprises determining whether to gather the item of information from the caller or a source other than the caller based at least in part on data reflecting behavior by the caller in one or more prior calls with the IVR system; and
predicting, from the data, the item of information used by the IVR system to service the call, wherein the predicting comprises outputting a confidence value associated with the predicted item of information.
10. The method of claim 9,
wherein the determining is performed based at least in part on output of the predicting, the output of the predicting comprising the item of information.
11. The method of claim 10, wherein:
the output of the predicting comprises the confidence value; and
the determining is performed based at least in part on the confidence value.
12. The method of claim 11, wherein
when the confidence value is in a predetermined range, the gathering further comprises gathering the item of information from the output of the predicting and prompting the caller to confirm the item of information.
13. The method of claim 11, wherein
when the confidence value is above a predetermined threshold, the gathering further comprises gathering the item of information from the output of the predicting and not prompting the caller.
14. The method of claim 11, wherein
when the confidence value is below a predetermined threshold, the gathering further comprises gathering the item of information from the caller by prompting the caller to input the item of information used by the IVR system to service the call.
15. The method of claim 14, further comprising:
recognizing speech, inputted by the caller in response to the prompting, based at least in part on the at least some of the predicted information.
16. The method of claim 9, wherein the call is a telephone call.
17. At least one non-transitory computer-readable storage medium storing processor-executable instructions that, when executed by at least one processor, cause the at least one processor to perform a method for gathering information for an interactive voice response (IVR) system, wherein the IVR system is configured to service calls from a plurality of callers, and wherein the method comprises:
gathering, for a call from a caller, at least some of the information used by the IVR system to service the call, wherein for an item of information in the at least some of the information used by the IVR system to service the call, the method comprises determining whether to gather the item of information from the caller or a source other than the caller based at least in part on data reflecting behavior by the caller in one or more prior calls with the IVR system; and
predicting, from the data, the item of information used by the IVR system to service the call, wherein the predicting comprises outputting a confidence value associated with the predicted item of information.
18. The at least one non-transitory computer-readable storage medium of claim 17, wherein
the determining is performed based at least in part on output of the predicting, the output of the predicting comprising the item of information.
19. The at least one non-transitory computer-readable storage medium of claim 18, wherein:
the output of the predicting comprises the confidence value; and
the determining is performed based at least in part on the confidence value.
20. The at least one non-transitory computer-readable storage medium of claim 19, wherein when the confidence value is in a predetermined range, the gathering further comprises gathering the item of information from the output of the predicting and prompting the caller to confirm the item of information.
21. The at least one non-transitory computer-readable storage medium of claim 19, wherein when the confidence value is above a predetermined threshold, the gathering further comprises gathering the item of information from the output of the predicting and not prompting the caller.
22. The at least one non-transitory computer-readable storage medium of claim 19, wherein when the confidence value is below a predetermined threshold, the gathering further comprises gathering the item of information from the caller by prompting the caller to input the item of information used by the IVR system to service the call.
23. The at least one non-transitory computer-readable storage medium of claim 22, wherein the method further comprises:
recognizing information, inputted by the caller in response to the prompting, based at least in part on the at least some of the predicted information.
24. The at least one non-transitory computer-readable storage medium of claim 17, wherein the call is a telephone call.
The claims below are in addition to those above.
All refrences to claim(s) which appear below refer to the numbering after this setence.
1. A method, comprising:
receiving a search query from a member of a social network; identifying two or more categories of data within the social network that include information satisfying the received search query;
ranking the identified two or more categories of data based on a selection criteria associated with the member of the social network and including a quality metric assigned to the information satisfying the received search query within the categories of data, the quality metric including:
a percentage of users who have previously selected the at least one search query suggestion; and
a percentage of users who have previously selected displayed results associated with the search query; and
presenting at least one search query suggestion based on the ranking of the identified categories of data within the social network.
2. The method of claim 1,
wherein ranking the identified two or more categories of data based on a selection criteria includes ranking the identified two or more categories of data based on member attributes associated with the member of the social network.
3. The method of claim 1,
wherein ranking the identified two or more categories of data based on a selection criteria includes ranking the identified two or more categories of data based on activities performed by the member within the social network.
4. The method of claim 1,
wherein ranking the identified two or more categories of data based on a selection criteria includes ranking the identified two or more categories of data based on activities associated with other members of the social network.
5. The method of claim 1, wherein ranking the identified two or more categories of data based on a selection criteria includes ranking the identified two or more categories based on historical user selections of the information within the two or more categories of data.
6. The method of claim 1, wherein ranking the identified two or more categories of data based on a selection criteria includes ranking the identified two or more categories based on a popularity assigned to the categories of data.
7. The method of claim 1, wherein ranking the identified two or more categories of data based on a selection criteria includes ranking the identified two or more categories based on a popularity assigned to the information satisfying the received search query within the categories of data.
8. The method of claim 1, wherein identifying two or more categories of data that include information satisfying the received search query includes querying an index associated with categories of data within a social network for information that satisfies the query.
9. The method of claim 1, wherein identifying two or more categories of data that include information satisfying the received search query includes querying an index associated with information stored by a social network for information that satisfies the query.
10. The method of claim 1, wherein identifying two or more categories of data that include information satisfying the received search query includes a member category of data and a company category of data.
11. The method of claim 1, wherein identifying two or more categories of data that include information satisfying the received search query includes a jobs category of data and a posts category of data.
12. A system, comprising:
a query module to receive a search query from a member of a social network;
an identification module to identify two or more categories of data within the social network that include information satisfying the received search query;
a category ranking module to rank the identified two or more categories of data based on a selection criteria associated with the member of the social network and including a quality metric assigned to the information satisfying the received search query within the categories of data, the quality metric including:
a percentage of users who have previously selected the at least one search query suggestion; and
a percentage of users who have previously selected displayed results associated with the search query; and
a suggestion module to present at least one search query suggestion based on the ranking of the identified categories of data within the social network.
13. The system of claim 12, wherein the suggestion module is to present a list of search query suggestions proximate to a search field of a user interface that received the search query, wherein the presented list includes a first suggestion associated with a higher ranked category of data proximate to the search field and a second suggestion associated with a lower ranked category of data proximate to the first suggestion.
14. The system of claim 12, wherein the suggestion module is to present a list of search query suggestions from a highest ranked category of data proximate to a search field of a user interface that received the search query.
15. The system of claim 12, wherein the query module is to receive a string of characters representing a partial search query within a search field of a user interface that received the search query; and
wherein the suggestion module is to complete the partial search query with a search query suggestion based on information satisfying the received search query from a highest ranked category of data.
16. The system of claim 12, wherein the query module is associated with a social network service that supports a social network; and
wherein the category ranking module is to rank the identified two or more categories of data based on a selection criteria associated with a member of a social network that submitted the search query.
17. The system of claim 12, wherein the query module is associated with a social network service that supports a social network; and
wherein the category ranking module is to rank the identified two or more categories of data based on attributes associated with a member of a social network that submitted the search query.
18. A non-transitory machine-readable medium whose contents, when executed by a computing system, cause the computing system to perform operations, comprising:
receiving a search query from a member of a social network;
identifying two or more categories of data within the social network that include information satisfying the received search query;
ranking the identified two or more categories of data based on a selection criteria associated with the member of the social network and including a quality metric assigned to the information satisfying the received search query within the categories of data, the quality metric including:
a percentage of users who have previously selected the at least one search query suggestion; and
a percentage of users who have previously selected displayed results associated with the search query; and
presenting at least one search query suggestion based on the ranking of the identified categories of data within the social network.
19. The non-transitory machine-readable medium of claim 18, wherein the social network is a professional social network; and
wherein identifying two or more categories of data within the social network that include information satisfying the received search query includes identifying a first category of data that includes member profile information and a second category of data that includes company profile information.
20. The non-transitory machine-readable medium of claim 18, wherein the social network is a professional social network; and
wherein identifying two or more categories of data within the social network that include information satisfying the received search query includes identifying a first category of data that includes job listing information and a second category of data that includes informational post information.