1. A normalization system, comprising:
a processor;
a memory communicatively coupled to the processor, the memory having stored therein computer-executable instructions to implement the system, including:
an interface component that processes questions posed by users, the questions corresponding to a heterogeneous knowledge base;
a dialog component that requests users to reformulate questions based upon a cost-benefit analysis;
a normalization component that applies a utility model that predicts accuracy results to provide a regularized understanding of the knowledge base based on at least one of the processed questions or the reformulated questions; and
an answer composer component that employs the predicted accuracy of results to generate answers to the processed questions.
2. The system of claim 1, the utility model dynamically controls extraction of previously unknown or disassociated information from the knowledge base.
3. The system of claim 1, the utility model controls a number of queries submitted to the knowledge base given decision-theoretic considerations.
4. The system of claim 1, the knowledge base includes at least one of a local database, a file, a directory, an electronic encyclopedia, a dictionary, a remote database, or a remote web site.
5. The system of claim 1, the utility model applies a cost-benefit analysis to dynamically control the number and types of attempts made to acquire information or answers from the knowledge base in response to a question or questions.
6. The system of claim 5, the utility model includes an analysis of the costs of searching for information versus the benefits of obtaining more accurate answers to questions.
7. The system of claim 1, the cost-benefit analysis factors a benefit of reformulating a question versus expending effort on processing a query that is expensive in terms of searching for information from the knowledge base or is likely to yield inaccurate results.
8. The system of claim 7, the cost-benefit analysis factors a cost of delay resulting from reformulating the query and a likelihood that a reformulation would lead to an improved result.
9. The system of claim 1, further comprising a preference component that enables users to assess or select various parameters that influence the utility model.
10. The system of claim 9, the preference component processes at least one of a user setting for a cost, a value, or a language preference.
11. The system of claim 10, the preference component includes a model where a user assesses a parameter v, indicating a dollar value of receiving a correct answer to a question, and where a parameter c represents a cost of each query rewrite submitted to a search engine.
12. The system of claim 11, further comprising a value of receiving an answer expressed as a function of details of a current context, the value of the answer is linked to at least one of a type of question, an informational goal, or a time of day for a user.
13. The system of claim 11, further comprising determining a cost of submitting queries as a function of at least one of a current load sensed on a search engine or the numbers of queries being submitted by a user’s entire organization to a third-party search service.
14. The system of claim 13, further comprising determining the costs non-linearly with increasing numbers of queries.
15. A method to normalize a database, comprising:
employing a processor executing computer executable instructions embodied on a computer readable storage medium to perform the following acts:
receiving a question from a user automatically forming a set of queries from the question received from the user, each query is assigned a different weight;
performing a cost-benefit analysis on the set of queries to generate a query subset, wherein the cost-benefit analysis factors cost of a quantity of queries to include in the query subset versus the accuracy of the results returned from the quantity of queries included in the query subset;
executing the query subset on the database to provide a set of results; and
providing an answer to the user based upon the set of results.
16. The method of claim 15, further comprising automatically ranking the set of queries in an order of likelihood of providing a suitable answer.
17. The method of claim 15, further comprising automatically training at least one model to generate the query subset.
18. The method of claim 15, further comprising submitting the query subset to at least one search engine.
19. The method of claim 18, further comprising receiving the set of results from the at least one search engine and automatically composing the answer.
20. A system to facilitate database normalization, comprising:
a processor;
a memory communicatively coupled to the processor, the memory having stored therein computer-executable instructions to implement the system, including:
means for receiving a question from a user
means for automatically forming a set of queries from the question received from the user;
means for generating query subset from the set of queries, wherein the means for generating the query subset dynamically determines a quantity of queries from the set of queries to include in a query subset based upon a cost-benefit analysis that factors cost of the quantity of queries to include in the query subset versus the accuracy of the results returned from the quantity of queries included in the query subset;
means for executing the query subset on the database to provide a set of results; and
means for providing an answer to the user based upon the set of results.
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 signal processing system comprising:
a pattern biasing look-ahead delta sigma modulator, the pattern biasing look-ahead delta sigma modulator comprising:
a quantizer to determine a quantization output value from a selected output candidate vector, wherein the output candidate vector is selected from a set of output candidate vectors and at least one member of the set of output candidate vectors is biased to alter a probability of the biased output candidate vectors being selected by the quantizer.
2. The signal processing system of claim 1 wherein the quantizer comprises a best match generator to determine a best match between an input signal vector and a set of output candidate vectors, wherein at least one of the output candidate vectors is biased to alter a probability of the biased output candidate vector(s) being selected as the best match to the input signal vector.
3. The signal processing system of claim 2 further comprising:
a filter to filter the input signal vector and each output candidate vector; and
wherein the best match between the input signal vector and a set of output candidate vectors is determined from the lowest power between a filtered input signal vector and each respective filtered output candidate vector.
4. The signal processing system of claim 1 further comprising:
a quantizer to quantize the input signal vector using the output candidate vector that best matches the input signal vector.
5. The signal processing system of claim 1 wherein each biased output candidate vector is biased using a bias factor multiplier.
6. The signal processing system of claim 1 wherein each biased output candidate vector is biased using a biasing factor, and a value of the bias factor is chosen to alter the probability of a selected biased output candidate vector sufficiently to allow detection of the altered probability while causing at most an insignificant change in signal-to-noise ratio.
7. The signal processing system of claim 1 further comprising:
a detector to detect biasing of an output signal derived from the quantized input signal, wherein the output signal is biased in accordance with selection by the quantizer of at least one biased output candidate vector.
8. The signal processing system of claim 1 wherein at least one of the biased output candidate vectors is chosen for biasing on the basis that each output candidate vector chosen for biasing is more densely compressible than substantially similar output candidate vectors.
9. The signal processing system of claim 1 wherein at least one biased output candidate vector has a known probability of selection by the quantizer relative to a probability of selection of another output candidate vector.
10. The signal processing system of claim 1 wherein to alter a probability of the biased output candidate vector(s) being selected comprises to increase the probability of the biased output candidate vector(s) being selected.
11. The signal processing system of claim 1 further comprising:
signal processing and recording equipment to process output data from the quantizer and record the processed output data on storage media.
12. The signal processing system of claim 1 wherein the input signal comprises audio input signal data.
13. The signal processing system of claim 1 wherein each output candidate vector includes a potential current quantization output value and at least one potential future quantization output value.
14. A method of processing an input signal with a look-ahead delta sigma modulator using at least one biased output candidate vector, wherein the look-ahead delta sigma modulator has a look-ahead depth greater than or equal to 2, the method comprising:
biasing at least one output candidate vector with a bias factor that alters a probability of each biased output candidate vector being selected by a quantizer to generate quantization output data.
15. The method of claim 14 wherein biasing at least one output candidate vector further comprises:
biasing output candidate vectors on the basis that each output candidate vector chosen for biasing is more densely compressible than substantially similar output candidate vectors.
16. The method of claim 14 wherein biasing at least one output candidate vector further comprises:
biasing an output candidate vector having a known probability of selection by the quantizer relative to a probability of selection of another output candidate vector.
17. The method of claim 14 wherein biasing at least one output candidate vector using a bias factor comprises multiplying each biased output candidate vector by the bias factor.
18. The method of claim 14 wherein the bias factor is chosen to alter the probability of a selected biased output candidate vector sufficiently to allow detection of the altered probability while causing at most an insignificant change in signal-to-noise ratio.
19. The method as in claim 14 wherein the input signal data sample comprises audio input signal data.
20. The method of claim 14 further comprising:
quantizing the input signal using a set of output candidate vectors that includes the biased output candidate vector.
21. The method as in claim 20 further comprising:
recording quantized input signal data on storage media.
22. A signal processing system comprising:
a detector to receive a first signal and to detect an outcome probability of prescribed bit patterns, wherein the outcome probability of the prescribed bit patterns is determined by biasing prescribed output candidate patterns used by a look-ahead delta sigma modulator to generate a second signal from which the first signal is derived.
23. The signal processing system as in claim 22 wherein the first signal includes audio data content.
24. An apparatus to process an input signal, the apparatus comprising:
means for biasing at least one output candidate vector with a bias factor that alters a probability of each biased output candidate vector being selected by a quantizer to generate quantization output data, wherein each output candidate vector includes a potential current output value and at least one future quantization output value; and
means for quantizing the input signal using a set of output candidate vectors that includes the biased output candidate vector.