Method for matching queries with answer items in a knowledge base
A system for providing answers to questions presented in the form of electronic signals representing natural language words conveyed to said system by way of a network connected to a computer. The system includes a plurality of search indexes relating to a field of knowledge, each in a specific natural language. A store-house of natural words is associated with each one of the search indexes, and in which a list of natural words is maintained in an order reflecting the usage frequency of said words in that list. In addition, a language storehouse of natural words common to each of the search indexes associated each with a specific natural language. The search index includes a list of score ordered keywords, indexed answer items each associated with an internal list of references (ILOR) pointing to it, and a list of ordered numerical references associated with each of the ordered keywords. Each such reference represents quantitatively an association between the keyword and an indexed answer item.
1. A system for providing an automated response to a user natural language query (NLQ) made in connection to a product or service, said system comprising:
a computing platform including communication circuitry and processing circuitry to run computer executable code adapted to cause the computing platform to:
(a) receive digital data representing the user NLQ;
(b) search a knowledgebase for one or more match candidate knowledgebase entries for the NLQ;
(c) assign a weight value to each of some or all of the words in the one or more match candidate knowledgebase entries, wherein a weight value assigned to a given word of the match candidate entries is inversely related to a rate of occurrence of the given word in at least one knowledgebase;
(d) calculate a query significance value for each of some or all of the words in the one or more match candidate knowledgebase entries, wherein calculating the query significance value for a given word in a given match candidate entry includes dividing the weight value of the given word by a sum of weight values of a set of words in the given match candidate entry;
(e) calculate a match score between the NLQ and each of the one or more match candidate entries by performing for each of the one or more match candidate entries a mathematical operation using the query significance value of a word in the respective match candidate entry, which word has a corresponding word in the NLQ, and a query significance value of the corresponding word in the NLQ; and
(f) send and automated response to the user, including indications of one or more selected match candidate entries of the one or more match candidate entries, which selected match candidate entries are selected based on said match scores of the selected match candidate entries calculated by said computing platform.
2. The system according to claim 1 , wherein scoring a match further includes performing the mathematical operation using the query significance value of the word in the respective match candidate and the query significance value of the corresponding word in the NLQ for each word in the respective match candidate having a corresponding word in the NLQ.
3. The system according to claim 2 , wherein scoring a match further includes performing an aggregation of the results of the mathematical operations performed using the query significance values of each match candidate word having a corresponding word in the NLQ and the query significance values of corresponding NLQ words.
4. The system according to claim 3 , wherein scoring a match further includes comparing a result of the aggregation with a perfect match score.
5. The system according to claim 1 , wherein said computer executable code is further adapted to cause the computing platform to assign a weight value to each of some or all of the words in the NLQ and in the knowledgebase entry, wherein a weight value assigned to a given word of the entry is inversely related to a rate of occurrence of the given word in at least one knowledgebase.
6. The system according to claim 1 , wherein said computer executable code is further adapted to cause the computing platform to calculate a query significance value for each of some or all of the words in the NLQ, wherein calculating the query significance value for a given word includes dividing the weight value of the given word by a sum of weight values of a set of words in the NLQ.
7. A system for providing an automated response to a user natural language query (NLQ) made in regard to a subject, said system comprising:
a computing platform including communication circuitry, processing circuitry and computer executable code adapted to cause the computing platform to:
(a) receive digital data representing the user NLQ;
(b) assign a weight value to each of some or all of the words in the NLQ, wherein a weight value assigned to a given word of the user NLQ is inversely related to a rate of occurrence of the given word in at least one knowledgebase;
(c) calculate a query significance value for each of some or all of the words in the NLQ, wherein the query significance value for a given word is proportional to the weight includes dividing the weight value of the given word by sum of weight values of a set of words in the NLQ;
(d) search the at least one knowledgebase for one or more candidate matches, which candidate matches include words corresponding to words in the user NLQ; and
(e) score a match between the NLQ and each of the match candidates by performing a mathematical operation using the query significance value of words in the NLQ, which words have a corresponding word in the match candidates and a query significance value of the corresponding words in the match candidates;
(f) send and automated response to the user, including indications of one or more selected match candidates of the one or more match candidate entries, which selected match candidates are selected based on said match scores of the selected candidates calculated by said computing platform.
8. The system according to claim 7 , wherein scoring a match further includes performing the mathematical operation using the query significance value of a NLQ word and the query significance value of a corresponding match candidate word for each word in the NLQ having a corresponding word in the match candidate.
9. The system according to claim 8 , wherein scoring a match further includes performing an aggregation of the results of the mathematical operations performed using the query significance values of each NLQ word having a corresponding word in the match candidate and the query significance values of corresponding match candidate words.
10. The system according to claim 9 , wherein scoring a match further includes comparing a result of the aggregation with a perfect match score.