US5504884A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Information retrieval system
Assignee: Renesas Electronics Corp
•
Filing: 1993-02-05
•
Granted: 1996-04-02
•
Expires: 2013-02-05
Abstract
Abstract An information retrieval system allowing the user to build a database or to retrieve data therefrom based on vague retrieval-designating data without becoming aware of the database structure. The system comprises a neural network, a memory, an interface part and a CRT. The neural network stores data designating electronic still pictures contained in the memory. When data for designating retrieval are input, the interface part groups the data into such categories as the place where the desired picture was taken and the date on which it was taken, and supplies the neural network with the categorized input data. In turn, the neural network outputs by association the data corresponding to the input data. Given the data from the network, the memory outputs the relevant electronic still picture to the CRT for display.
Inventors
- 👤 Kazuo Kyuma
- 👤 Shuichi Tai
- 👤 Masaya Oita
- 👤 Nagaaki Ohyama
- 👤 Masahiro Yamaguchi
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-25 10:29
CPC Classifications
G; G06; G06F; G06F16/00; G06F16/90; G06F16/907; Y; Y10; Y10S; Y10S707/00; Y10S707/99931; Y10S707/99933; Y10S707/99935
Claims Analysis
Total Claims: 7
Claim 1
Independent Claim
127 words
An information retrieval system for retrieving data from a database, said system comprising: input means for admitting textual input information for designating retrieval of the data from the database, said textual input information being sufficient to at least partially correspond to said data; conversion means for categorizing said textual input information and for converting the categorized information into input data in bit strings; and a neural network, including at least an input layer for admitting said input data and an output layer for outputting output data indicating those data in said database which correspond to said textual input information, for changing, during a learning process, the weight of connection between said input layer and said output layer when said input data are admitted into said input layer.
Claim 2
Dependent Claim
127 words
An information retrieval system for retrieving data from a database, said system comprising: input means for admitting textual input information for designating retrieval of the data from the database, said textual input information being sufficient to at least partially correspond to said data; conversion means for categorizing said textual input information and for converting the categorized information into input data in bit strings; and a neural network, including at least an input layer for admitting said input data and an output layer for outputting output data indicating those data in said database which correspond to said textual input information, for changing, during a learning process, the weight of connection between said input layer and said output layer when said input data are admitted into said input layer.
Claim 3
Dependent Claim
50 words
An information retrieval system according to claim 1, wherein said input means can be used to input a degree of likelihood that the input information is correct and the conversion means provides the input layer of the neural network with a degree of excitation corresponding to said degree of likelihood.
Claim 4
Dependent Claim
74 words
An information retrieval system according to claim 1, wherein said neural network comprises: a data storage network for inputting the bit strings from said conversion means and correcting format by means of association; and a data retrieval network for providing for said data storage network a correction signal for changing a threshold value of output neuron of said data storage network when an output from said data storage network is judged to be inconsistent.
Claim 5
Dependent Claim
31 words
An information retrieval system according to claim 1, wherein the output layer of the neural network outputs a plurality of candidates of input data with degrees of likelihood of the candidates.
Claim 6
Dependent Claim
24 words
An information retrieval system according to claim 1, wherein the output layer of the neural network outputs a plurality of candidates of output data.
Claim 7
Dependent Claim
34 words
An information retrieval system according to claim 5, further comprising selecting means for selecting the plurality of candidates of output data in order responsive to a request on the input means by a user.
References Cited (Backward Citations)
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1999-04-02 | 1999-10-02 | 2000-04-02 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2003-04-02 | 2003-10-02 | 2004-04-02 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2007-04-02 | 2007-10-02 | 2008-04-02 | $7700.00 | Window Closed / Lapsed |