Obviousness

The obviousness of US patent 9116908B2 under 35 U.S.C. § 103 can be argued by combining existing prior art references and general knowledge prevalent at the time of the patent's priority date (March 11, 1999). For this analysis, the core inventive concept of US9116908B2 is taken from its "Summary of the Invention" section, as the claims themselves were not provided. The summarized method for accelerated data storage and retrieval includes the steps of:

1. Receiving a data stream at an input data transmission rate greater than a data storage rate of a target storage device.
2. Compressing the data stream at a compression ratio that provides a data compression rate greater than the data storage rate.
3. Storing the compressed data stream in the target storage device.
4. Retrieving the compressed data stream from the target storage device at a rate equal to a data access rate of the target storage device.
5. Decompressing the compressed data at a decompression ratio to provide an output data stream having an output transmission rate greater than the data access rate of the target storage device.

Combinations of Prior Art References and Explanation of Obviousness

A person having ordinary skill in the art (PHOSITA) in 1999 would have been motivated to combine the following elements to arrive at the invention claimed in US9116908B2:

Prior Art References:

1. US6195024B1 (Fallon), entitled "Content Independent Data Compression Method and System": This patent, filed on December 11, 1998, predates the priority date of US9116908B2 and is explicitly incorporated by reference into US9116908B2. It teaches "systems and methods for providing fast and efficient data compression using a combination of content independent data compression and content dependent data compression". Crucially, US9116908B2 itself states that the compression and decompression methods disclosed in US6195024B1 (via its application number US Ser. No. 09/210,491) "are suitable for compressing and decompressing data at rates which provide accelerated data storage and retrieval."

2. General Knowledge Regarding Data Storage Bandwidth Limitations: The "Background" section of US9116908B2 explicitly details the problem being addressed, stating that "existing memory storage devices severely limit the performance... suffer from significant seek-time access delays along with profound read/write data rate limitations" [Summary]. It highlights the disparity between modern computer bus speeds (e.g., PCI Bus at 264 MB/sec, internal local bus at 800 MB/sec) and typical magnetic disk drive speeds (e.g., 17.1 MB/sec) [Summary]. This clearly establishes that the problem of storage device bandwidth acting as an I/O bottleneck was well-recognized in the prior art.

3. General Knowledge Regarding the Use of Data Compression for Improved I/O Performance and Effective Bandwidth:

   • The background of US9116908B2 itself admits that "It is well known within the current art that data compression provides several unique benefits. First, data compression can reduce the time to transmit data by more efficiently utilizing low bandwidth data links. Second, data compression economizes on data storage and allows more information to be stored for a fixed memory size by representing information more efficiently." [Summary]
   • Further reinforcing this, prior art like the "Data Compression Abstract INTRODUCTION" document explicitly teaches that "Compressing a file to half of its original size is equivalent to doubling the capacity of the storage medium. It may then become feasible to store the data at a higher, thus faster, level of the storage hierarchy and reduce the load on the input/output channels of the computer system." This reference directly links data compression to reducing I/O load and facilitating faster storage, thereby increasing effective bandwidth. It also mentions that reducing transmitted data "increases the capacity of the communication channel," which is directly analogous to increasing effective bandwidth for data transfer.

Motivation for a PHOSITA to Combine the References:

A PHOSITA in 1999, confronted with the widely known problem of slow data storage devices creating I/O bottlenecks (as described in the background of US9116908B2), would have a clear motivation to apply existing and efficient lossless data compression techniques to overcome these limitations.

The motivation to combine these elements would stem from the established understanding that:

• Performance Gap: There was a significant and growing performance gap between computing components (CPUs, buses) and storage devices. This bottleneck needed to be addressed to improve overall system performance.
• Known Benefits of Compression for Speed: It was a known principle that data compression could effectively increase data transfer rates over limited bandwidth channels. The general knowledge articulated in the "Data Compression Abstract INTRODUCTION" specifically suggests that compression can "reduce the load on the input/output channels" and effectively increase "channel capacity". This provides a direct and explicit motivation for using compression not just for storage space, but for performance enhancement in I/O operations.
• Available High-Speed Compression: Fallon's US6195024B1 provided specific, high-speed lossless compression and decompression algorithms, which US9116908B2 itself deems "suitable" for accelerated data storage and retrieval. This demonstrated the technical feasibility of performing compression/decompression fast enough to be useful in a real-time acceleration context.

Application of the Combination to the Claimed Method:

Given this motivation, a PHOSITA would logically arrive at the method described in US9116908B2:

1. Receiving a data stream faster than the storage device can handle: Recognizing the bottleneck, the PHOSITA would seek a way to process this faster input for storage on the slower device.
2. Compressing the data stream at a sufficient ratio (Step 2) before storing it (Step 3): To accommodate an input data stream (Step 1) that is faster than the storage device's native rate, the PHOSITA would apply a lossless compression technique (from US6195024B1) to reduce the volume of data that needs to be physically written. Calculating the necessary compression ratio to ensure the effective storage rate (of the original data) matches or exceeds the input rate for continuous flow would be a straightforward engineering exercise.
3. Retrieving the compressed data (Step 4) and decompressing it at a sufficient ratio (Step 5): Similarly, to provide an output data stream faster than the retrieval rate of the storage device, the PHOSITA would decompress the retrieved compressed data using the high-speed lossless decompression techniques (from US6195024B1). The effective output data rate would then be the native retrieval rate multiplied by the decompression ratio, thus appearing "accelerated" to the receiving system. The necessary decompression ratio to meet or exceed a maximum accepted output rate for continuous, optimal flow would also be a matter of routine system design.

The use of buffering mechanisms (e.g., input buffer 15, buffer/counter module 30, output data buffer 70, as described in US9116908B2) to manage temporary mismatches in data rates between components is also a well-known technique in computer architecture and would be an obvious design choice for a PHOSITA implementing such a system.

In conclusion, the core method of US9116908B2—using high-speed lossless data compression and decompression to accelerate the effective bandwidth of data storage and retrieval when confronted with slower storage devices—would have been obvious to a PHOSITA by combining the specific lossless compression/decompression techniques of US6195024B1 with the widely understood problem of storage bottlenecks and the general principle that data compression can enhance I/O performance.