Skip links

Analysis for your idea.

The new way to analyze your idea and discover its novelty and position in the IP landscape.

LOCI lets you take your invention idea, input it into the Loci platform for analysis, and then get a report that analyzes the product or service and sets a score that helps you understand how novel or unique your idea is.

Stewart Rogers, VentureBeat

Let LOCI Score guide your next steps.

Your LOCI Score is a quantitative representation of how unique or patentable your idea *may* be. Here at LOCI, we call this ‘novelty.’

Score Ranges and Meanings:

  • 1-40: A score in this range is BAD. It indicates that your invention/idea heavily overlaps another existing patent and may indicate plagiarism.
  • 40-70: A score in this range is AVERAGE. It indicates that your invention/idea *may* be patentable and is fairly average when compared with the novelty of other ideas in our database.
  • 70-90: A score in this range is GOOD. We like to call this our SWEET SPOT. It indicates that you’ve represented your ideas sufficiently and that there is novelty worthy of patentability.
  • 90-100: A score in this range is *potentially* GOOD. It indicates a high level of novelty; however, the idea may be so novel that it could be unpatentable and may not work.

Believe it or not, you don’t want a 100% on this test! These are the existing patents most similar to the idea you’ve submitted for analysis. Therefore, please note that in this section, it is better to have an overall lower average matching percentage than receiving a higher percentage on related documents.

Using this Loci Score, you can determine next steps for what you want to do with your idea. Next steps will be different for everyone, so below you will find some suggestions based on the score ranges.

  • 1-40: (BAD) Suggested next steps include: 1) research the inventions that came back with the highest percentage matching, 2) identify where the overlaps are, and 3) consider rewriting the description of your idea.
  • 40-70: (AVERAGE) Suggested next steps include: 1) research all related documents AND classification codes, 2) identify which classification your idea best fits, and 3) review alternate classifications for your idea and see if there is a unique use case that you hadn’t already considered.
  • 70-90: (GOOD) Suggested next steps include: 1) use and review the top related documents to identify where your prior art is, 2) prepare to stake your idea on the blockchain through our system, and 3) consider filing for a patent.
  • 90-100: (*potentially* GOOD) Suggested next steps include: 1) identify if your idea is actually feasible/possible, 2) identify that the idea isn’t blocked from being patented, and if these queries are successful, 3) consider staking your idea on the blockchain and/or filing a patent.
  • 80% and higher: This matches too closely to your submission; therefore, your submission is in danger of being considered plagiarism if you proceed in the patenting process.
  • 50-80%: This is a close match and is indicative of strong prior art.
  • 30-50%: This is a fairly close match and is indicative of good prior art.
  • 0-30%: This match may include some related prior art, but it’s unlikely to be useful.

These are the classification codes (CPCs) that best fit your idea.These codes help identify where inventions fit in the world of innovation. Not only is this useful information to know where your idea belongs, but perhaps, more importantly, for you to consider other possible use cases that may apply to your idea.

Use a few of our examples.

Completely new to LOCI Search and Invention Analysis? Don’t have an idea to try? No worries! We’ve got you covered with a few example ideas.

LOCI Score ~ 82

Short Description

We propose an alternative generator architecture for generative adversarial networks, borrowing from style transfer literature. The new architecture leads to an automatically learned, unsupervised separation of high-level attributes (pose and identity when trained on human faces) and stochastic variation in the generated images (freckles, hair), and it enables intuitive, scale-specific control of the synthesis. The new generator improves the state-of-the-art in terms of traditional distribution quality metrics, leads to demonstrably better interpolation properties, and also better disentangles the latent factors of variation. To quantify interpolation quality and disentanglement, we propose two new, automated methods that are applicable to any generator architecture. Finally, we introduce a new, highly varied and high-quality dataset of human faces. Our generator embeds the input latent code into an intermediate latent space, which has a profound effect on how the factors of variation are represented in the network. The input latent space must follow the probability density of the training data, and we argue that this leads to some degree of unavoidable entanglement. Our intermediate latent space is free from that restriction and is therefore allowed to be disentangled. As previous methods for estimating the degree of latent space disentanglement are not directly applicable in our case, we propose two new automated metrics — perceptual path length and linear separability — for quantifying these aspects of the generator. Using these metrics, we show that compared to a traditional generator architecture, our generator admits a more linear, less entangled representation of different factors of variation. The architecture makes it possible to control the image synthesis via scale-specific modifications to the styles. We can view the mapping network and affine transformations as a way to draw samples for each style from a learned distribution, and the synthesis network as a way to generate a novel image based on a collection of styles. The effects of each style are localized in the network, modifying a specific subset of the styles can be expected to affect only certain aspects of the image.

Purpose

GANs for Blending Facial Recognition features to Unlock (hack) a Smartphone(LOCIScore ~ 82)Short DescriptionWe propose an alternative generator architecture for generative adversarial networks, borrowing from style transfer literature. The new architecture leads to an automatically learned, unsupervised separation of high-level attributes (pose and identity when trained on human faces) and stochastic variation in the generated images (freckles, hair), and it enables intuitive, scale-specific control of the synthesis. The new generator improves the state-of-the-art in terms of traditional distribution quality metrics, leads to demonstrably better interpolation properties, and also better disentangles the latent factors of variation. To quantify interpolation quality and disentanglement, we propose two new, automated methods that are applicable to any generator architecture. Finally, we introduce a new, highly varied and high-quality dataset of human faces. Our generator embeds the input latent code into an intermediate latent space, which has a profound effect on how the factors of variation are represented in the network. The input latent space must follow the probability density of the training data, and we argue that this leads to some degree of unavoidable entanglement. Our intermediate latent space is free from that restriction and is therefore allowed to be disentangled. As previous methods for estimating the degree of latent space disentanglement are not directly applicable in our case, we propose two new automated metrics — perceptual path length and linear separability — for quantifying these aspects of the generator. Using these metrics, we show that compared to a traditional generator architecture, our generator admits a more linear, less entangled representation of different factors of variation. The architecture makes it possible to control the image synthesis via scale-specific modifications to the styles. We can view the mapping network and affine transformations as a way to draw samples for each style from a learned distribution, and the synthesis network as a way to generate a novel image based on a collection of styles. The effects of each style are localized in the network, modifying a specific subset of the styles can be expected to affect only certain aspects of the image. PurposeTo see the reason for this localization, let us consider how the AdaIN operation first normalizes each channel to zero mean and unit variance, and only then applies scales and biases based on the style. The new per-channel statistics, as dictated by the style, modify the relative importance of features for the subsequent convolution operation, but they do not depend on the original statistics because of the normalization. Thus each style controls only one convolution before being overridden by the next AdaIN operation. There are many aspects in human portraits that can be regarded as stochastic, such as the exact placement of hairs, stubble, freckles, or skin pores. Any of these can be randomized without affecting our perception of the image as long as they follow the correct distribution. Consider how a traditional generator implements stochastic variation. Given that the only input to the network is through the input layer, the network needs to invent a way to generate spatially-varying pseudorandom numbers from earlier activations whenever they are needed. This consumes network capacity and hiding the periodicity of generated signal is difficult — and not always successful, as evidenced by commonly seen repetitive patterns in generated images. Our architecture sidesteps these issues altogether by adding per-pixel noise after each convolution. Stochastic realizations of the same underlying image are produced using our generator with different noise realizations. We can see that the noise affects only the stochastic aspects, leaving the overall composition and high-level aspects such as identity intact. We further illustrate the effect of applying stochastic variation to different subsets of layers. Since these effects are best seen in animation, please consult the accompanying video for a demonstration of how changing the noise input of one layer leads to stochastic variation at a matching scale. We find it interesting that the effect of noise appears tightly localized in the network. We hypothesize that at any point in the generator, there is pressure to introduce new content as soon as possible, and the easiest way for our network to create stochastic variation is to rely on the noise provided. A fresh set of noise is available for every layer, and thus there is no incentive to generate the stochastic effects from earlier activations, leading to a localized effect.

Essential Function

Many mobile devices have a lock mode. The lock mode may be used to prevent inadvertent operation of a touch screen display, e.g., while the device is in a user’s pocket or purse or when another object is placed against the device. The lock mode may also be used to prevent an unauthorized person from using the device. Generally, the device is programmed to enter the lock mode when a user presses a specific button or a series of buttons or when it has been idle for a certain period of time. When a user desires to use a device that is locked, the user will typically be required to drag a slide bar, press a specific button or a series of buttons (e.g., to enter a password) to unlock the device. However, a user may find these steps inconvenient and time consuming. For example, a user may be reading a document using the device when the device detects that it has been idle for a certain period of time. In this case, the device will automatically enter the lock mode where it turns off or dims its display screen, and the user will be required to unlock the device before being able to resume reading the document. In another example, a user may be prone to forgetting the password needed to unlock the device. As a result, the user may decide to configure the device so that it does not automatically lock. If she then forgets or chooses not to manually lock her device, that leaves the device susceptible to inadvertent operation or unauthorized use.

Composition

As electronic commerce and information becomes more prevalent in our society, security issues have become an ongoing and important challenge. Such challenges exist both in peoples’ business and in home environments. For instance, in business environments, security is required for transactions such as banking at an ATM, purchasing goods with a credit card, or downloading secure data from the Internet. Similarly, in some households it may be desirable to prevent children from viewing undesirable material on the internet or TV. In order to provide security in such environments, the particular systems need to correctly establish the identity of the participants. A traditional method of establishing identity is through the use of passwords, such as a PIN number. Unfortunately, because passwords can be forgotten, stolen, disseminated, etc., they provide only a limited form of security and can be readily defeated. In order to overcome such limitations, recent security developments have focused on “biometrics,” which is a term that describes automated methods of establishing a person’s identity from their unique physiological or behavioral characteristics. Fingerprinting, retina scans and handwriting recognition are all examples of biometrics that can or have been used to establish identity. Unfortunately, most security systems that use biometric applications not only require specialized hardware (e.g., a retinal scanner), but may also be seen as intrusive to one’s personal privacy. One form of biometric security that is relatively non-intrusive involves facial recognition, in which an image of a person’s face can be digitally compared to a previously stored image. As disclosed, a stored reference face, which comprises facial images characterized as a set of eigenvectors or “eigenfaces,” can be used to identify or authenticate an individual.

End Result

In an embodiment of the invention, a mobile device is configured to automatically lock based on determining that a user’s face is no longer present in images captured by the device’s built-in camera. For instance, consider that the device is initially unlocked. In that state, a built-in camera captures one or more images, and the images are then analyzed to determine whether a user’s face is present therein. If a user’s face is not present in the images captured over a predetermined amount of time, the device automatically locks. Thus, the device is automatically locked when it determines that no user is currently using the device without having to wait for an idle timer to expire or a manual switch off by the user. The camera capturing and face recognition processing may be triggered by the device having detecting that it has been motionless for a threshold period of time. In another embodiment, a mobile device is configured to automatically unlock. Consider that the device is initially locked. In that state, the camera captures an initial image. When movement of the device is detected, the camera captures a new image. The device then determines whether it has moved to a use position (i.e., a position that indicates that a user is likely to want to use the device) by comparing the new image with the initial image. If the device has moved to a use position, the camera captures a subsequent image, and the subsequent image is analyzed to detect a user’s face. If a user’s face is detected in the subsequent image, the device is automatically unlocked. This unlocks the locked device without requiring the user to press a sequence of buttons (e.g., to enter a password) each time the user wants to use the device. The above summary does not include an exhaustive list of all aspects of the present invention. It is contemplated that the invention includes all systems and methods that can be practiced from all suitable combinations of the various aspects summarized above, as well as those disclosed in the Detailed Description above and particularly pointed out in the Short Description. Such combinations have particular advantages not specifically recited in the above summary.

LOCI Score ~ 65

Short Description

The present invention is a remotely piloted aircraft, or drone, that was originally designed to be an operable aircraft and accommodate a pilot as necessary. The related art of drone design and development has typically adopted two distinct approaches. The first approach, similar to the present invention, is to convert an existing aircraft into a drone. Traditional aircraft to drone conversions have required extensive modifications to the existing aircraft. The development of additional and unique hardware and software systems, both on the aircraft and in a ground station are often required. Further, many aircraft to drone conversions also require the development of new or modified aircraft control laws. These controls laws, or algorithms, are part of the additional hardware/software systems on board the drone and are used to govern the drone operations. Due primarily to the aforementioned modifications, aircraft to drone conversions often become expensive and technically complex.

Purpose

Because aircraft cockpits and controls are designed for certain human population size range, a generic set of actuators are used which provide full range control actuation in any fighter or attack aircraft, in essence replacing the pilot. The generic Drone Control System would therefore be, with the exception of several minor elements, fully useful in and transferable to many aircraft types. No permanent modifications to the existing aircraft would be required. This in turn, would allow the aircraft to remain fully man-rated with no system or performance degradation.

The telemetered flight command signals from the ground station are processed on the aircraft in order to control the mechanical actuators. The processing of the telemetered flight command signals is done with an actuator control system in a manner so that the mechanical actuators exactly replicate the original controls movements of the support equipment in the ground station. The drone aircraft response and handling qualities are therefore exactly like those of this aircraft before droning. The primary difference is the replacement of pilot with a set of mechanical actuators.

The drone aircraft response is recorded on a video camera mounted at eye level in the cockpit of the air vehicle. The video camera is focused on essentially aircraft attitude and performance instruments. These aircraft attitude and performance instruments (not shown), as in normal aircraft operations, indicate aircraft performance. The video images of the aircraft attitude and performance information is then captured and the corresponding signals are telemetered to the ground station rather than digital telemetered readings from the instruments themselves. The above mentioned video images are transmitted to the ground station via standard video telemetry techniques.

Essential Function

The present invention relates to a Drone Control System, and more particularly, a method to remotely pilot an air vehicle. A drone is a pilotless aircraft operated by remote control. Drones are used in many military applications as aerial targets and for other purposes such as reconnaissance when ground mobility is low.

Composition

The Drone Control System of the present invention is essentially comprised of a ground station and an air vehicle. The air vehicle in the disclosed Drone Control System is an operable aircraft. The ground station in the present inventions includes a replicated cockpit of the operable aircraft with the identical controls as are found on the operable aircraft. The only difference is the replacement of the pilot with a set of mechanical actuators. Altitude and performance information of the aircraft will be telemetered using a video link, rather than telemetered readings from the instrument themselves. The mobile camera device, comprising a processor and a camera, is located within the vehicle or attached to the vehicle for taking an image or video within or outside the vehicle. The transmitter or transmitting transceiver is in communication with the mobile camera device for transmitting the image or the video taken by the mobile camera device.

End Result

There have been no generic drone conversion kits that could be simply used on multiple types of aircraft. Likewise, once an aircraft has been converted to a drone using conventional methods, it is impractical and cost prohibitive to convert the drone back to an operable aircraft due to the fact that the modifications were so extensive. That is to say, there are no known removable and transferrable aircraft to drone conversion packages which would simplify the conversion process. The second approach to the design and development of drones is to design and manufacture the drone from scratch. These vehicles are thus not designed for a pilot on board the vehicle. These vehicles are commonly known as Remotely Piloted Vehicles (RPVs), and Unmanned Air Vehicles (UAVs). Both UAVs and RPVs are vehicles which are originally designed without a pilot on board. The typical drone system consists of an airborne vehicle, or airborne system, in combination with a ground station. The ground station is adapted to provide positive control of the drone throughout the flight envelope of the air vehicle. In addition, appropriate electrical or mechanical devices are also controlled through the ground station. These electrical/mechanical devices are used to actuate things such as landing gear, wing flaps, slats, wheel brakes, speed brakes, nose wheel steering, and a variety of other electrical connections used for commanding the air vehicle.

What are you waiting for?

Sign Up

What is LOCI?

LOCI is the future of innovation, intellectual property, and ideas.LOCI is a tech company founded with the one goal in mind – to change the way the world invents and values ideas. Built upon Aristotelian theory that property may be private but should serve as a benefit to the common good, not just serve to benefit a privileged few, and the belief that we, as humans, truly think better together,LOCI has set out to build a space for these theories to become practice and to put power back into the hands of inventors.

Protect Your Ideas

LOCI and its patented technology, LOCI Search, are poised to facilitate and energize the first-inventor-to-file system of patenting here in the United States and throughout the world. Our system allows inventors to safely search for their ideas, identify if other ‘prior art’ exists, and if their ideas are unique, our system provides them the ability to stake claim to their invention on the blockchain, thus, serving as a public immutable record of their idea. Along with this action of staking claim on the blockchain, the searches conducted in our system can be saved, exported, and submitted to the USPTO as evidence of precedence, further increasing the likelihood that a patent will be granted. In short, LOCI and its technology offer a protected environment for inventors to search, stake, and eventually sell their ideas.