Ungria López, Javier

The present invention discloses a system (1) and a method for an automatic classification of recyclable containers. The system comprises: a receptacle (2) for holding a recyclable container (3); a computing unit (4); a loudspeaker (5) for generating ultrasonic (50) and/or audible sound waves (51); microphones (7) for capturing the sound waves. The computing unit is configured to generate signal: an exponential sine sweep (ESS) in the audible range, an ESS in the ultrasonic range, or an audible ESS and modulate it to the ultrasonic range; send the signal to the loudspeaker; measure the sound waves and compute the acoustic impulse responses (52); postprocessing the acoustic impulse responses; classify the type of recyclable container using Machine Learning, trained using a training dataset. The training dataset includes acoustic impulse responses of recyclable containers to ultrasonic and/or audible sound waves, and types of recyclable containers issued from a classification test.

Artificial intelligence (AI) agents for user interface (UI) automation to application programming interface (API) automation, and vice versa, are disclosed. The operations performed by a UI automation on the back-end can be captured by an AI agent, including what communications are sent and the context thereof. A robotic process automation (RPA) activity can then be built in an RPA workflow that replaces the UI automation with an API automation. Alternatively, an API automation is replaced with a UI automation. The AI agent employs a fine-tuned generative AI model to understand the context of the communications. The AI agent may also find obsolete duplicates of UI automations and replace these with API automations, or vice versa.

System and method for cleaning and upgrading biogas into biomethane in a sustainable way by means of absorption in a carbonates-bicarbonates solution and subsequent regeneration of said solution by desorption; wherein the resulting biomethane has a quality for injection into the natural gas grid. The overall process operates at atmospheric pressure and ambient temperature by increasing reaction rates and without applying neither heat nor pressure, or addition of any absorption promoter. Any known sulphide pre-cleaning step is not needed. The claimed system comprises four or more high mass transfer bubble columns with a counter-current configuration, filled with plastic media and operating at different pH ranges, two for absorption and two for CO<2> desorption by air stripping, in which the reaction rate in the carbonates-bicarbonates solution is increased. The invention also comprises the implementation of control strategies.

An agentic searching method is provided. The agentic searching method is implemented by artificial intelligence (AI) agents. The agentic searching method includes performing advanced agentic searching of a sematic storage including context embeddings in response to a complex query. The agentic searching method includes outputting a context grounding resulting from the searching of the sematic storage and the context embeddings to an Al model with the complex query to enhance an accuracy of a response of the Al model. The agentic searching method includes receiving the response to the complex query from the Al model.

An agentic memory method is provided. The agentic memory method is implemented by artificial intelligence (AI) agents. The agentic memory method includes storing vectors including context embeddings generated by advanced agentic extraction in response to queries in an agentic memory. The agentic memory method includes receiving and matching a complex query to the vectors of the agentic memory by an advanced agentic search to determine a context grounding. The agentic memory method includes providing the context grounding to an Al model with the complex query to enhance an accuracy of a response of the Al model and receiving the response to the complex query from the Al model.

Predictive healing artificial intelligence (AI) agents that preemptively detect impending workflow errors, failures, and/or faults and automatically attempt recovery are disclosed. The healing capabilities of the Al agents may be seamlessly integrated into existing systems and workflows with minimal disruption. A developer may build a user interface (UI) automation workflow that works at design time, but will fail at runtime for some reason. For instance, the automation may be deployed to a computing system with different graphical characteristics than those that were present when the automation was designed, a software update may change aspects of the UI, the computing system may be too busy to run the automation, there may be connectivity issues, a third party system that the automation relies upon may be down, etc. An Al agent can detect that these issues will occur when the automation is run and attempt to automatically correct them.

Generation of unified projects/solutions in artificial intelligence (AI) agent, robotic process automation (RPA) robot, and agentic orchestration process (AOP) development applications is disclosed. Based on a prompt, a process definition document, or some other source, an entire end-to-end business process can be automated, including underlying code and the requisite dependencies. A generative AI model is used to generate an AOP for the business process, including steps performed by AI agent(s) and/or RPA robot(s). The AOP may be represented in Business Process Model and Notation (BPMN), which is an Extensible Markup Language (XML) description of the business process. The designer application may also display a flowchart that shows the AOP. The generative AI model employed by the designer application is fine-tuned to understand which BPMN steps to include in the AOP, including steps that are executed by AI agents and/or RPA robots.

Artificial intelligence (Al)-based techniques for determining best action recommendations for issues that arise during the operation of conductor applications and/or robotic process automation (RPA) robots, and for implementing such recommendations, are disclosed. A generative Al model or other type of AI model (e.g., a classifier) is trained to detect issues that occur during operation of such conductor applications and/or RPA robots and to provide recommendations to users with respect to the best action to address the problem. The AI model may list the recommendations that exceed a recommendation threshold, along with their respective confidence scores. In some cases, the Al model may analyze characteristics of executing jobs and provide recommendations for improving the automations, or implement the improvements automatically.

The present invention relates to a food baking pan (1) comprising: at least one hollow element (3) which shape is equivalent to a shape of a food to be baked; a frame (5) configured to hold several hollow elements (3) and to be displaced by a conveyor device (6); a lid (2) covering the at least one hollow element (3). The lid (2) is made of ferromagnetic materials and the frame (5) comprises attracting magnets (4) configured to keep the lid (2) against the hollow elements (3) at temperatures above 100° Celsius. The invention further relates to a removal system for removing the lid with removing magnets (7), which are made of samarium-cobalt.

The present invention comprises several positioning devices (3) for stabilising the roof (2) of the body (1), and means for moving the roof vertically and thus placing it at the required height with final resting on the positioning devices. Each positioning device comprises a movable vertical structure (8) with height-adjustable displacement, formed by an elongated profile (8a) and a tilting skid (8b), which is coupled to the elongated profile (8a) below it by means of a horizontal articulated connection (9). The tilting skid (8b) includes a horizontal transverse shaft (10) which is configured to fit into one of several recesses (15a) delimited between teeth of a toothed rack (15) according to the required height of the roof (2). The positioning devices are arranged at least in the four vertical corner areas of the truck body (1), so that the roof (2) rests on ends of the various movable vertical structures (8).