# US 12,001,963 B2 · Facilitating ML algorithm contribution to use cases where data is prohibitive > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,001,963 B2 - Document ID: US12001963B2 - Status: Granted - Kind: B2 - Application number: 17/207,340 - Filed: 2021-03-19 - Published: 2021-11-04 - Granted: 2024-06-04 - Earliest claimed: 2020-04-30 - Assignees: Sensormatic Electronics Corporation - Applicants: Sensormatic Electronics, LLC - Inventors: Gopi Subramanian; Michael C. Stewart - Web page: https://patentgrep.com/patent/US12001963B2 ## CPC - G06N 3/126: Evolutionary algorithms, e.g. genetic algorithms or genetic programming - G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting - G06N 20/00: Machine learning - G08B 13/2474: {Antenna or antenna activator geometry, arrangement or layout (loop antennae H01Q1/22)} - G08B 13/2482: {EAS methods, e.g. description of flow chart of the detection procedure} - G08B 29/186: {Fuzzy logic; neural networks} - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G08B: SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS ## Abstract Example aspects include techniques for building a ML model in a use case with prohibitive training data and employing the ML model within the use case. These techniques may include determining training information including a plurality of stray training reads and a plurality of valid training reads, determining modified training information based at least in part on modifying the plurality of valid training reads, and generating a model for distinguishing a valid read from a stray read based on the modified training information and an evolutionary algorithm. In addition, the techniques may include detecting, by a monitoring device, a plurality of tag reads in response to a plurality of interactions between a tag and the monitoring device, and determining, by the monitoring device, a plurality of valid tag reads based on the model and plurality of tag reads. ## Claims ### Claim 1 A method, comprising: determining training information including a plurality of stray training reads and a plurality of valid training reads; determining modified training information based at least in part on modifying the plurality of valid training reads; generating a model for distinguishing a valid read from a stray read based on the modified training information and an evolutionary algorithm; detecting, by a monitoring device, a plurality of tag reads in response to a plurality of interactions between a tag and the monitoring device; and determining, by the monitoring device, a plurality of valid tag reads based on the model and plurality of tag reads. ### Claim 2 (depends on 1) The method of claim 1, wherein the evolutionary algorithm is a genetic algorithm, and generating the model comprises: determining a first plurality of models for distinguishing the valid read from the stray read; determining fitness information indicating an efficacy of the first plurality of models; determining a second plurality of models based upon the fitness information and a threshold; determining a third plurality of models by mating amongst the second plurality of models and applying mutations to offspring of the mating; and selecting the model from the third plurality of models. ### Claim 3 (depends on 1) The method of claim 1, wherein the monitoring device comprises a first pedestal including a first plurality of antennae and a second pedestal including a second plurality of antennae, and detecting the plurality of tag reads, comprises: synchronizing the first plurality of antennae of the first pedestal and the second plurality of antennae of the second pedestal to create a field; and detecting a first tag read of the plurality of tag reads within the field. ### Claim 4 (depends on 1) The method of claim 1, wherein the monitoring device is a tag reader system in an electronic article surveillance system, and further comprising: determining that the plurality of valid tag reads corresponds to unauthorized movement of the tag outside of a geographic area; and triggering an alarm notification based at least in part on the unauthorized movement. ### Claim 5 (depends on 1) The method of claim 1, wherein the monitoring device is a tag scanner in an inventory management system, and further comprising: determining that the plurality of valid tag reads correspond to a relocation of the tag to a geographic area; and triggering a location notification identifying the geographic area. ### Claim 6 (depends on 5) The method of claim 5, further comprising updating inventory information to indicate an article associated with the tag is located at a location of the monitoring device based on the location notification. ### Claim 7 (depends on 1) The method of claim 1, further comprising updating the model based on a measured accuracy of the monitoring device. ### Claim 8 A system comprising: a management device comprising: a memory storing instructions thereon; and at least one processor coupled to the memory and configured by the instructions to: identify training information including a plurality of stray training reads and a plurality of valid training reads; determine modified training information based at least in part on modifying the plurality of valid training reads; and generate a model for distinguishing a valid read from a stray read based on the modified training information and an evolutionary algorithm, the model to be employed to identify a plurality of valid tag reads captured at a monitoring device. ### Claim 9 (depends on 8) The system of claim 8, wherein the evolutionary algorithm is a genetic algorithm. ### Claim 10 (depends on 9) The system of claim 9, wherein to generate the model, the at least one processor is configured by the instructions to: determine a first plurality of models for distinguishing the valid read from the stray read; determine fitness information indicating an efficacy of the first plurality of models; determine a second plurality of models based upon the fitness information and a threshold; determine a third plurality of models by mating amongst the second plurality of models and applying mutations to offspring of the mating; and select the model from the third plurality of models. ### Claim 11 (depends on 8) The system of claim 8, further comprising the monitoring device including a first pedestal including a first plurality of antennae and a second pedestal including a second plurality of antennae, and wherein the monitoring device is configured to detect, based on interactions with one or more tags, a plurality of tag reads including the plurality of valid tag reads. ### Claim 12 (depends on 8) The system of claim 8, further comprising the monitoring device, and wherein the monitoring device is configured to determine that the plurality of valid tag reads corresponds to unauthorized movement of a tag outside of a geographic area, and triggering an alarm notification based at least in part on the unauthorized movement. ### Claim 13 (depends on 8) The system of claim 8, further comprising the monitoring device, and wherein the monitoring device is configured to determine that the plurality of valid tag reads correspond to a relocation of a tag to a geographic area, and trigger a location notification identifying the geographic area. ### Claim 14 A non-transitory computer-readable device having instructions thereon that, when executed by at least one computing device, causes the at least one computing device to perform operations comprising: determining training information including a plurality of stray training reads and a plurality of valid training reads; determining modified training information based at least in part on modifying the plurality of valid training reads; generating a model for distinguishing a valid read from a stray read based on the modified training information and an evolutionary algorithm; detecting, by a monitoring device, a plurality of tag reads in response to a plurality of interactions between a tag and the monitoring device; and determining, by the monitoring device, a plurality of valid tag reads based on the model and plurality of tag reads. ### Claim 15 (depends on 14) The non-transitory computer-readable device of claim 14, wherein the evolutionary algorithm is a genetic algorithm, and generating the model comprises: determining a first plurality of models for distinguishing the valid tag read from the stray read; determining fitness information indicating an efficacy of the first plurality of models; determining a second plurality of models based upon the fitness information and a threshold; determining a third plurality of models by mating amongst the second plurality of models and applying mutations to offspring of the mating; and selecting the model from the third plurality of models. ### Claim 16 (depends on 15) The non-transitory computer-readable device of claim 15, wherein selecting the model from the third plurality of models comprises determining that the third plurality of models have converged. ### Claim 17 (depends on 14) The non-transitory computer-readable device of claim 14, wherein the monitoring device comprises a first pedestal including a first plurality of antennae and a second pedestal including a second plurality of antennae, and detecting the plurality of tag reads, comprises: synchronizing the first plurality of antennae of the first pedestal and the second plurality of antennae of the second pedestal to create a field; and detecting a first tag read of the plurality of tag reads within the field. ### Claim 18 (depends on 14) The non-transitory computer-readable device of claim 14, wherein the monitoring device is a tag reader system in an electronic article surveillance system, and the operations further comprising: determining that the plurality of valid tag reads corresponds to unauthorized movement of the tag outside of a geographic area; and triggering an alarm notification based at least in part on the unauthorized movement. ### Claim 19 (depends on 14) The non-transitory computer-readable device of claim 14, wherein the operations further comprise: determining that the plurality of valid tag reads correspond to a relocation of the tag to a geographic area; and triggering a location notification identifying the geographic area. ### Claim 20 (depends on 19) The non-transitory computer-readable device of claim 19, wherein the operations further comprise updating inventory information to indicate an article associated with the tag is located at a location of the monitoring device based on the location notification.