# US 2026/0094069 A1 · System and method for selecting a candidate transfer apparatus > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2026/0094069 A1 - Document ID: US20260094069A1 - Status: Published application - Kind: A1 - Application number: 19/411,531 - Filed: 2025-12-08 - Published: 2026-04-02 - Earliest claimed: 2020-10-16 - Assignees: Hammel Companies Inc. - Applicants: Hammel Companies, Inc. - Inventors: Joseph Charles Dohrn - Web page: https://patentgrep.com/patent/US20260094069A1 ## CPC - G06N 20/00: Machine learning - G06F 16/24578: {using ranking} - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/09: Supervised learning - G06N 3/045: Combinations of networks - G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound - G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks - G06N 20/20: Ensemble learning - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract A method for determining a transfer apparatus based on user preferences includes receiving, by a computing device, at least a transfer invocation and a plurality of user preferences and generating, by the computing device, and for each candidate transfer apparatus of a plurality of candidate transfer apparatuses, a plurality of performance prognoses corresponding to the plurality of user preferences. The method includes selecting, by the computing device, a candidate transfer apparatus as a function of the plurality of performance prognoses and providing, by the computing device, the selected candidate transfer apparatus to a user. ## Claims ### Claim 1 A method of determining a transfer apparatus based on user preferences, the method comprising: receiving, by a computing device, at least a transfer invocation and a plurality of user preferences, wherein the at least a transfer invocation comprises at least an origin location and at least a destination location; determining, by the computing device, a plurality of candidate transfer apparatuses as a function of the transfer invocation and the plurality of user preferences; generating, by the computing device and using a plurality of trained candidate transfer apparatus models, a plurality of performance prognoses for the plurality of candidate transfer apparatuses, wherein generating the plurality of performance prognoses comprises: receiving, by the plurality of trained candidate transfer apparatus models, the at least the transfer invocation and the plurality of user preferences; and generating, by each trained candidate transfer apparatus model, a performance prognosis corresponding to the candidate transfer apparatus; ranking, by the computing device, the plurality of performance prognoses as a function of a difference between each performance prognosis and the plurality of user preferences, wherein ranking the plurality of performance prognoses comprises: computing, using a loss function, a score representing a deviation between each performance prognosis and the plurality of user preferences; optimizing the score as a function of an objective function configured to identify a candidate transfer apparatus indicative of a maximal satisfaction of the plurality of user preferences; and ordering the plurality of performance prognoses in accordance with the optimized score; and selecting, by the computing device, a transfer apparatus as a function of the ranking; providing, by the computing device, the transfer apparatus selected from the plurality of candidate transfer apparatuses to a user. ### Claim 2 (depends on 1) The method of claim 1, wherein the plurality of user preferences comprises a plurality of required data associated with the at least a transfer invocation, wherein the plurality of required data comprises at least a preferred cost. ### Claim 3 (depends on 1) The method of claim 1, further comprising: storing, by the computing device, the candidate transfer apparatuses in a candidate transfer apparatus archive; retrieving, by the computing device, the stored candidate transfer apparatuses from the candidate transfer apparatus archive for subsequent use in determining the transfer apparatus; receiving, by the computing device, a later transfer invocation associated with one or more pieces; generating, by the computing device, past prioritized user preferences corresponding to the later transfer invocation; modifying, by the computing device, the past prioritized user preferences; and determining, using the modified past prioritized user preferences, the transfer apparatus for the later transfer invocation. ### Claim 4 (depends on 1) The method of claim 1, further comprising training the plurality of candidate transfer apparatus models using a candidate transfer apparatus performance archive, wherein the candidate transfer apparatus performance archive comprises performance metrics associated with candidate transfer apparatuses. ### Claim 5 (depends on 1) The method of claim 1, further comprising providing, by the computing device, the transfer apparatus selected from the plurality of candidate transfer apparatuses to the user by transmitting a notification indicative of the selected transfer apparatus to a user device. ### Claim 6 (depends on 1) The method of claim 1, further comprising providing, by the computing device, the transfer apparatus selected from the plurality of candidate transfer apparatuses to the user by transmitting an output comprising a list of routes associated with one or more legs of a transfer between the at least an origin location and the at least a destination location. ### Claim 7 (depends on 1) The method of claim 1, wherein each of the plurality of trained candidate transfer apparatus models comprises a supervised machine learning model. ### Claim 8 (depends on 1) The method of claim 1, wherein the transfer apparatus comprises a freight carrier. ### Claim 9 (depends on 1) The method of claim 1, further comprising computing, by the computing device, a score of a performance prognosis based on a combination of one or more factors of the plurality of user preferences and a plurality of constraints, wherein the plurality of constraints comprises at least transfer dates, arrival dates, load size, and piece type. ### Claim 10 (depends on 9) The method of claim 9, further comprising assigning, by the computing device, the score to each factor of the one or more factors based on predetermined variables, wherein the assigned scores are weighted. ### Claim 11 A system for determining a transfer apparatus based on user preferences, the system comprising a computing device, the computing device configured to: receive at least a transfer invocation and a plurality of user preferences, wherein the at least a transfer invocation comprises at least an origin location and at least a destination location; determine a plurality of candidate transfer apparatuses as a function of the transfer invocation and the plurality of user preferences; generate, using a plurality of trained candidate transfer apparatus models, a plurality of performance prognoses for the plurality of candidate transfer apparatuses, wherein generating the plurality of performance prognoses comprises: receiving, by the plurality of trained candidate transfer apparatus models, the at least the transfer invocation and the plurality of user preferences; and generating, by each trained candidate transfer apparatus model, a performance prognosis corresponding to the candidate transfer apparatus; rank the plurality of performance prognoses as a function of a difference between each performance prognosis and the user preferences, wherein ranking the plurality of performance prognoses comprises: computing, using a loss function, a score representing a deviation between each performance prognosis and the plurality of user preferences; and optimizing the score as a function of an objective function configured to identify a candidate transfer apparatus indicative of a maximal satisfaction of the user preferences; ordering the plurality of performance prognoses in accordance with the optimized score; and select a transfer apparatus as a function of the ranking; provide the transfer apparatus selected from the plurality of candidate transfer apparatuses to a user. ### Claim 12 (depends on 11) The system of claim 11, wherein the plurality of user preference comprise a plurality of required data associated with the at least a transfer invocation, wherein the plurality of required data comprises at least a preferred cost. ### Claim 13 (depends on 11) The system of claim 11, wherein the computing device is further configured to: store the candidate transfer apparatuses in a candidate transfer apparatus archive; retrieve the stored candidate transfer apparatuses from the candidate transfer apparatus archive for subsequent use in determining the transfer apparatus; receive a later transfer invocation associated with one or more pieces; generate past prioritized user preferences corresponding to the later transfer invocation; and modify the past prioritized user preferences; and determine, using the modified past prioritized user preferences, the transfer apparatus for the later transfer invocation. ### Claim 14 (depends on 11) The system of claim 11, wherein the computing device is further configured to train the plurality of candidate transfer apparatus models using a candidate transfer apparatus performance archive, wherein the candidate transfer apparatus performance archive comprises performance metrics associated with candidate transfer apparatuses. ### Claim 15 (depends on 11) The system of claim 11, wherein the computing device is further configured to provide the transfer apparatus selected from the plurality of candidate transfer apparatuses to the user by transmitting a notification indicative of the selected transfer apparatus to a user device. ### Claim 16 (depends on 11) The system of claim 11, wherein the computing device is further configured to provide the transfer apparatus selected from the plurality of candidate transfer apparatuses to the user by transmitting an output comprising a list of routes associated with one or more legs of a transfer between the origin location and the destination location. ### Claim 17 (depends on 11) The system of claim 11, wherein each of the plurality of trained candidate transfer apparatus models comprise a supervised machine learning model. ### Claim 18 (depends on 11) The system of claim 11, wherein the transfer apparatus comprises a freight carrier. ### Claim 19 (depends on 11) The system of claim 11, wherein the computing device is further configured to compute a score of a performance prognosis based on a combination of one or more factors of the plurality of user preferences and a plurality of constraints comprising, wherein the plurality of constraints comprise at least transfer dates, arrival dates, load size, and piece type. ### Claim 20 (depends on 19) The system of claim 19, wherein the computing device is further configured to assign the score to each factor of the one or more factors based on predetermined variables, wherein the assigned scores are weighted.