Abstract: Systems and methods are described for determining a second entity having a similar trademark portfolio as a first entity. In embodiments, a user submits a request identifying a first entity. A trademark portfolio generator compiles a trademark portfolio of the first entity by accessing a database of trademarks. A trademark portfolio analyzer analyzes the features of the trademark portfolio to form a trademark portfolio profile. A portfolio similarity score calculator determines a trademark portfolio similarity score based by determining the similarity between the trademark portfolio profile of the first entity and trademark portfolio profiles of the second entity. In embodiments, feature vectors related to trademark portfolio profiles of two or more entities are compared to generate portfolio similarity scores. Based on the portfolio similarity scores, a user interface presents the second entity to the user as an entity having a similar trademark portfolio as the first entity.

Abstract: Systems and methods are described for obtaining evidence of online commercial use of a trademark. In embodiments, a query generator receives information about the trademark and generates search queries based thereon. A search results collector submits the search queries to at least one Internet search engine to obtain a set of search results pertaining to a plurality of web pages. A web page content analyzer obtains and analyzes page content of each web page in the plurality of web pages to generate a brand score indicative of a degree of confidence that the web page includes the trademark and a commercial score indicative of a degree of confidence that the web page relates to commerce. A user interface (UI) manager presents information about each web page in the plurality of web pages via a UI, including associated brand score and commercial score representations, in a ranked order based on relevance.

Abstract: Machine learning-based techniques for predicting trademark similarity are described. For instance, a first trademark pair comprising an attribute of a first trademark and a corresponding attribute of a second trademark is received. A level of similarity is determined between the first trademark pair and respective second trademark pairs included in respective legal proceedings maintained in a database. A subset of proceedings from the proceedings is selected, each proceeding of the subset including a respective second trademark pair that has the level of similarity with the first trademark pair. A feature vector is generated based on each proceeding of the subset. The feature vector is provided to a machine learning model that outputs a prediction score, based on the feature vector, as to whether a subsequent proceeding would find a likelihood of confusion between the first trademark and the second trademark. The prediction score is provided to a user interface.

Abstract: A system is disclosed for ranking trademark search results. The ranking may be performed using one or more similarity models that comprises a trained model (e.g., a machine-learning model, an artificial intelligence model, or a deep neural network). In an example system, a candidate trademark name is received. A set of search results is obtained for the candidate trademark that identifies trademark names having at least a minimum degree of similarity with the candidate trademark name. The candidate trademark name and the set of search results are provided to a first trained model that outputs, for each trademark name, a trademark name similarity score. For each trademark name, a goods/services similarity score is obtained indicating a level of goods/services similarity with the candidate trademark name. A ranked list of results is provided based at least on a combination of the trademark name similarity scores and the goods/services similarity scores.

Abstract: Systems and methods for generating strings based on a seed string are disclosed. Machine learning models are trained using domain-specific training data. Random walk models are derived from the trained machine learning models. A seed string is input into each of the random walk models, and each of the random walk models iteratively generate one or more next characters for the seed string to generate at least one term from each of the random walk models. A predicted class for the at least one term generated by each of the random walk models can be determined, and a ranked order for the at least one term generated by each of the random walk models with the predicted classes can be output to a graphical user interface.

Abstract: Exemplary embodiments of the present disclosure provide for identifying similar trademarks from one or more repositories and providing an interactive graphical user interface in which selectable graphical segments corresponding to the trademarks in a graphical user interface are grouped based on similarity measures associated with one or more characters of the trademarks and arranged radially and circumferentially in the graphical user interface about a central circle representing the trademark input string of an electronic search order. Retrieval of the trademarks in the set can include a subset of possible trademarks available for retrieval that would satisfy one or more of the similarity measures and a color of each of the selectable graphical segments depends on whether the trademarks retrieved corresponding to the selectable graphical segments represent a complete set of the possible trademarks available, a subset of the possible trademarks available, or a null set of the possible trademarks available.

Abstract: Exemplary embodiments of the present disclosure provide for extraction data from one or more repositories in response to an electronic search order including a text-based input string, a list of jurisdictions, and a list of international classes. Conditional logic of one or more rules is executed to process the search order, and the search order is transformed into one or more queries based on execution of the conditional logic of the one or more rules. A set of data is retrieved from the one or more repositories using the one or more queries to generate search results, where the set of trademarks retrieved can be limited to the list of jurisdictions and the list of international classes identified in the search order. At least a portion of the search results are transmitted to a user computing device to be rendered in a graphical user interface of a display device associated with the user computing device.

Abstract: Systems and methods for generating strings based on a seed string are disclosed. Machine learning models are trained using domain-specific training data. Random walk models are derived from the trained machine learning models. A seed string is input into each of the random walk models, and each of the random walk models iteratively generate one or more next characters for the seed string to generate at least one term from each of the random walk models. A predicted class for the at least one term generated by each of the random walk models can be determined, and a ranked order for the at least one term generated by each of the random walk models with the predicted classes can be output to a graphical user interface.

Abstract: Exemplary embodiments of the present disclosure provide for identifying similar trademarks from one or more repositories based on training a goods and/or services similarity engine to identify similarities between pairs of descriptions of goods and/or services in a corpus of training data that includes the descriptions of goods and/or services for registered trademarks and trademark classes associated with the descriptions of goods and/or services. A goods and/or services similarity value indicative of similarities between a reference description of goods and/or services and descriptions of goods and/or services associated with registered trademarks can be generated by a goods and/or services similarity engine and a presentation of at least a subset of the set of trademarks can be generated that includes graphics emphasizing the registered trademarks in the subset based, at least in part, on the plurality of goods and/or services similarity values.

Abstract: Exemplary embodiments of the present disclosure provide for identifying similar trademarks from one or more repositories and providing an interactive graphical user interface in which selectable graphical segments corresponding to the trademarks in a graphical user interface are grouped based on similarity measures associated with one or more characters of the trademarks and arranged radially and circumferentially in the graphical user interface about a central circle representing the trademark input string of an electronic search order. Retrieval of the trademarks in the set can include a subset of possible trademarks available for retrieval that would satisfy one or more of the similarity measures and a color of each of the selectable graphical segments depends on whether the trademarks retrieved corresponding to the selectable graphical segments represent a complete set of the possible trademarks available, a subset of the possible trademarks available, or a null set of the possible trademarks available.

Abstract: Exemplary embodiments of the present disclosure provide for extraction data from one or more repositories in response to an electronic search order including a text-based input string, a list of jurisdictions, and a list of international classes. Conditional logic of one or more rules is executed to process the search order, and the search order is transformed into one or more queries based on execution of the conditional logic of the one or more rules. A set of data is retrieved from the one or more repositories using the one or more queries to generate search results, where the set of trademarks retrieved can be limited to the list of jurisdictions and the list of international classes identified in the search order. At least a portion of the search results are transmitted to a user computing device to be rendered in a graphical user interface of a display device associated with the user computing device.

Abstract: Exemplary embodiments of the present disclosure provide for extraction data from one or more repositories in response to an electronic search order including a text-based input string, a list of jurisdictions, and a list of international classes. Conditional logic of one or more rules is executed to process the search order, and the search order is transformed into one or more queries based on execution of the conditional logic of the one or more rules. A set of data is retrieved from the one or more repositories using the one or more queries to generate search results, where the set of trademarks retrieved can be limited to the list of jurisdictions and the list of international classes identified in the search order. At least a portion of the search results are transmitted to a user computing device to be rendered in a graphical user interface of a display device associated with the user computing device.

Abstract: Exemplary embodiments of the present disclosure provide for identifying similar trademarks from one or more repositories based on training a goods and/or services similarity engine to identify similarities between pairs of descriptions of goods and/or services in a corpus of training data that includes the descriptions of goods and/or services for registered trademarks and trademark classes associated with the descriptions of goods and/or services. A goods and/or services similarity value indicative of similarities between a reference description of goods and/or services and descriptions of goods and/or services associated with registered trademarks can be generated by a goods and/or services similarity engine and a presentation of at least a subset of the set of trademarks can be generated that includes graphics emphasizing the registered trademarks in the subset based, at least in part, on the plurality of goods and/or services similarity values.

Abstract: Exemplary embodiments of the present disclosure provide for extraction data from one or more repositories in response to an electronic search order including a text-based input string, a list of jurisdictions, and a list of international classes. Conditional logic of one or more rules is executed to process the search order, and the search order is transformed into one or more queries based on execution of the conditional logic of the one or more rules. A set of data is retrieved from the one or more repositories using the one or more queries to generate search results, where the set of trademarks retrieved can be limited to the list of jurisdictions and the list of international classes identified in the search order. At least a portion of the search results are transmitted to a user computing device to be rendered in a graphical user interface of a display device associated with the user computing device.