Abstract: A system and method to generate and manage clusters of search terms. The system and method generate a cluster including a set of search terms. A size of the cluster is compared to a cluster size threshold level to determine that the cluster comprises a valid-sized cluster. A noise rate of the cluster is compared to a noise rate threshold level to determine that the noise rate is less than the noise rate threshold level, wherein the noise rate relates to a distance of the cluster from a set of other clusters. Performance data associated with the cluster is generated based on a comparison with one or more cluster performance metric thresholds. A user interface is generated to display information associated with the cluster comprising the performance data. Input is received via the user interface comprising an adjustment of the one or more cluster performance metrics thresholds.

Abstract: A system and method to generate and manage clusters of search terms. A cluster generation process is executed at a first time to generate a first set of clusters including respective sets of search terms. At least one of a first value of a first parameter associated with the first set of clusters or a first value of a second parameter associated with the first set of clusters is determined. At a second time, the cluster generation process is executed to generate a second set of clusters. At least one of a second value of the first parameter associated with the second set of clusters or a second value of the second parameter associated with the second set of clusters is determined. A determination is made whether either the second value of the first parameter satisfies a first condition or the second value of the second parameter satisfies a second condition.

Abstract: Systems, methods, and computer-readable storage media for receiving data at a computer system, wherein the data has a plurality of rows; receiving, from a user at the computer system, a description of a task associated with the data; receiving, from the user at the computer system, a plurality of example transformations; combining, via at least one processor of the computer system, the task description together with the plurality of example transformations and input and output labels, resulting in a prompt; executing, via the at least one processor, a machine learning model, wherein the prompt is an input to the machine learning model, and wherein output of the machine learning model comprises an algorithm for executing the task; and executing, via the at least one processor, the task on the data using the algorithm.

Abstract: Embodiments of the disclosure provide for a knowledge search engine platform to identifying first data associated with a merchant system from one or more databases based on a search query submitted by a user device. The knowledge search engine platform generates a user dialog interface to display to the user device to enable a communication to collect additional information to supplement the first data. Second data to supplement the first data is received from the user system via the user dialog interface. Responsive to receiving the second data, a set of communications are transmitted to a set of search provider systems, where each communication of the set of communications comprising a recommended update comprising the first data and the second data.

Abstract: A system and method to generate and manage clusters of search terms. The system and method collect a set of search terms associated with multiple search queries relating to an entity. A neural network identifies a set of embedding vectors, wherein each of the set of embedding vectors represents a search term of the set of search terms. A cluster is generated including a portion of the set of search terms based on a comparison of embedding vectors associated with the portion of the set of search terms. A size of the cluster is compared to a cluster size threshold level to determine if a first condition is satisfied. In response to determining satisfaction of the first condition, the cluster is identified as a valid-sized cluster. A user interface is generated to display information related to the cluster and one or more cluster metrics.

Abstract: Embodiments of the disclosure provide for a knowledge search engine platform to analyze a search query initiated by a user device to identify a natural language inquiry associated with questions about a particular business, (e.g., product brand data such as products, services, employees, events, etc.). This may include searching through large amounts of data for hidden patterns and relationships of events, and presenting this knowledge data in a readily understandable format for users. The knowledge data is then presented in a structured form that is easily digestible to allow users via the user device to find the information they are looking to retrieve. The knowledge data may also include competitor intelligence that allows users to identify competitors, by searching a local pack to return results of potential competitors. The local pack may be within proximity of an indication of location of where the user is searching using with user device.

Abstract: A system and method to receive a search query input from an end user system, wherein the search query input relates to information associated with a merchant system. In view of the search query, a document associated with the merchant system is identified. A set of portions of the document are identified. A keyword-matching density level is determined for each portion of the set of portions of the document. A selected portion of the set of portions having a highest relative keyword-matching density level is identified. A graphical user interface including a search result responsive to the search query is generated, the graphical user interface including the selected portion of the document.

Abstract: A system and method to train one or more components of a search algorithm based on feedback received from a user system. The system and method provide, via an interface, a first search query comprising one or more terms and a first query response generated by a component of the search algorithm. The system and method receive, via the interface, a label corresponding to the query response. An override action is generated in view of the label. In response to a second query comprising the one or more terms, generating a second query response in accordance with the override action.

Abstract: A system and method to generate and manage clusters of search terms. A cluster generation process is executed at a first time to generate a first set of clusters including respective sets of search terms. At least one of a first value of a first parameter associated with the first set of clusters or a first value of a second parameter associated with the first set of clusters is determined. At a second time, the cluster generation process is executed to generate a second set of clusters. At least one of a second value of the first parameter associated with the second set of clusters or a second value of the second parameter associated with the second set of clusters is determined. A determination is made whether either the second value of the first parameter satisfies a first condition or the second value of the second parameter satisfies a second condition.

Abstract: A system and method to generate and manage clusters of search terms. The system and method collect a set of search terms associated with multiple search queries relating to an entity. A neural network identifies a set of embedding vectors, wherein each of the set of embedding vectors represents a search term of the set of search terms. A cluster is generated including a portion of the set of search terms based on a comparison of embedding vectors associated with the portion of the set of search terms. A size of the cluster is compared to a cluster size threshold level to determine if a first condition is satisfied. In response to determining satisfaction of the first condition, the cluster is identified as a valid-sized cluster. A user interface is generated to display information related to the cluster and one or more cluster metrics.

Abstract: A system and method to manage data associated with a merchant system to provide in response to a search query from an end user system. The system and method to generate, in a data graph associated with a merchant system, a first entity type including a first data field storing a first data value corresponding to the merchant system. A second entity type comprising a second data field storing a second data value corresponding to the merchant system is generated in the data graph. A relationship type between the first entity type and the second entity type is established. A first update to the first data value of the first entity type is generated. In view of the relationship type, a second update to the second data value of the second entity type is generated. The first update of the first entity type and the second update of the second entity type are stored in the data graph.

Abstract: A system and method to manage data associated with a merchant system to provide in response to a search query from an end user system. The system and method generate a custom entity type including one or more fields comprising first data corresponding to the merchant system. An update to the first data of the custom entity type can be received and an updated custom entity type is generated. The updated custom entity type is distributed to multiple business listing provider systems configured to provide search results associated with the merchant system in response to a search query from an end user system. The system and method can also generate a search experience interface including multiple input fields. The search experience interface is displayed to an end user to receive search terms via the first input and the second input field in response to a single search action.

Abstract: A system and method to provide search capabilities via a merchant system including search responses aggregated from multiple different search provider sources. The system and method receive, via an interface of the merchant system, a search query input from an end user system. The search query input is routed to the multiple search provider sources. A set of response to the search query input is received from at least a portion of the search providers sources. A first portion of the set of responses is identified as having a verified status. A ranking of the set of responses is generated based on a level of responsiveness to the search query input. The system and method cause, based at least in part on the ranking, a display including a search result comprising at least a portion of the set of responses.