Abstract: The present disclosure relates to systems and methods for automatic generation of summaries for record objects using one or more large language models. The system can identify a plurality of electronic activities matched to a record object of a customer relationship management system. The system can generate one or more text strings from the plurality of electronic activities using the large language models. The system can generate a first set of topics by inputting a first set of text strings into the large language models. The system can generate a second set of topics by inputting a first subset of text strings of the first set of text strings into the large language models. The system can transmit one or more topics to a computing device for presentation.

Abstract: The present disclosure relates to methods, systems, and storage media for detecting events based on updates to node profiles from electronic activities. Exemplary implementations may access an electronic activity transmitted or received via an electronic account associated with a data source provider; generate a plurality of activity field-value pairs; maintain a plurality of node profiles; identify a first state of a first node profile of the plurality of node profiles; update the first node profile using the electronic activity; identify a second state of the first node profile subsequent to updating the first node profile using the electronic activity; detect a state change of the first node profile based on the first state and the second state; determine that the state change satisfies an event condition; and store an association between the first node profile and an event type corresponding to the event condition.

Abstract: The present disclosure relates to systems and methods for updating email addresses based on email generation patterns. The method includes accessing a plurality of electronic activities used to update a plurality of member node profiles. The method includes determining that the plurality of member node profiles is linked to a group node profile of a group entity. The methods includes identifying, for each of the plurality of member node profiles, a first field-value pair of the member node profile corresponding to an email address. The method includes determining, for each member node profile, a correlation between the email address, a second field-value pair corresponding to a first name and a third field-value pair corresponding to a last name. The method includes determining, based on the determined correlation, an electronic account identifier pattern. The method includes storing an association between the group node and the electronic account identifier pattern.

Abstract: The present disclosure relates to systems and methods for automatic generation of summaries for record objects using one or more large language models. The system can identify a plurality of electronic activities matched to a record object of a customer relationship management system. The system can generate one or more text strings from the plurality of electronic activities using the large language models. The system can generate a first set of topics by inputting a first set of text strings into the large language models. The system can generate a second set of topics by inputting a first subset of text strings of the first set of text strings into the large language models. The system can transmit one or more topics to a computing device for presentation.

Abstract: The present disclosure relates to systems and methods for automatic generation of datasets for record objects using one or more large language models. A system can identify a plurality of electronic activities. The system can generate, using one or more large language models, a first set of text strings from the electronic activities. The system can store, in one or more data structures, a first association between the first set of text strings and the record object. The system can identify a second electronic activity. The system can generate, using the one or more large language models, a second set of text strings based on data corresponding to the second electronic activity and the first set of text strings. The system can store, in the one or more data structures, a second association between the second set of text strings and the record object.

Abstract: The present disclosure relates to systems and methods for automatic generation of summaries for record objects using one or more large language models. The system can identify a plurality of electronic activities matched to a record object of a customer relationship management system. The system can generate one or more text strings from the plurality of electronic activities using the large language models. The system can generate a first set of topics by inputting a first set of text strings into the large language models. The system can generate a second set of topics by inputting a first subset of text strings of the first set of text strings into the large language models. The system can transmit one or more topics to a computing device for presentation.

Abstract: The present disclosure relates to determining detecting blast electronic activities. A method can include identifying a plurality of first electronic activities transmitted by a first electronic account of a data source provider. For each first electronic activity of the plurality of first electronic activities, a plurality of features can be extracted. For at least one first electronic activity of the plurality of first electronic activities, a blast probability score can be generated indicating a likelihood that the at least one first electronic activity is a blast electronic activity. The blast probability score can be generated using a machine learning model trained using features extracted from second electronic activities labeled as blast electronic activities and features extracted from third electronic activities labeled as non-blast electronic activities. An association between the at least one first electronic activity and the blast probability score can be stored in a data structure.

Abstract: The present disclosure relates to methods, systems, and storage media for detecting events based on updates to node profiles from electronic activities. Exemplary implementations may access an electronic activity transmitted or received via an electronic account associated with a data source provider; generate a plurality of activity field-value pairs; maintain a plurality of node profiles; identify a first state of a first node profile of the plurality of node profiles; update the first node profile using the electronic activity; identify a second state of the first node profile subsequent to updating the first node profile using the electronic activity; detect a state change of the first node profile based on the first state and the second state; determine that the state change satisfies an event condition; and store an association between the first node profile and an event type corresponding to the event condition.

Abstract: The present disclosure relates to systems and methods for removing electronic activities from systems of record based on filtering policies. The method includes accessing record objects of one or more systems of record. The method includes identifying a plurality of electronic activities stored in a record object of one of the systems of record. The method includes parsing the plurality of electronic activities. The method includes determining that one of the electronic activities is associated with an electronic account corresponding to a data source provider. The method includes selecting one or more filtering policies associated with the electronic account. The method includes applying the selected one or more filtering policies to the plurality of electronic activities to identify a subset of electronic activities. The method includes initiating a process to cause removal of at least one electronic activity of the subset of electronic activities from the system of record.

Abstract: The present disclosure relates to systems and methods for matching electronic activities with record objects based on entity relationships. The method can include accessing a plurality of electronic activities, identifying an electronic activity, identifying a first participant associated with a first entity and a second participant associated with a second entity, determining whether a record object identifier is included in the electronic activity, identifying a first record object of the system of record that includes an instance of the record object identifier, and storing an association between the electronic activity and the first record object. The method can include determining a second record object corresponding to the second entity, identifying, using a matching policy, a third record object linked to the second record object and identifying a third entity, and storing, by the one or more processors, an association between the electronic activity and the third record object.

Abstract: The present disclosure relates to systems and methods for determining an engagement profile of a participant by associating electronic activities to a profile. It may generate the engagement profile based on analysis of the electronic activity level. An example implementation may contain the following steps. The system may access for a first record object a plurality of electronic activities linked with the first record object. The system may identify for a participant from the plurality of electronic activities a set of electronic activities including the participant. The system may determine an engagement profile of the participant based on a first number of electronic activities of the set of electronic activities sent by the participant, a second number of the set of electronic activities received by the participant and a temporal distribution of the set of electronic activities. The system may store the engagement profile in one or more data structures.

Abstract: The present disclosure relates to methods, systems, and storage media for detecting events based on updates to node profiles from electronic activities. Exemplary implementations may access an electronic activity transmitted or received via an electronic account associated with a data source provider; generate a plurality of activity field-value pairs; maintain a plurality of node profiles; identify a first state of a first node profile of the plurality of node profiles; update the first node profile using the electronic activity; identify a second state of the first node profile subsequent to updating the first node profile using the electronic activity; detect a state change of the first node profile based on the first state and the second state; determine that the state change satisfies an event condition; and store an association between the first node profile and an event type corresponding to the event condition.

Abstract: The present disclosure relates to methods, systems, and storage media for detecting events based on updates to node profiles from electronic activities. Exemplary implementations may access an electronic activity transmitted or received via an electronic account associated with a data source provider; generate a plurality of activity field-value pairs; maintain a plurality of node profiles; identify a first state of a first node profile of the plurality of node profiles; update the first node profile using the electronic activity; identify a second state of the first node profile subsequent to updating the first node profile using the electronic activity; detect a state change of the first node profile based on the first state and the second state; determine that the state change satisfies an event condition; and store an association between the first node profile and an event type corresponding to the event condition.

Abstract: The present disclosure relates to for managing the generation or deletion of record objects based on electronic activities and communication policies. Data of a plurality of electronic activities from one or more electronic accounts of the entity may be identified. It may be determined whether the identified data satisfies a communication policy. The communication policy may include one or more rules based on the electronic activities. Instructions to generate a contact record object or instructions to delete an existing contact record for the entity may be transmitted based on the condition of the communication of the communication policy that is satisfied.

Abstract: The present disclosure is directed to systems and methods of maintaining confidence scores of entity associations derived from systems of record. The system can access a record objects of systems of record. The system can identify, from a record object corresponding to a first group entity, an account relationship data structure specifying a relationship. The system can identify a first group node profile corresponding to the first group entity. The system can identify, for each second group entity, a second group node profile. The system can detect a change in a relationship of the group entities in the account relationship data structure or from electronic activities. The system can determine, between the first and a second group node profile, a relationship type in the change. The system can update, in a node graph, an edge between a first and a second group node profile to indicate the relationship type.

Abstract: The present disclosure relates to generating a filtered data set. Data from a plurality of systems of record of a plurality of data source providers may be accessed. A master data set generated using the data accessed from the plurality of systems of record may be maintained. Restriction policies including one or more rules for restricting sharing of data may be maintained. A filtered data set may be generated for a data source provider responsive to an application of restriction policies of other data source providers to the master data set. The filtered data set may be provisioned.

Abstract: The present disclosure relates to systems and methods for generating new node profiles using information from electronic activities. The system is configured to maintain node profiles corresponding to unique entities; access electronic activities transmitted or received via electronic accounts associated with data source providers; identify a first email address of a sender and second email addresses of respective recipients of an electronic activity; identify that the first email address matches a value of a field of a first node profile; link the electronic activity to the first node profile; determine that a second email address of a respective recipient of the electronic activity cannot be matched to any node profile associated with the respective participant; and generate, responsive to determining that the electronic activity cannot be matched to any node profile of the plurality of node profiles, a new node profile including the second email address of the respective recipient.

Abstract: The present disclosure relates to systems and methods for determining an engagement profile of a participant by associating electronic activities to a profile. It may generate the engagement profile based on analysis of the electronic activity level. An example implementation may contain the following steps. The system may access for a first record object a plurality of electronic activities linked with the first record object. The system may identify for a participant from the plurality of electronic activities a set of electronic activities including the participant. The system may determine an engagement profile of the participant based on a first number of electronic activities of the set of electronic activities sent by the participant, a second number of the set of electronic activities received by the participant and a temporal distribution of the set of electronic activities. The system may store the engagement profile in one or more data structures.

Abstract: The present disclosure relates to systems and methods for filtering electronic activities. The method includes identifying an electronic activity. The method includes parsing the electronic activity to identify one or more electronic accounts in the electronic activity. The method includes determining, responsive to parsing the electronic activity, that the electronic activity is associated with an electronic account of the one or more electronic accounts. The method includes selecting, based on the electronic account, one or more filtering policies associated with the data source provider to apply to the electronic activity. The method includes determining, by applying the selected one or more filtering policies to the electronic activity, to restrict the electronic activity from further processing based on the electronic activity satisfying at least one of the selected one or more filtering policies. The method includes restricting, the electronic activity from further processing.

Abstract: The present disclosure relates to methods, systems, and storage media for detecting events based on updates to node profiles from electronic activities. Exemplary implementations may access an electronic activity transmitted or received via an electronic account associated with a data source provider; generate a plurality of activity field-value pairs; maintain a plurality of node profiles; identify a first state of a first node profile of the plurality of node profiles; update the first node profile using the electronic activity; identify a second state of the first node profile subsequent to updating the first node profile using the electronic activity; detect a state change of the first node profile based on the first state and the second state; determine that the state change satisfies an event condition; and store an association between the first node profile and an event type corresponding to the event condition.