发明名称 AUTOMATIC CRM DATA ENTRY
摘要 A method for data processing includes obtaining from multiple different organizations (24, 52, 54, 56) customer relationship management (CRM) records (110) and communication records (90). Reference vectors (130) of feature values are computed for the communication records in a training set. Global weights are computed for the feature values by evaluating the reference vectors for all of the different organizations. For each organization, respective company weights are computed by evaluating specifically the reference vectors computed over the CRM records and communication records belonging to the organization. For each person belonging to a given organization, respective user weights are computed for the feature values by evaluating specifically the reference vectors computed over the communication records that identify the person as the user. The weights are applied in order to assign the communication records that are not in the training set to respective ones of the CRM records.
申请公布号 US2016247163(A1) 申请公布日期 2016.08.25
申请号 US201415021695 申请日期 2014.10.14
申请人 IMPLISIT INSIGHTS LTD. 发明人 Donsky Elad;Raichshtain Gilad
分类号 G06Q30/00;G06F17/30 主分类号 G06Q30/00
代理机构 代理人
主权项 1. A method for data processing, comprising: obtaining from each organization among multiple different organizations: a respective first plurality of customer relationship management (CRM) records belonging to the organization, each CRM record comprising multiple CRM fields containing first data; anda respective second plurality of communication records belonging to the organization, including a set of the communication records that have been assigned to respective CRM records within the first plurality, each communication record comprising multiple communication record fields containing second data relating to a communication and identifying at least a user of the communication; computing respective reference vectors of feature values for the communication records in the set, each feature value indicating a degree of correspondence between a second datum in a specified communication record field of a given communication record and a first datum in a specified CRM field of a respective CRM record to which the given communication record has been assigned; computing global weights for the feature values by evaluating the reference vectors computed for all of the different organizations; computing, for each organization, respective company weights for the feature values by evaluating specifically the reference vectors computed over the CRM records and communication records belonging to the organization; computing, for each person belonging to a given organization, respective user weights for the feature values by evaluating specifically the reference vectors computed over the communication records that identify the person as the user; computing further vectors of the feature values for the communication records that are not in the set, and applying the global weights, company weights, and user weights to the further vectors in order to assign the communication records that are not in the set to respective ones of the CRM records; and inserting entries in the respective ones of the CRM records to indicate the communication records that have been assigned thereto.
地址 Tel Aviv IL