Automated identification of hardware and software components relevant to incident reports

A system, comprising:

• a processor;
• and
• a memory, accessible by the processor, and storing instructions that, when executed by the processor, cause the processor to perform operations comprising:
• receiving an incident report that is not linked to a configuration item;
• generating a feature vector for the received incident report, wherein the feature vector comprises a plurality of keys, each key of the plurality of keys having a respective key value, wherein each key of the plurality of keys corresponds to a respective word of a plurality of words in the incident report, and wherein the respective key value for each of the plurality of keys represents a number of occurrences of the respective word in the incident report;
• comparing the generated feature vector to one or more feature vectors of a plurality of feature vectors stored in a database, wherein each of the plurality of feature vectors corresponds to a respective past incident report of a plurality of past incident reports stored in the database;
• based on the comparison, identifying a set of candidate incident reports of the plurality of incident reports that are potentially related to the received incident report;
• determining whether a particular configuration item of a plurality of configuration items stored in the database is associated with the received incident report based on whether the particular configuration item is linked to at least a threshold number of incident reports from the set of candidate incident reports;
• in response to determining that none of the plurality of configuration items is associated with the received incident report, initiating a network discovery process to discover one or more new configuration items;
• and
• updating the plurality of configuration items to include the one or more new configuration items.

A non-transitory, computer-readable medium storing instructions, that when executed by one or more processors, cause the one or more processors to perform operations comprising:

• receiving an incident report that is not linked to a configuration item;
• generating a feature vector for the received incident report, wherein the feature vector comprises a plurality of keys, each key of the plurality of keys having a respective key value, wherein each key of the plurality of keys corresponds to a respective word of a plurality of words in the incident report, and wherein the respective key value for each of the plurality of keys represents a number of occurrences of the respective word in the incident report;
• comparing the generated feature vector to one or more feature vectors of a plurality of feature vectors stored in a database, wherein each of the plurality of feature vectors corresponds to a respective past incident report of a plurality of past incident reports stored in the database;
• based on the comparison, identifying a set of candidate incident reports of the plurality of incident reports that are potentially related to the received incident report;
• determining whether a particular configuration item of a plurality of configuration items stored in the database is associated with the received incident report based on whether the particular configuration item is linked to at least a threshold number of incident reports from the set of candidate incident reports;
• in response to determining that the particular configuration item of the plurality of configuration items is associated with the received incident report:
• linking the particular configuration item to the received incident report;
• and
• storing, in the database, the link between the received incident report and the particular configuration item;
• and
• in response to determining that none of the plurality of configuration items is associated with the received incident report:
• initiating a network discovery process to discover one or more new configuration items;
• and
• updating the plurality of configuration items to include the one or more new configuration items.