# US 2021/0342536 A1 · Recommender and remediation system for enterprise service management

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0342536 A1
- Document ID: US20210342536A1
- Status: Published application
- Kind: A1
- Application number: 16/634,656
- Filed: 2020-01-20
- Published: 2021-11-04
- Earliest claimed: 2019-01-21
- Assignees: BayesTree Intelligence Pvt Ltd.
- Applicants: BayesTree Intelligence Pvt Ltd.
- Inventors: Partha Pratim GHOSH; Girish KOPPAR; Avijit BISWAS; Jatin PURI; Nabarun MONDAL
- Web page: https://patentgrep.com/patent/US20210342536A1

## CPC

- G06F 40/279: Recognition of textual entities
- G06F 16/313: {Selection or weighting of terms for indexing}
- G06F 16/319: {Inverted lists}
- G06F 16/35: Clustering; Classification
- G06F 40/169: Annotation, e.g. comment data or footnotes
- G06F 40/205: Parsing
- G06N 5/022: Knowledge engineering; Knowledge acquisition
- H04L 41/5074: Handling of user complaints or trouble tickets
- G06Q 10/20: Administration of product repair or maintenance
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

A system and method for automatically and algorithmically resolving service tickets through the utilization of historical solution data obtained from multiple sources. The system and method are optionally capable of providing and executing a BOT capable of implementing one or solutions based on the automatic and algorithmic recommendation of a solution to resolve the service ticket(s).

## Claims

### Claim 1

A computer-implemented method for automatically providing a solution to a problem ticket to an end-user, comprising the steps of:
providing at least one problem ticket in an electronic format,
wherein the problem ticket has multiple fields that each contain a portion of text;
normalizing, by a processor, each portion of text to create a modified version of each portion of text which is stored in a memory;
generating, by the processor, a plurality of problem inverted indices for each of the multiple fields of the at least one problem ticket, based on the modified version of each portion of text created in the previous step;
weighting, by the processor, the plurality of problem inverted indices to assist in the automatic recommendation;
providing a database containing a plurality of index solution tickets, each index solution ticket having at least one field where the at least one field correlates at least in part to the multiple fields of the problem ticket and one or more proposed solutions;
performing a similarity calculation on the plurality of index solution tickets, by the processor, to determine a most-similar index solution ticket to the problem ticket;
determining, by the processor, the most-similar index solution ticket in the database automatically providing the most-similar index solution ticket and the corresponding one or more proposed solutions to the end-user.

### Claim 2 (depends on 1)

The method of claim 1, wherein each of the multiple fields are selected from the group consisting essentially of: title, description, and resolution.

### Claim 3 (depends on 1)

The method of claim 1, the step of “normalizing, by a processor, each portion of text to create a modified version of each portion of text which is stored in a memory” further comprises:
processing, by the processor, each portion of text with a language parser and storing each processed portion in the memory;
subsequently replacing, by the processor each word in the processed portion from the above step with all-lowercase versions of each word and storing the replacement in the memory;
removing, by the processor, stop words from each portion of text from the above step; and
reducing, by the processor, each word on each portion of text from the above step to each word's word stem.

### Claim 4 (depends on 1)

The method of claim 1, wherein the plurality of problem inverted indices is based on a method selected from the group consisting of: tfidf; tf; idf, and length-of-document.

### Claim 5 (depends on 1)

The method of claim 1, wherein the plurality of problem inverted indices are given a static weight assignment by the processor.

### Claim 6 (depends on 1)

The method of claim 1, wherein the plurality of problem inverted indices are given a dynamic weight assignment by the processor.

### Claim 7 (depends on 3)

The method of claim 3, wherein the similarity calculation comprises:
extending, by the processor, the multiple fields of the problem ticket;
assigning, by the processor, a category for each of the plurality of problem inverted indices, where problem inverted indices relating to the same field are assigned to the same category;
calculating, by the processor, a first similarity measure of each of the plurality of problem inverted indices against each of the plurality of index solution tickets;
joining, by the processor, each of the plurality of index solution tickets when the first similarity measure of each field is above a threshold amount;
extending, by the processor, the multiple fields of the joined index solution tickets;
calculating, by the processor, a second similarity measure of each field of the problem ticket with each grouped field of the joined index solution tickets;
providing, by the processor, the top x results of the plurality of index solution tickets based on the first similarity measure and the second similarity measure, sampled from the top (x*a) results of the plurality of index solutions tickets, where a is an integer multiple of x.

### Claim 8 (depends on 7)

The method of claim 7, wherein the database containing the plurality of index solution tickets is populated from a plurality of documents selected from the group consisting of: standard operating procedures, knowledge base articles, and FAQ sections of related websites,
wherein each of the plurality of documents is manually annotated, by a human user, with at least one piece of relevant metadata to aid in the step of “performing a similarity calculation on the plurality of index solution tickets, by the processor, to determine a most-similar index solution ticket to the problem ticket”.

### Claim 9 (depends on 8)

The method of claim 8, further comprising the steps of:
providing at least one BOT containing a linked, executable electronic file, configured to implement the one or more proposed solutions contained in the automatically provided index solution ticket;
manually annotating, by a human user, each of the at least one BOTs with a portion of the at least one piece of relevant metadata corresponding to the at least one of the multiple fields in the problem ticket;
populating the database with the annotated BOTs, such that each annotated BOT is listed as one of the plurality of index solution ticket within said database.

### Claim 10 (depends on 9)

The method of claim 9, further comprising the step of:
executing, by a second processor, one of the at least one annotated BOTs when it is identified as the most-similar solution ticket such that said BOT implements the one or more proposed solutions on an end-user's device that is experiencing the problem listed in the problem ticket.
