# US 2020/0403944 A1 · Chatbot support platform

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

- Number: US 2020/0403944 A1
- Document ID: US20200403944A1
- Status: Published application
- Kind: A1
- Application number: 16/444,609
- Filed: 2019-06-18
- Published: 2020-12-24
- Earliest claimed: 2019-06-18
- Assignees: Accenture Global Solutions Limited
- Applicants: Accenture Global Solutions Limited
- Inventors: Armish JOSHI; Sanjoy GHOSH; Vedika Vinay SAWANT; Prashant SAXENA
- Web page: https://patentgrep.com/patent/US20200403944A1

## CPC

- H04L 51/02: using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
- G06F 9/543: {User-generated data transfer, e.g. clipboards, dynamic data exchange [DDE], object linking and embedding [OLE]}
- G06F 9/547: {Remote procedure calls [RPC]; Web services}
- G06F 16/2365: {Ensuring data consistency and integrity}
- G06F 16/90332: {Natural language query formulation or dialogue systems}
- G06F 16/9535: Search customisation based on user profiles and personalisation
- H04L 41/20: {Network management software packages}
- H04L 41/50: Network service management, e.g. ensuring proper service fulfilment according to agreements
- H04L 41/5051: Service on demand, e.g. definition and deployment of services in real time
- H04L 41/5064: {Customer relationship management}
- H04L 41/0806: for initial configuration or provisioning, e.g. plug-and-play
- H04L 41/0895: Configuration of virtualised networks or elements, e.g. virtualised network function or OpenFlow elements
- H04L 41/16: using machine learning or artificial intelligence
- H04L 41/40: using virtualisation of network functions or resources, e.g. SDN or NFV entities
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A device receives, based on a user interaction with a chatbot, request data for a request for a service associated with a software tool that is part of a service management system. The device identifies, based on the request data, the service that is being requested and a first set of entity data for a first set of entities relating to the service. The device obtains a second set of entity data for a second set of entities by using an application programming interface (API) to reference a data structure that is associated with the service management system and that stores the second set of entity data. The device causes one or more components of the service management system to use the first set of entity data to execute a set of actions to perform the service.

## Claims

### Claim 1

A method, comprising:
receiving, by a device and based on a user interaction with a chatbot, request data for a request for a service associated with a software tool that is part of a service management system;
identifying, by the device and based on the request data, the service that is being requested and a first set of entity data for a first set of entities relating to the service;
determining, by the device and based on the identified service and the first set of entity data, that a second set of entity data for a second set of entities is needed in order to provide the service;
obtaining, by the device, the second set of entity data for the second set of entities based on at least one of:
another user interaction with the chatbot, or
a search query to reference a data structure that is associated with the service management system and that stores the second set of entity data;
causing, by the device, a validation procedure to be performed to validate the first set of entity data or the second set of entity data; and
causing, by the device, one or more components of the service management system to use validated entity data to execute a set of actions to perform the service.

### Claim 2 (depends on 1)

The method of claim 1, wherein identifying the identified service and the first set of entity data comprises:
processing terms included in the request using a data model that has been trained using machine learning to generate a set of service scores that indicate likelihoods of particular terms identifying particular services that are part of a set of available services,
selecting the service identifier, from a list of service identifiers for the set of available services, based on the set of service scores, and
processing the terms included in the request using one or more natural language processing techniques to identify the first set of entity data for the first set of entities relating to the service.

### Claim 3 (depends on 1)

The method of claim 1, wherein causing the validation procedure to be performed comprises:
selecting, based on the identified service, an application programming interface (API) that is to be used to validate a subset of the first set of entity data for an entity included in the first set of entities, and
providing, via the selected API, a validation request to another device to cause the other device to provide the device with a validation response that indicates whether the subset of the first set of entity data has been validated.

### Claim 4 (depends on 1)

The method of claim 1, wherein obtaining the second set of entity data comprises:
causing the chatbot to display a follow-up question via a chatbot interface, and receiving, from a user device associated with the user, response data that includes a subset of the second set of entity data for at least one of the second set of entities.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
standardizing a format of at least one of the first set of entity data or the second set of entity data by referencing a data structure.

### Claim 6 (depends on 1)

The method of claim 1, further comprising:
receiving user action data that describes one or more operations performed by the user while accessing the software tool;
providing the user action data as input to an application programming interface (API) to cause a data model that has been trained using machine learning to process the user action data to generate a set of recommended service scores for a set of available services;
generating recommendation data for a recommendation to provide the user with another service based on the set of recommended service scores; and
causing the recommendation to be provided to an interface accessible to the user.

### Claim 7 (depends on 1)

The method of claim 1, further comprising:
receiving feedback data from a particular user that has identified at least one false positive in the first set of entity data; and
retraining a data model that is used to identify the first set of entities based on the feedback data.

### Claim 8

A device, comprising:
one or more memories; and
one or more processors, operatively coupled to the one or more memories, to:
determine to provide a user with a service associated with a software tool that is part of a service management system based on:
request data for a request that the user has submitted for the service based on a user interaction with a chatbot, or
recommendation data for a recommendation to provide the user with the service based on user activity data associated with one or more operations performed by the user via the software tool;
identify entity data for a set of entities relating to the service,
wherein the entity data is identified from at least one of:
the request data,
another user interaction with the chatbot, or
a data structure that is associated with the service management system and that stores the entity data;
cause a validation procedure to be performed to validate the entity data; and
cause one or more components of the service management system to use validated entity data to execute a set of actions to perform the service.

### Claim 9 (depends on 8)

The device of claim 8, wherein the one or more processors, when determining to provide the user with the service, are to:
determine to provide the user with the service based on receiving the request data,
wherein the request data includes a service identifier for the service that is being requested; and
wherein the one or more processors, when identifying the entity data, are to:
identify a first set of entity data for a first subset of entities, of the set of entities relating to the service, by processing the request data, and
identify a second set of entity data for a second subset of entities, of the set of entities relating to the service, by instructing the chatbot to display an entity request message to the user via a chatbot interface to permit an entity response message that includes the second set of entity data to be provided to the device.

### Claim 10 (depends on 8)

The device of claim 8, wherein the one or more processors, when determining to provide the user with the service, are to:
determine to provide the user with the service based on receiving the request data,
wherein the request data includes a service identifier for the service that is being requested; and
wherein the one or more processors, when identifying the entity data, are to:
identify a first set of entity data for a first subset of entities, of the set of entities relating to the service, by processing the request data, and
identify a second set of entity data for a second subset of entities, of the set of entities relating to the service, by performing a search query to reference the data structure associated with the service management system to cause a search response that includes the second set of entity data to be provided to the device.

### Claim 11 (depends on 8)

The device of claim 8, wherein the one or more processors, when determining to provide the user with the service, are to:
receive user activity data that describes one or more operations performed by the user while accessing the software tool,
provide the user activity data as input to a data model that has been trained using machine learning to cause the data model to output a set of recommended service scores that indicate likelihoods of particular services being appropriate services to recommend to the user,
generate the recommendation data based on the set of recommended service scores, and
determine to provide the user with the service based on the recommendation data.

### Claim 12 (depends on 8)

The device of claim 8, wherein the set of entities include at least one of:
an identifier of the user,
an identifier of the software tool,
an identifier of the service management system,
an identifier of a role that the user has within an organization,
an identifier of an operation that is capable of being performed as part of the role, or
an identifier of a priority level of the service requested by the user.

### Claim 13 (depends on 8)

The device of claim 8, wherein the one or more processors, when causing the validation procedure to be performed, are to:
identify, based on a service identifier for the service, a subset of entities, of the set of entities, that are to be validated,
select, based on the service identifier for the service, an application programming interface (API) that is to be used to validate particular entity data for one or more entities of the set of entities, and
provide, via the API, a validation request to another device to cause the other device to provide the device with a validation response that indicates whether the particular entity data has been validated.

### Claim 14 (depends on 8)

The device of claim 8, wherein the one or more processors are further to:
select, based on a service identifier for the service, an application programming interface (API) that is to be used to cause the one or more components of the service management system to execute the set of actions to perform the service; and
wherein the one or more processors, when causing the one or more components of the service management system to perform the set of actions to provide the service, are to:
provide the validated entity data to the one or more components of the service management system via the API to cause the one or more components to execute the set of actions to perform the service.

### Claim 15

A non-transitory computer-readable medium storing instructions, the instructions comprising:
one or more instructions that, when executed by one or more processors of a device, cause the one or more processors to:
receive, based on a user interaction with a chatbot, request data for a request for a service associated with a software tool that is part of a service management system;
identify, based on the request data, the service that is being requested;
identify, based on the request data, a first set of entity data for a first set of entities relating to the service;
obtain a second set of entity data for a second set of entities by using an application programming interface (API) to reference a data structure that is associated with the service management system and that stores the second set of entity data; and
cause one or more components of the service management system to use the first set of entity data and the second set of entity data to execute a set of actions to perform the service.

### Claim 16 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the first set of entity data and the second set of entity data are collectively as a third set of entity data;
wherein the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:
select, based on the identified service identifier, a second API that is to be used to validate a subset of the third set of entity data; and
provide, via the second API, a validation request to another device to cause the other device to provide the device with a validation response that indicates whether the subset of the third set of entity data has been validated.

### Claim 17 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the one or more instructions, that cause the one or more processors to identify the service, cause the one or more processors to:
provide, via another API, the request data to a machine learning engine to cause the machine learning engine to execute a machine learning module to process the request data and to select the service identifier for the service, from a set of service identifiers for a set of available services;
receive the service identifier for the service via the other API; and
wherein the one or more instructions, that cause the one or more processors to identify the first set of entity data, cause the one or more processors to:
provide, via the other API, the request data to a natural language processing engine to cause the natural language processing engine to process the request data to identify the first set of entity data for the first set of entities, and
receive the first set of entity data via the other API.

### Claim 18 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the set of actions to perform the service include:
receiving service data from a service management system using one or more application programming interfaces (APIs),
generating response data based on the received service data, and
causing the response data to be made available to another device or account associated with a user.

### Claim 19 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:
receive user action data that describes one or more operations performed by the user while accessing the software tool;
provide the user action data as input to an application programming interface (API) to cause a data model that has been trained using machine learning to process the user action data to generate a set of recommended service scores for a set of available services;
generate recommendation data for a recommendation to provide the user with another service based on the set of recommended service scores; and
cause the recommendation to be provided to an interface accessible to the user.

### Claim 20 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:
receive feedback data from a particular user that has identified at least one false positive in the first set of entity data; and
retrain a data model that is used to identify the first set of entities based on the feedback data.
