Entity detection in messages
A messaging server that concurrently provides a business or other recipient with a message sent to the recipient and the set of entities detected within the message using natural language processing (NLP). A business interacts with the messaging server to specify the types of NLP to perform on messages received by the business. The messaging server creates a configuration token describing the specified NLP configuration. The messaging server receives a message sent from a client to the business and generates a payload describing the message and including the configuration token. The messaging server then sends the payload to a NLP server. The NLP server performs NLP on the message in the payload according to the configuration specified by the token to detect a set of entities. The messaging server forms an enriched payload including the message and detected entities and forwards the enriched payload to the business.
1. A method comprising:
receiving a message having message content and sent by a client to a recipient;
determining, from the received message, a page in an online system and a messaging bot associated with the message;
retrieving a configuration token from a repository responsive to the determined page and messaging bot;
providing a message payload including the message content and the configuration token to a NLP server, the configuration token specifying natural language processing (NLP) to perform on the message content;
receiving a response to the message payload from the NLP server, the response including a set of entities detected in the message content responsive to the NLP specified by the configuration token; and
providing an enriched payload including the message content and the response to the message payload to the messaging bot.
2. The method of claim 1 , further comprising:
receiving, from the recipient, registration of the messaging bot to process messages sent to the recipient;
receiving a specification of NLP processing to perform on message content in messages sent to the messaging bot; and
creating the configuration token responsive to the received specification of NLP processing.
3. The method of claim 1 , further comprising:
receiving a response payload from the recipient, the recipient having generated the response payload responsive to receiving the enriched payload;
forming a response message based on the response payload; and
forwarding the response message to the client.
4. The method of claim 1 , further comprising:
normalizing the message content; and
forming the message payload using the normalized message content and the retrieved configuration token.
5. The method of claim 1 , wherein the NLP server is adapted to parse the configuration token to determine a NLP configuration specifying the NLP to perform on the message content and to perform the NLP to detect the set of entities in the message content.
6. The method of claim 1 , wherein the response received from the NLP server comprises the set of entities detected in the message content and metadata describing the entities, and wherein the enriched payload provided to the recipient includes the set of entities and the metadata.
7. A non-transitory computer-readable medium storing computer program instructions executable by a processor to perform operations comprising:
receiving a message having message content and sent by a client to a recipient;
determining, from the received message, a page in an online system and a messaging bot associated with the message;
retrieving a configuration token from a repository responsive to the determined page and messaging bot;
providing a message payload including the message content and the configuration token to a NLP server, the configuration token specifying natural language processing (NLP) to perform on the message content;
receiving a response to the message payload from the NLP server, the response including a set of entities detected in the message content responsive to the NLP specified by the configuration token; and
providing an enriched payload including the message content and the response to the message payload to the messaging bot.
8. The computer-readable medium of claim 7 , the operations further comprising:
receiving, from the recipient, registration of the messaging bot to process messages sent to the recipient;
receiving a specification of NLP processing to perform on message content in messages sent to the messaging bot; and
creating the configuration token responsive to the received specification of NLP processing.
9. The computer-readable medium of claim 7 , the operations further comprising:
receiving a response payload from the recipient, the recipient having generated the response payload responsive to receiving the enriched payload;
forming a response message based on the response payload; and
forwarding the response message to the client.
10. The computer-readable medium of claim 7 , the operations further comprising:
normalizing the message content; and
forming the message payload using the normalized message content and the retrieved configuration token.
11. The computer-readable medium of claim 7 , wherein the NLP server is adapted to parse the configuration token to determine a NLP configuration specifying the NLP to perform on the message content and to perform the NLP to detect the set of entities in the message content.
12. The computer-readable medium of claim 7 , wherein the response received from the NLP server comprises the set of entities detected in the message content and metadata describing the entities, and wherein the enriched payload provided to the recipient includes the set of entities and the metadata.
13. A computer system comprising:
a computer processor adapted to execute computer program instructions; and
a non-transitory computer-readable storage medium storing computer program instructions executable by the processor to perform operations comprising:
receiving a message having message content and sent by a client to a recipient;
determining, from the received message, a page in an online system and a messaging bot associated with the message;
retrieving a configuration token from a repository responsive to the determined page and messaging bot;
providing a message payload including the message content and the configuration token to a NLP server, the configuration token specifying natural language processing (NLP) to perform on the message content;
receiving a response to the message payload from the NLP server, the response including a set of entities detected in the message content responsive to the NLP specified by the configuration token; and
providing an enriched payload including the message content and the response to the message payload to the messaging bot.
14. The computer system of claim 13 , the operations further comprising:
receiving, from the recipient, registration of the messaging bot to process messages sent to the recipient;
receiving a specification of NLP processing to perform on message content in messages sent to the messaging bot; and
creating the configuration token responsive to the received specification of NLP processing.
15. The computer system of claim 13 , the operations further comprising:
receiving a response payload from the recipient, the recipient having generated the response payload responsive to receiving the enriched payload;
forming a response message based on the response payload; and
forwarding the response message to the client.
16. The computer system of claim 13 , the operations further comprising:
normalizing the message content; and
forming the message payload using the normalized message content and the retrieved configuration token.
17. The computer system of claim 13 , wherein the NLP server is adapted to parse the configuration token to determine a NLP configuration specifying the NLP to perform on the message content and to perform the NLP to detect the set of entities in the message content.