Determining semantic content of textual clusters
US-2020349199-A1 · Nov 5, 2020 · US
US12095634B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-12095634-B2 |
| Application number | US-202217886954-A |
| Country | US |
| Kind code | B2 |
| Filing date | Aug 12, 2022 |
| Priority date | Aug 12, 2022 |
| Publication date | Sep 17, 2024 |
| Grant date | Sep 17, 2024 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
Persistent storage contains a state machine for a request routing process and a plurality of requests related to the request routing process. One or more processors are configured to apply the state machine through operations including: obtaining a request from the plurality of requests; providing, to a criticality detection application and to an intent detection application, a representation of the request, wherein the criticality detection application is configured to detect a criticality of the request, and wherein the intent detection application is configured to determine a semantic intent of the request; receiving, from the criticality detection application and the intent detection application, respective indications of a detected criticality of the request and a detected intent of the request; determining whether to route the request to a channel that is one of a live agent, a virtual agent, or a search-based application; and routing the request to the channel as determined.
Opening claim text (preview).
What is claimed is: 1. A system comprising: persistent storage containing a state machine for a request routing process and a plurality of requests related to the request routing process; and one or more processors configured to apply the state machine through operations including: obtaining a request from the plurality of requests; providing, to a criticality detection application and to an intent detection application, a representation of the request, wherein the criticality detection application is configured to detect a criticality of the request, and wherein the intent detection application is configured to determine a semantic intent of the request; receiving, from the criticality detection application and the intent detection application, respective indications of a detected criticality of the request and a detected intent of the request; based at least on the detected criticality of the request and the detected intent of the request, and while the request is not assigned to an agent, selecting a channel from a plurality of channels to route the request, wherein the plurality of channels includes a live agent, a virtual agent, and a search-based application; and routing the request to the channel as selected. 2. The system of claim 1 , wherein selecting the channel from the plurality of channels to route the request comprises: determining that the detected criticality of the request is less than a pre-determined threshold criticality; in response to determining that the detected criticality of the request is less than the pre-determined threshold criticality, determining that the detected intent does not match any virtual agent topic supported by the virtual agent; and in response to determining that the detected intent does not match any virtual agent topic supported by the virtual agent, routing the request to the search-based application. 3. The system of claim 2 , wherein routing the request to the search-based application comprises: determining a preferred search channel of a user associated with the request, wherein the preferred search channel is either a web portal, email, or text message; routing the request to the preferred search channel; and providing, to the user, search-based results related to the request by way of the preferred search channel. 4. The system of claim 1 , wherein selecting the channel from the plurality of channels to route the request comprises: determining that the detected criticality of the request is greater than a pre-determined threshold criticality; and in response to determining that the detected criticality of the request is greater than the pre-determined threshold criticality, routing the request to the live agent. 5. The system of claim 1 , wherein the detected intent is associated with an intent confidence value, and wherein selecting the channel from the plurality of channels to route the request comprises: determining that the detected criticality of the request is less than a pre-determined threshold criticality; in response to determining that the detected criticality of the request is less than the pre-determined threshold criticality, determining that the intent confidence value is less than a pre-determined intent threshold; and in response to determining that the intent confidence value is less than the pre-determined intent threshold, routing the request to the live agent. 6. The system of claim 1 , wherein selecting the channel from the plurality of channels to route the request comprises: determining that the detected criticality of the request is less than a pre-determined threshold criticality; in response to determining that the detected criticality of the request is less than the pre-determined threshold criticality, determining that the detected intent matches a virtual agent topic supported by the virtual agent; and in response to determining that the detected intent matches the virtual agent topic supported by the virtual agent, routing the request to the virtual agent. 7. The system of claim 1 , wherein the request includes textual content, and wherein the criticality detection application is configured to detect a criticality of the request based on presence or absence of a sensitive personal problem, an indication of a problem with a multi-user impact, or an indication of timeliness within the textual content. 8. The system of claim 1 , wherein providing the representation of the request comprises: providing, to a pre-processor, the request; obtaining, from the pre-processor, a modified version of the request; and providing, to the criticality detection application and to the intent detection application, the modified version of the request. 9. The system of claim 1 , wherein receiving the respective indications of the detected criticality of the request and the detected intent of the request comprises: receiving, from the criticality detection application and the intent detection application, respective initial indications of the detected criticality of the request and the detected intent of the request; providing, to a post-processor, one or more of the respective initial indications of the detected criticality of the request and the detected intent of the request; and obtaining, from the post-processor, modified versions of the one or more of the respective initial indications of the detected criticality of the request and the detected intent of the request. 10. The system of claim 1 , wherein providing the representation of the request comprises also providing the representation of the request to a language detection application, wherein the language detection application is configured to detect a language in which the request is written, the operations further comprising: receiving, from the language determine application, an indication of a detected language of the request, wherein determining whether to route the request to the channel is also based on the detected language. 11. The system of claim 1 , wherein the request is initially assigned to a virtual agent queue for processing, and wherein the request is removed from the virtual agent queue when it is routed to the live agent or the search-based application. 12. The system of claim 1 , wherein the request is initially routed to the virtual agent, the operations further comprising: determining that a user associated with the request has rejected a recommendation from the virtual agent, requested the live agent, or has not replied to a query from the virtual agent within a pre-determined period of time; and re-routing the request to the live agent. 13. A computer-implemented method comprising: obtaining, by a computing system, a request from a plurality of requests; providing, by the computing system, to a criticality detection application and to an intent detection application, a representation of the request, wherein the criticality detection application is configured to detect a criticality of the request, and wherein the intent detection application is configured to determine a semantic intent of the request; receiving, by the computing system, from the criticality detection application and the intent detection application, respective indications of a detected criticality of the request and a detected intent of the request; based at least on the detected criticality of the request and the detected intent of the request, and while the request is not assigned to an agent, selecting, by the computing system, a channel from a plurality of channels to route the request, wherein the plurality of channels includes a live agent, a virtual agent, and a search-based application; and
Handling of user complaints or trouble tickets · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.