# US 2023/0069088 A1 · Grouping Events and Generating a Textual Content Reporting the Events

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

- Number: US 2023/0069088 A1
- Document ID: US20230069088A1
- Status: Published application
- Kind: A1
- Application number: 17/976,807
- Filed: 2022-10-30
- Published: 2023-03-02
- Earliest claimed: 2021-10-31
- Inventors: Ron Zass; Ben Avi Ingel
- Web page: https://patentgrep.com/patent/US20230069088A1

## CPC

- G06F 40/40: Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30)
- G06F 16/433: {using audio data}
- G06F 16/483: using metadata automatically derived from the content
- G06F 16/685: {using automatically derived transcript of audio data, e.g. lyrics (speech recognition G10L15/00)}
- G06F 16/686: {using information manually generated, e.g. tags, keywords, comments, title or artist information, time, location or usage information, user ratings}
- G06F 40/253: Grammatical analysis; Style critique
- G06F 40/30: Semantic analysis
- G06F 40/56: Natural language generation
- G06V 10/82: using neural networks
- G06V 20/41: {Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items (segmenting video sequences G06V20/49)}
- G06V 20/44: {Event detection}
- G06V 20/50: Context or environment of the image
- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- G06V 20/70: Labelling scene content, e.g. deriving syntactic or semantic representations
- G10L 15/26: Speech to text systems (G10L15/08 takes precedence)
- G10L 25/51: for comparison or discrimination
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

Systems, methods and non-transitory computer readable media for grouping events and generating a textual content reporting the events are provided. An indication of a plurality of events may be received. A group of two or more events of the plurality of events may be identified. The group of events may not include at least a particular event of the plurality of events. A quantity associated with the group of events may be determined. A description of the group of events that includes an indication of the quantity may be generated. Data associated with the particular event may be analyzed to generate a description of the particular event. A textual content that includes the description of the group of events and the description of the particular event may be generated. The generated textual content may be provided.

## Claims

### Claim 1

A non-transitory computer readable medium storing a software program comprising data and computer implementable instructions that when executed by at least one processor cause the at least one processor to perform operations for generating a textual content selectively reporting events, the operations comprising:
receiving an indication of a plurality of events;
identifying a group of two or more events of the plurality of events, the group of two or more events does not include at least a particular event of the plurality of events;
determining a quantity associated with the group of two or more events;
generating a description of the group of two or more events, the description of the group of two or more events includes an indication of the quantity associated with the group of two or more events;
analyzing data associated with the particular event to generate a description of the particular event;
generating a textual content that includes the description of the group of two or more events and the description of the particular event, wherein for at least one specific event of the group of two or more events, the textual content does not include information identifying the specific event; and
providing the generated textual content.

### Claim 2 (depends on 1)

The non-transitory computer readable medium of claim 1, wherein each event in the group of two or more events is associated with a number, and the quantity associated with the group of two or more events is a function of the numbers associated with the events in the group of two or more events.

### Claim 3 (depends on 1)

The non-transitory computer readable medium of claim 1, wherein each event in the group of two or more events is associated with image data, and the operations further comprise:
for each event in the group of two or more events, analyzing the image data associated with the event to determine data associated with the event; and
determining the quantity associated with the group of two or more events based on the data associated with the group of two or more events.

### Claim 4 (depends on 1)

The non-transitory computer readable medium of claim 1, wherein each event in the group of two or more events is associated with audio data, and the operations further comprise:
for each event in the group of two or more events, analyzing the audio data associated with the event to determine data associated with the event; and
determining the quantity associated with the group of two or more events based on the data associated with the group of two or more events.

### Claim 5 (depends on 1)

The non-transitory computer readable medium of claim 1, wherein each event in the group of two or more events is associated with an object, and the operations further comprise determining the quantity associated with the group of two or more events based on the objects associated with the group of two or more events.

### Claim 6 (depends on 1)

The non-transitory computer readable medium of claim 1, wherein each event of the plurality of events is associated with image data, and the identification of the group of two or more events of the plurality of events is based on an analysis of the image data associated with the plurality of events.

### Claim 7 (depends on 6)

The non-transitory computer readable medium of claim 6, wherein the operations further comprise:
calculating a convolution of at least part of the image data and thereby obtain a result value of the calculated convolution of the at least part of the image data; and
basing the identification of the group of two or more events of the plurality of events on the result value of the calculated convolution of the at least part of the image data.

### Claim 8 (depends on 1)

The non-transitory computer readable medium of claim 1, wherein each event of the plurality of events is associated with audio data, and the identification of the group of two or more events of the plurality of events is based on an analysis of the audio data associated with the plurality of events.

### Claim 9 (depends on 1)

The non-transitory computer readable medium of claim 1, wherein the identification of the group of two or more events of the plurality of events is based on a writer persona, and the generated description of the group of two or more events is in a style associated with the writer persona.

### Claim 10 (depends on 1)

The non-transitory computer readable medium of claim 1, wherein the identification of the group of two or more events of the plurality of events is based on a prospective audience, and the generated description of the group of two or more events is in a style associated with the prospective audience.

### Claim 11 (depends on 1)

The non-transitory computer readable medium of claim 1, wherein the identification of the group of two or more events of the plurality of events is based on a topic associated with the generated textual content.

### Claim 12 (depends on 1)

The non-transitory computer readable medium of claim 1, wherein the operations further comprise:
for each event of the plurality of events, determining a mathematical object in a mathematical space corresponding to the event; and
basing the identification of the group of two or more events of the plurality of events on the mathematical objects corresponding to the plurality of events.

### Claim 13 (depends on 1)

The non-transitory computer readable medium of claim 1, wherein the operations further comprise:
receiving first modality data captured from an environment using at least one sensor of a first type of sensors;
receiving second modality data captured from the environment using at least one sensor of a second type of sensors, the second type of sensors differs from the first type of sensors;
analyzing at least part of the first modality data to identifying the group of two or more events of the plurality of events; and
analyzing at least part of the second modality data to determine the quantity associated with the group of two or more events.

### Claim 14 (depends on 1)

The non-transitory computer readable medium of claim 1, wherein generating the textual content includes selecting an order for the description of the group of two or more events and the description of the particular event in the generated textual content.

### Claim 15 (depends on 1)

The non-transitory computer readable medium of claim 1, wherein generating the textual content includes selecting a conjunction for the description of the group of two or more events and the description of the particular event, and wherein the generated textual content includes: the description of the group of two or more events, followed by the selected conjunction, followed by the description of the particular event.

### Claim 16 (depends on 1)

The non-transitory computer readable medium of claim 1, wherein the generated textual content does not include information identifying any specific event of the group of two or more events.

### Claim 17 (depends on 1)

The non-transitory computer readable medium of claim 1, wherein the operations further comprise:
analyzing data associated with the group of two or more events to select an adjective; and
including the selected adjective in the generated description of the group of two or more events.

### Claim 18 (depends on 1)

The non-transitory computer readable medium of claim 1, wherein the operations further comprise:
analyzing data associated with the group of two or more events to select an adverb; and
including the selected adverb in the generated description of the group of two or more events.

### Claim 19

A system for generating a textual content selectively reporting events, the system comprising:
at least one processing unit configured to perform the operations of:
receiving an indication of a plurality of events;
identifying a group of two or more events of the plurality of events, the group of two or more events does not include at least a particular event of the plurality of events;
determining a quantity associated with the group of two or more events;
generating a description of the group of two or more events, the description of the group of two or more events includes an indication of the quantity associated with the group of two or more events;
analyzing data associated with the particular event to generate a description of the particular event;
generating a textual content that includes the description of the group of two or more events and the description of the particular event, wherein for at least one specific event of the group of two or more events, the textual content does not include information identifying the specific event; and
providing the generated textual content.

### Claim 20

A method for generating a textual content selectively reporting events, the method comprising:
receiving an indication of a plurality of events;
identifying a group of two or more events of the plurality of events, the group of two or more events does not include at least a particular event of the plurality of events;
determining a quantity associated with the group of two or more events;
generating a description of the group of two or more events, the description of the group of two or more events includes an indication of the quantity associated with the group of two or more events;
analyzing data associated with the particular event to generate a description of the particular event;
generating a textual content that includes the description of the group of two or more events and the description of the particular event, wherein for at least one specific event of the group of two or more events, the textual content does not include information identifying the specific event; and
providing the generated textual content.
