# US 2019/0318223 A1 · Methods and Systems for Data Analysis by Text Embeddings > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0318223 A1 - Document ID: US20190318223A1 - Status: Published application - Kind: A1 - Application number: 16/383,563 - Filed: 2019-04-12 - Published: 2019-10-17 - Earliest claimed: 2018-04-12 - Assignees: Georgia Tech Research Corporation - Applicants: Georgia Tech Research Corporation - Inventors: Yao Xie; Shixiang Zhu - Web page: https://patentgrep.com/patent/US20190318223A1 ## CPC - G06F 40/284: Lexical analysis, e.g. tokenisation or collocates - G06F 40/20: Natural language analysis (semantic analysis of natural language G06F40/30) - G06F 40/30: Semantic analysis - G06N 3/047: Probabilistic or stochastic networks - G06N 3/0475: Generative networks - G06N 3/08: Learning methods - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A method for database management is disclosed. The method may include receiving a plurality of crime reports. Field data and/or narrative field data may be extracted from the plurality of crime reports. Further, a plurality of tokens may be generated from the narrative field data. The plurality of tokens may be sent to a neural network. In response, crime prediction data may be received from the neural network. Based on the crime prediction data and field data, related crimes may be determined. The related crimes may be plotted to map. Further, a visual display of the map may be generated. The visual display may be sent to a user portal and the user portal may then display the visual display as a graphical user interface. ## Claims ### Claim 1 A method for detecting crime series, the method comprising: receiving, by one or more processors, a plurality of crime reports; extracting, by the one or more processors, field data from each of the plurality of crime reports; identifying, by the one or more processors, a narrative field from each of the plurality of crime reports; extracting, by the one or more processors, narrative field data from the narrative field of each of the plurality of crime reports, wherein the narrative field data includes a plurality of words and a plurality of punctuation characters; generating a plurality of tokens from the narrative field data; sending, with a transceiver, the plurality of tokens and the field data to a neural network; receiving, at the one or more processors and from the neural network, crime prediction data; determining, by the one or more processors, based on the crime prediction data and the field data, related crimes; plotting, by the one or more processors, the related crimes to a map; generating, by the one or more processors, a visual display of the map; sending, by the transceiver, the visual display to a user portal; and displaying, by the user portal, the visual display as a graphical user interface. ### Claim 2 (depends on 1) The method of claim 1, wherein the field data includes at least one of an incident time or an incident location. ### Claim 3 (depends on 1) The method of claim 1, wherein generating the plurality of tokens further comprises: normalizing, by the one or more processors, the narrative field data such that the plurality of words within the narrative field data are the same case; removing, by the one or more processors, the plurality of punctuation characters from the narrative field data; converting, by the one or more processors, the narrative field data into the plurality of tokens; determining, by the one or more processors, an amount of occurrences within the narrative field data for each of the plurality of tokens; associating, by the one or more processors, the corresponding amount of occurrences with each of the plurality of tokens; determining, by the one or more processors, a weight of each of the plurality of tokens based at least in part on the corresponding amount of occurrences; and associating, by the one or more processors, the corresponding weight to each of the plurality of tokens. ### Claim 4 (depends on 3) The method of claim 3, wherein each of the plurality of tokens include three-word combinations. ### Claim 5 (depends on 3) The method of claim 3, further comprising: comparing, by the one or more processors, each of the plurality of tokens to terms within a database for at least a partial match; and calculating an amount of at least partial matches for each of the plurality of tokens. ### Claim 6 (depends on 5) The method of claim 5, wherein determining the weight of each of the plurality of tokens is further based on the amount of at least partial matches. ### Claim 7 (depends on 1) The method of claim 1, further comprising: determining, by the one or more processors, based on the crime prediction data and the field data, one or more future crimes. ### Claim 8 A method for detecting patterns within data, the method comprising: receiving, by one or more processors, a plurality of reports; extracting, by the one or more processors, field data from amongst each of the plurality of reports, wherein the field data includes a plurality of words and a plurality of punctuation characters; generating a plurality of tokens from the field data; sending, with a transceiver, the plurality of tokens and the field data to a neural network; and receiving, at the one or more processors and from the neural network, predictive data. ### Claim 9 (depends on 8) The method of claim 8, further comprising: plotting, by the one or more processors, the predictive data to a map; generating, by the one or more processors, a visual display of the map; sending, by the transceiver, the visual display to the user portal; and displaying, by a user portal, the visual display as a graphical user interface. ### Claim 10 (depends on 8) The method of claim 8, wherein each of the plurality of tokens includes a three-word combination. ### Claim 11 (depends on 8) The method of claim 8, wherein generating the plurality of tokens further comprises: normalizing, by the one or more processors, the field data such that the plurality of words within the field data are the same case; removing, by the one or more processors, the plurality of punctuation characters from the field data; converting, by the one or more processors, the field data into the plurality of tokens; determining, by the one or more processors, an amount of occurrences within the field data for each of the plurality of tokens; associating, by the one or more processors, the corresponding amount of occurrences with each of the plurality of tokens; determining, by the one or more processors, a weight of each of the plurality of tokens based at least in part on the corresponding amount of occurrences; and associating, by the one or more processors, the corresponding weight to each of the plurality of tokens. ### Claim 12 (depends on 11) The method of claim 11, further comprising: comparing, by the one or more processors, each of the plurality of tokens to terms within a database for at least a partial match; and calculating an amount of at least partial matches for each of the plurality of tokens. ### Claim 13 (depends on 12) The method of claim 12, wherein determining the weight of each of the plurality of tokens is further based on the amount of at least partial matches. ### Claim 14 (depends on 8) The method of claim 8, wherein the plurality of reports are crime reports. ### Claim 15 (depends on 14) The method of claim 14, wherein the predictive data comprises related crime data. ### Claim 16 (depends on 15) The method of claim 15, further comprising: determining, by the one or more processors, based on the predictive data, one or more future crimes. ### Claim 17 A system for detecting crimes series comprising: one or more processors; a user portal; a neural network; a transceiver; and at least one memory in communication with the processor, the user portal, the neural network, and the transceiver and storing computer program code that, when executed by the one or more processors, is configured to cause the system to: receive, from the user portal, a plurality of crime reports; extract field data from amongst each of the plurality of crime reports; identify a narrative field from amongst each of the plurality of crime reports; extract narrative field data from the narrative field of each of the plurality of crime reports, wherein the narrative field data includes a plurality of words and a plurality of punctuation terms; generate a plurality of tokens from the narrative field data; send, with the transceiver, the plurality of tokens and the field data to a neural network; receive, from the neural network, crime prediction data; determine based on the crime prediction data and the field data, related crimes; plot the related crimes to a map; generate a visual display of the map; and send the visual display to a user portal, such that the visual display can be displayed by the user portal as a graphical user interface. ### Claim 18 (depends on 17) The system of claim 17, wherein generating the plurality of tokens further comprises: normalize the narrative field data such that the plurality of words within the narrative field data are the same case; convert the narrative field data into the plurality of tokens; determine an amount of occurrences within the narrative field data for each of the plurality of tokens; associate the corresponding amount of occurrences with each of the plurality of tokens; determine a weight of each of the plurality of tokens based on the corresponding amount of occurrences and the amount of at least partial matches; and associate the corresponding weight to each of the plurality of tokens. ### Claim 19 (depends on 18) The system of claim 18, further comprising: compare each of the plurality of tokens to terms within a database for at least a partial match; calculate an amount of at least partial matches for each of the plurality of tokens; and wherein determining the weight of each of the plurality of tokens is further based on the amount of at least partial matches. ### Claim 20 (depends on 18) The system of claim 18, further comprising: determining, by the processor, based on the crime prediction data and the field data, one or more future crimes.