DETAILED ACTION
This action is in response to the original filing dated 27 March 2024. Claims 1-20 are pending and have been considered below.
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
The information disclosure statements (IDS) submitted on 27 September 2024 and 08 April 2025 have been received, entered into the record, and considered. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statements are being considered by the examiner.
Claim Objections
Claims 3 and 14 are objected to because of the following informalities: claims 3 and 14 recite “with the of the plurality of subsequent hierarchical code descriptions”, examiner suggests “with one of the plurality of subsequent hierarchical code descriptions.” Appropriate correction is required.
Claim Rejections - 35 USC § 103
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-5, 11-16 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Holliday et al. (US 2020/0387504 A1) in view of Hart (US 2014/0181983 A1).
As for independent claim 1, Holliday teaches a method comprising:
identifying, by one or more processors, an interaction code from an interaction data object [(e.g. see Holliday paragraph 0057) ”a search sources interface 414 configured to allow the user to identify one or more code lists within a concept universe including concepts from multiple code lists, to include in a subsequent search. In some embodiments, the user may identify code lists by beginning to type characters of a desired code list identifier, such as “ICD” to identify code lists based on an ICD standard. In response to providing a partial code list identifier, the system may provide a list of matching code list identifiers for selection by the user. The user can then select any code list to be included in the search, which will then appear in the search sources interface 414”].
receiving, by the one or more processors, a modified candidate keywords list for the interaction code, wherein the modified candidate keywords list is generated by: [(e.g. see Holliday paragraphs 0056, 0061) ”a code list panel 510 that includes all of the items previously selected for addition to the custom code list by the user. In this example, the items in the custom code list are displayed in a hierarchical tree structure, sorted by their corresponding code list first and then by their codes. Thus, in the example of FIG. 5, items that were identified in an “ICD10 Diagnosis” code list are grouped together first and then items identified in an “ICD 9 Diagnosis” are grouped afterwards. Thus, the user interface provides an integrated display of items that have been identified by the user through multiple iterations of searching code lists, viewing and manipulating visualizations, and selecting codes for addition to the custom code list … details regarding the selected item are displayed in code detail panel 330”].
iteratively appending one or more interaction code descriptions of an interaction corpus corresponding to the interaction code to generate a candidate keywords list [(e.g. see Holliday paragraphs 0038, 0053, 0058) ”the user interface and interactions component 104 communicates those codes to the code list builder 106, which creates and updates a custom code list as the user continues to select codes for addition to the custom code list 109 … The user may perform any number of such iterations. In the example of FIG. 2, each iteration ends with the custom code list being updated with any items selected for addition to the custom code list … Matching items are identified by the system and at least a portion of the items are displayed in the match panel 418. The matched items may organized into a hierarchical relationship, such as a tree structure, and/or sorted based on machine code, human recognizable concept, search relevance, and/or other characteristics”].
and initiating, by the one or more processors, the performance of a prediction-based action on the interaction-specific keywords list [(e.g. see Holliday paragraph 0047) ”the system determines any related items of the matching items. For example, related items for a particular matched item may include items found in a different code list. For example, a first item in a first code list may be a related item to a second item in a second code list, e.g., both machine codes are related to a particular medical diagnosis. The system may also identify other related items in the same code set as each matched item, such as based on the related items having a hierarchical relationship (perhaps within a predetermined relationship length) with the matched item”].
Holliday does not specifically teach generating, using a domain-specific term corpus, the modified keywords list by pruning one or more predefined terms of the domain-specific term corpus from the candidate keywords list or generating, by the one or more processors, an interaction-specific keywords list based on a comparison between the modified candidate keywords list and an interaction description of the interaction data object. However, in the same field of invention or solving similar problems, Hart teaches:
generating, using a domain-specific term corpus, the modified keywords list by pruning one or more predefined terms of the domain-specific term corpus from the candidate keywords list [(e.g. see Hart paragraphs 0033, 0044) ”the keyword generator 200 may uses a domain document corpus 215 … generate a candidate list of DKP terms 210, and from the candidate list generate a domain specific keyword list … If difference in term frequency is statistically significant (based on the statistical test used to evaluate F.sub.1 and F.sub.2) and if the term is more likely to appear in the general document corpus, then at step 435 the term T is excluded from the DLP keyword list. This result occurs as the evaluation indicates that the term is primarily monosemous (i.e., single sense) but it has a sense that is not associated with the target domain (e.g., medicine)”].
generating, by the one or more processors, an interaction-specific keywords list based on a comparison between the modified candidate keywords list and an interaction description of the interaction data object [(e.g. see Hart paragraphs 0037, 0044) ”Using medicine as an example, the keyword generator 200 may parse the ICD-9 coding standard and strip out key terms and (and phrases) to create candidate DLP terms 210. A variety of approaches may be used to find candidate monosemous words to include in list 210. One approach is to identify key terms and phrases for example with a frequency of use falling below a threshold. For example, both "xerothalmic scars" and be included as a two-word phrase. Similarly, "xerotlanlic" alone can be a term, while "scars" may be dropped--as not being infrequent enough to include in the candidate DLP terms 210. Note, in this example, the bigram "xerothalmic scars" can be dropped as the single word "xerothalmic" is adequate to capture all instances of the bigram. In other cases, however, bigrams (or trigrams etc.) may be included in the candidate DLP Terms list 210. For example, the bigram "California Disease" could be included as a candidate DLP keyword, where neither "California" nor "Disease" would be included … the term is more likely to appear in the domain specific document corpus, then at step 440 the term T is added to the DLP keyword list. This result occurs as the evaluation that the term is substantially monosemous and has a sense associated with the target domain”].
Therefore, considering the teachings of Holliday and Hart, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to add generating, using a domain-specific term corpus, the modified keywords list by pruning one or more predefined terms of the domain-specific term corpus from the candidate keywords list and generating, by the one or more processors, an interaction-specific keywords list based on a comparison between the modified candidate keywords list and an interaction description of the interaction data object, as taught by Hart, to the teachings of Holliday because generating a keyword list from an ontology or standard will result in a keyword list with terms that are infrequent, but do not have a meaning specific to that target domain (e.g. see Hart paragraph 0006).
As for dependent claim 2, Holliday and Hart teach the method as described in claim 1 and Holliday further teaches:
wherein the prediction-based action comprises one or more of (i) highlighting terms in the interaction description based on the interaction-specific keywords list or (ii) applying a color gradient to terms in the interaction description based on the interaction-specific keywords list and an ordering scheme [(e.g. see Holliday paragraphs 0047, 0058 and Fig. 4 numeral 419) ”The system may also identify other related items in the same code set as each matched item, such as based on the related items having a hierarchical relationship (perhaps within a predetermined relationship length) with the matched item … Matching items are identified by the system and at least a portion of the items are displayed in the match panel 418. The matched items may organized into a hierarchical relationship, such as a tree structure, and/or sorted based on machine code, human recognizable concept, search relevance, and/or other characteristics. The user may then select one or more displayed items to initiate generation and display of a visualization in code visualization panel 430. In the example of FIG. 4, two matched items 419 are selected].
As for dependent claim 3, Holliday and Hart teach the method as described in claim 1 and Holliday further teaches:
wherein the interaction corpus comprises a hierarchical node structure and generating the candidate keywords list comprises: [(e.g. see Holliday paragraph 0040) ”a known hierarchical arrangement of codes in the particular coding system”].
identifying an initial interaction code description for the interaction code from an initial node with the interaction corpus that corresponds to the interaction code [(e.g. see Holliday paragraph 0058) ”Matching items are identified by the system and at least a portion of the items are displayed in the match panel 418. The matched items may organized into a hierarchical relationship, such as a tree structure, and/or sorted based on machine code, human recognizable concept, search relevance, and/or other characteristics. The user may then select one or more displayed items to initiate generation and display of a visualization in code visualization panel 430”].
identifying a plurality of subsequent hierarchical code descriptions for a plurality of subsequent interaction codes that respectively correspond to a plurality of subsequent nodes within the interaction corpus [(e.g. see Holliday paragraphs 0041, 0047) ”For example, a first item in a first code list may be a related item to a second item in a second code list, e.g., both machine codes are related to a particular medical diagnosis. The system may also identify other related items in the same code set as each matched item, such as based on the related items having a hierarchical relationship (perhaps within a predetermined relationship length) with the matched item … edges in the tree structure may represent a hierarchical relationship with a particular code, such as to indicate a subcode or a parent code”].
appending the initial interaction code description with the plurality of subsequent hierarchical code descriptions [(e.g. see Holliday 0059) ”add selected nodes button 436 may be selected to initiate addition of all items associated with selected nodes in the code list panel 418 to the custom code list. Thus, with node 433 selected, selection of button 436 would cause the item associated with selected node 433, e.g., including machine code “24901”, to be added to the custom code list”].
As for dependent claim 4, Holliday and Hart teach the method as described in claim 3 and Holliday further teaches:
wherein each of the plurality of subsequent nodes is a parent node of the initial node within the hierarchical node structure [(e.g. see Holliday paragraph 0041) ”Graph builder component 108 generates a visualization, such as in a tree structure, e.g., a directed acyclic graph or a hierarchical directed acyclic graph, or any other visualization format. In some embodiments, the graph builder generates a tree structure having nodes representing machine codes and edges representing relationships between codes. For example, edges in the tree structure may represent a hierarchical relationship with a particular code, such as to indicate a subcode or a parent code. In some embodiments, details regarding a hierarchical relationship may be indicated by a particular visual effect, such as a particular color, size, pattern, etc. of the particular edge and/or associated nodes. For example, child nodes of a selected parent node may each be indicated in a certain color”].
As for dependent claim 5, Holliday and Hart teach the method as described in claim 3 and Holliday further teaches:
wherein the plurality of subsequent nodes comprises a subset of a plurality of parent nodes of the initial node and the subset of parent nodes is based on a relevance threshold [(e.g. see Holliday paragraph 0040) ”The code list access and filtering component 102 may also identify related items associated with the matching items, such as subcodes or parent codes of items matching the actual syntax of the user's search query, such as by reference to a known hierarchical arrangement of codes in the particular coding system. Additionally, related items for a particular matched item may include items found in a different code list. For example, a first item in a first code list may be a related item to a second code in a second code list, e.g., both are related to a particular medical diagnosis. Identification of such related items may be performed by evaluating a relationship mapping that is accessible to the system 100. A relationship mapping may include mappings between two, three, or any quantity of machine codes or items in different code lists”].
As for dependent claim 11, Holliday and Hart teach the method as described in claim 1, but Holliday does not specifically teach the following limitation. However, Hart teaches:
further comprising: identifying a secondary interaction corpus based on a code type of the interaction code; in response to identifying the secondary interaction corpus, extracting a plurality of secondary candidate keyword tokens from the secondary interaction corpus and generating a secondary keywords list from the plurality of secondary candidate keyword tokens [(e.g. see Hart paragraph 0007, 0033) ”This method also includes receiving a second document corpus. Unlike the first document corpus, each document in the second document corpus is unrelated to the target domain. This method also includes, for each of a plurality of candidate terms, determining a first frequency of usage of the candidate term within first document corpus, determining a second frequency of usage of the candidate term within second document corpus, and based on the first and second frequency of usage, determining whether the candidate term has a single sense associated with the target domain, and if so, adding the candidate term to the monosemous keyword list … the keyword generator 200 may uses a domain document corpus 215, general document corpus 220, and term frequency dictionary 225 to, first, generate a candidate list of DKP terms 210, and from the candidate list generate a domain specific keyword list. As noted, the domain specific keyword 205 list includes a set of infrequently used terms (or short phrases) that have a primarily single "sense," i.e., a set of monosemous keywords related to a target domain”].
The motivation to combine is the same as that used for claim 1.
As for independent claim 12, Holliday and Hart teach a system. Claim 12 discloses substantially the same limitations as claim 1. Therefore, it is rejected with the same rational as claim 1.
As for dependent claim 13, Holliday and Hart teach the system as described in claim 12; further, claim 13 discloses substantially the same limitations as claim 2. Therefore, it is rejected with the same rational as claim 2.
As for dependent claim 14, Holliday and Hart teach the system as described in claim 12; further, claim 14 discloses substantially the same limitations as claim 3. Therefore, it is rejected with the same rational as claim 3.
As for dependent claim 15, Holliday and Hart teach the system as described in claim 14; further, claim 15 discloses substantially the same limitations as claim 4. Therefore, it is rejected with the same rational as claim 4.
As for dependent claim 16, Holliday and Hart teach the system as described in claim 14; further, claim 16 discloses substantially the same limitations as claim 5. Therefore, it is rejected with the same rational as claim 5.
As for independent claim 20, Holliday and Hart teach a non-transitory computer-readable storage media. Claim 20 discloses substantially the same limitations as claim 1. Therefore, it is rejected with the same rational as claim 1.
Claims 6 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Holliday et al. (US 2020/0387504 A1) in view of Hart (US 2014/0181983 A1), as applied to claim 1 above, and further in view of Yang et al. (US 2023/0245735 A1).
As for dependent claim 6, Holliday and Hart teach the method as described in claim 1, but do not specifically teach wherein generating the interaction-specific keywords list comprises: generating, using a domain-specific machine learning embedding model, a plurality of token-level candidate keywords embeddings for a plurality of candidate tokens of the modified candidate keywords list, generating, using the domain-specific machine learning embedding model, a plurality of token-level interaction description embeddings for a plurality of description tokens of the interaction description or generating the interaction-specific keywords list by selecting one or more candidate tokens from the plurality of candidate tokens based on a plurality of cross-token similarity scores between the plurality of token-level candidate keyword embeddings and the plurality of token-level interaction description embeddings. However, in the same field of invention or solving similar problems, Yang teaches:
wherein generating the interaction-specific keywords list comprises: generating, using a domain-specific machine learning embedding model, a plurality of token-level candidate keywords embeddings for a plurality of candidate tokens of the modified candidate keywords list [(e.g. see Yang paragraph 0023) ”The electronic medical record data analysis system displays the electronic medical record data 301 through the display device, and uses a label embedding method and a document embedding method to highlight a plurality of texts or tokens corresponding to the plurality of medical record feature parameters 303 in the electronic medical record data 301, so that the medical personnel intuitively focus on the highlighted keywords, texts, or tokens in the electronic medical record data 301 through the display device”].
generating, using the domain-specific machine learning embedding model, a plurality of token-level interaction description embeddings for a plurality of description tokens of the interaction description [(e.g. see Yang paragraph 0029) ”the electronic medical record data analysis system obtains a plurality of text descriptions corresponding to the plurality of disease diagnosis codes, and generates a plurality of label embeddings used for representing the plurality of disease diagnosis codes and interrelationships thereof through the text analysis model 311. In this embodiment, the electronic medical record data analysis system obtains, in an embodiment, all disease diagnosis codes of the ICD-10 and relevant disease diagnosis descriptions, and performs semantic identification through the text analysis model 311, to generate a plurality of label embeddings used for representing the plurality of disease diagnosis codes and interrelationships thereof”].
and generating the interaction-specific keywords list by selecting one or more candidate tokens from the plurality of candidate tokens based on a plurality of cross-token similarity scores between the plurality of token-level candidate keyword embeddings and the plurality of token-level interaction description embeddings [(e.g. see Yang paragraph 0026) ”the attention-based model 314 includes a patient representation model 3141 (label-wise document attention layer) and a label representation model 3142 (document attention layer). The patient representation model 3141 compares a similarity between the medical record feature parameters 303_1 to 303_N and the plurality of basic patient feature parameters 304, to generate a plurality of first assessment features 308 (or referred to as case assessment features). The label representation model 3142 compares a similarity between the medical record feature parameters 303_1 to 303_N and a plurality of diagnosis code feature parameters 305_1 to 305_M that is corresponding to different diagnosis codes and is generated based on the International Classification of Diseases data 302, to generate a plurality of second assessment features 309_1 to 309_M (or referred to as a plurality of disease diagnosis code assessment features)”].
Therefore, considering the teachings of Holliday, Hart and Yang, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to add wherein generating the interaction-specific keywords list comprises: generating, using a domain-specific machine learning embedding model, a plurality of token-level candidate keywords embeddings for a plurality of candidate tokens of the modified candidate keywords list, generating, using the domain-specific machine learning embedding model, a plurality of token-level interaction description embeddings for a plurality of description tokens of the interaction description and generating the interaction-specific keywords list by selecting one or more candidate tokens from the plurality of candidate tokens based on a plurality of cross-token similarity scores between the plurality of token-level candidate keyword embeddings and the plurality of token-level interaction description embeddings, as taught by Yang, to the teachings of Holliday and Hart because it saves medical personnel time and energy on the analysis and filing operations for medical record data (see Yang paragraph 0003).
As for dependent claim 17, Holliday and Hart teach the system as described in claim 12; further, claim 17 discloses substantially the same limitations as claim 6. Therefore, it is rejected with the same rational as claim 6.
Claims 7-10, 18 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Holliday et al. (US 2020/0387504 A1) in view of Hart (US 2014/0181983 A1) and further in view of Yang et al. (US 2023/0245735 A1), as applied to claim 6 above, and further in view of Shachor et al. (US 2024/0062004 A1).
As for dependent claim 7, Holliday, Hart and Yang teach the method as described in claim 6, but do not specifically teach wherein the one or more candidate tokens are based on (i) a comparison between the plurality of cross-token similarity scores and a similarity threshold and (ii) a limit threshold. However, in the same field of invention or solving similar problems, Shachor teaches:
wherein the one or more candidate tokens are based on (i) a comparison between the plurality of cross-token similarity scores and a similarity threshold and (ii) a limit threshold [(e.g. see Shachor paragraph 0045) ”a limit may also be imposed on the total number of fuzzy tokens generated in step 204 (irrespective of the limit mentioned above with respect to the syllable fuzzy tokens), for similar considerations. This may include, for example, a limit on the number of tokens per glossary word, such as selection of those fuzzy tokens per glossary word which have a similarity score above a certain threshold (e.g., a value between 50-70), or the top-k fuzzy tokens per glossary word (namely, a predefined number of fuzzy tokens per glossary word which have the highest similarity scores)”].
Therefore, considering the teachings of Holliday, Hart, Yang and Shachor, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to add wherein the one or more candidate tokens are based on (i) a comparison between the plurality of cross-token similarity scores and a similarity threshold and (ii) a limit threshold, as taught by Shachor, to the teachings of Holliday, Hart and Yang because it allows for computational efficiency (see Shachor paragraph 0044).
As for dependent claim 8, Holliday, Hart, Yang and Shachor teach the method as described in claim 7, but Holliday and Hart do not specifically teach the following limitation. However, Yang teaches:
wherein the computer-implemented method further comprises expanding the modified candidate keywords list by: identifying, using the domain-specific machine learning embedding model, one or more expansion tokens for the modified candidate keywords list based on (i) a plurality of expansion token similarity scores between an initial subset of the plurality of token-level candidate keyword embeddings and a plurality of candidate expansion token embeddings corresponding to a plurality of candidate expansion tokens, (ii) an expansion similarity threshold, and (iii) an expansion threshold [(e.g. see Yang paragraphs 0018, 0023, 0024, 0029) ”the electronic medical record data analysis system obtains a plurality of text descriptions corresponding to the plurality of disease diagnosis codes, and generates a plurality of label embeddings used for representing the plurality of disease diagnosis codes and interrelationships thereof through the text analysis model 311. In this embodiment, the electronic medical record data analysis system obtains, in an embodiment, all disease diagnosis codes of the ICD-10 and relevant disease diagnosis descriptions, and performs semantic identification through the text analysis model 311, to generate a plurality of label embeddings used for representing the plurality of disease diagnosis codes and interrelationships thereof … The electronic medical record data analysis system displays the electronic medical record data 301 through the display device, and uses a label embedding method and a document embedding method to highlight a plurality of texts or tokens corresponding to the plurality of medical record feature parameters 303 in the electronic medical record data 301 … the electronic medical record feature code transformation model 315 calculates a plurality of correlation degree scores corresponding to the plurality of disease diagnosis codes according to a determining result of the attention-based model 314. The electronic medical record data analysis system performs sorting according to the plurality of disease diagnosis codes and the plurality of correlation degree scores, to generate an initial list. In this embodiment, the post-processing module 320 rearranges the initial list according to a preset coding rule (a specific coding rule of the ICD-10) and patient information in the electronic medical record data 301. In this embodiment, the main diagnosis recommendation model 330, in an embodiment, adjusts arrangement sequences of the plurality of disease diagnosis codes in the post-processed initial list 306 according to historical medical record data of the patient, to generate a recommendation list 307. In this way, the medical personnel, in an embodiment, select a disease diagnosis code in the recommendation list displayed by the display device by operating the input device, so that the processor of the electronic medical record data analysis system immediately reads main diagnosis information corresponding to the disease diagnosis code, to immediately obtain the most relevant main diagnosis information of the current medical treatment of the patient … In step S230, the processor 110 sorts the plurality of disease diagnosis codes according to the plurality of correlation degree scores, to generate an initial list; The processor 110 first sequentially arranges the plurality of disease diagnosis codes with higher correlation degree scores to lower correlation degree scores, to generate the initial list.”].
and appending the one or more expansion tokens to the modified candidate keyword list [(e.g. see Yang paragraph 0014) ”The processor 110 arranges the plurality of disease diagnosis codes according to the plurality of disease diagnosis codes and the plurality of correlation degree scores, to generate a list, and adjusts the list by executing the post-processing module 122 and the main diagnosis recommendation model 123, to generate a final recommendation list”].
The motivation to combine is the same as that used for claim 6.
As for dependent claim 9, Holliday, Hart, Yang and Shachor teach the method as described in claim 8, but Holliday and Hart do not specifically teach the following limitation. However, Yang teaches:
wherein the interaction corpus comprises a hierarchical node structure and the initial subset of the plurality of token-level candidate keyword embeddings correspond to a subset of the plurality of candidate tokens of the modified candidate keywords list that are associated with an initial layer of the hierarchical node structure [(e.g. see Yang paragraphs 0023, 0029) ”the electronic medical record data analysis system obtains a plurality of text descriptions corresponding to the plurality of disease diagnosis codes, and generates a plurality of label embeddings used for representing the plurality of disease diagnosis codes and interrelationships thereof through the text analysis model 311. In this embodiment, the electronic medical record data analysis system obtains, in an embodiment, all disease diagnosis codes of the ICD-10 and relevant disease diagnosis descriptions, and performs semantic identification through the text analysis model 311, to generate a plurality of label embeddings used for representing the plurality of disease diagnosis codes and interrelationships thereof … The electronic medical record data analysis system displays the electronic medical record data 301 through the display device, and uses a label embedding method and a document embedding method to highlight a plurality of texts or tokens corresponding to the plurality of medical record feature parameters 303 in the electronic medical record data 301”].
The motivation to combine is the same as that used for claim 6.
As for dependent claim 10, Holliday, Hart and Yang teach the method as described in claim 6, but do not specifically teach the following limitation. However, Shachor teaches:
wherein the cross-token similarity score of the plurality of cross-token similarity scores comprises a fuzzy matching score [(e.g. see Shachor paragraphs 0008, 0014) ”obtaining multiple glossary terms each comprising one or more words; automatically operating a fuzzy token generator to generate multiple fuzzy tokens from each word of each of the glossary terms; automatically calculating a similarity score for each of the fuzzy tokens, wherein the similarity score denotes a similarity between the respective fuzzy token and its respective word; obtaining multiple input terms to be matched with the multiple glossary terms; automatically operating a tokenizer to separate each of the input terms into multiple input tokens; automatically generating multiple n-grams from each of the input tokens; automatically comparing the n-grams with the fuzzy tokens, to output a list of matching n-grams and fuzzy tokens; based on the list of matching n-grams and fuzzy tokens, automatically identifying, from the glossary terms, candidate glossary term matches for each of the input terms; and automatically calculating one or more scores that quantify the match between each of the candidate glossary term matches and its respective input term … the calculation of the similarity score comprises calculating a distance between the respective fuzzy token and its respective word”].
The motivation to combine is the same as that used for claim 7.
As for dependent claim 18, Holliday, Hart and Yang teach the system as described in claim 17; further, claim 18 discloses substantially the same limitations as claim 7. Therefore, it is rejected with the same rational as claim 7.
As for dependent claim 19, Holliday, Hart and Yang teach the system as described in claim 17; further, claim 19 discloses substantially the same limitations as claim 8. Therefore, it is rejected with the same rational as claim 8.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
U.S. PGPub 2017/0235887 A1 issued to Cox et al. on 17 August 2017. The subject matter disclosed therein is pertinent to that of claims 1-20 (e.g. mapping medical codes).
U.S. PGPub 2016/0019356 A1 issued to Martin et al. on 21 January 2016. The subject matter disclosed therein is pertinent to that of claims 1-20 (e.g. medical keywords and various medical concepts linked to medical codes).
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CHRISTOPHER J FIBBI whose telephone number is (571)-270-3358. The examiner can normally be reached Monday - Thursday (8am-6pm).
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, William Bashore can be reached at (571)-272-4088. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/CHRISTOPHER J FIBBI/Primary Examiner, Art Unit 2174