DETAILED ACTION
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 statement (IDS) submitted on 06/10/2024 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Drawings
The drawings were submitted on 05/28/2024. These drawings are reviewed and accepted by the examiner.
Claim Rejections - 35 USC § 103
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.
Claim(s) 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Rosenkranz et al. (US 20240296425 A1) in view of Varga et al. (US 20200302564 A1).
Regarding claim 1, Rosenkranz teaches:
“receiving, from a user, a first natural language user input” (par. 0047; ‘In other implementations, for instance, an automated chatbot is used in place of a fill-in form, where the chatbot requests the user to input the requested information via a conversational, natural language dialog or message-based format using text and/or spoken-language digital audio received via a microphone embedded in a computing device.’);
“determining a profile associated with the user, user role, or context” (par. 0057; ‘The name of the user's company is obtained from the user's stored profile data, which can be extracted from the user connection network, in some implementations.’),
“generating, based on at least the first natural language user input and the determined profile, a prompt for a language model” (par. 0074; ‘In response to a selection of GUI control element 308 or GUI control element 312, and a selection of GUI control element 316, the job posting system incorporates skill keywords, which are extracted from the user connection network that contains the user profile of the selected suggested user (e.g., user 306 or user 310), into the prompt for the generative language model and inputs the prompt into the generative language model to cause the generative language model to output a job description that the generative language model has machine-generated based on the skill keywords extracted from the user profile of the selected suggested user in the user connection network.’); and
“providing the prompt to the language model” (par. 0074; ‘… inputs the prompt into the generative language model).
However, Rosenkranz does not expressly teach:
“the profile including indications of: one or more knowledge base; one or more functions; one or more templates; and one or more plugins.”
Varga teaches:
“the profile including indications of: one or more knowledge base; one or more functions; one or more templates; and one or more plugins” (par. 0074; ‘Embodiments of the user profile module 107 may create a brand-new user profile for each user, select a user profile for each user from an existing profile template that most closely fits the interests, personality and behavior of the user from a pool of user profile templates and/or a hybrid user profile that customizes an existing user profile template using the gathered user data 130 and user-defined parameters. In an embodiment wherein the user profile is brand new and fully defined by the user profile module 107, the user profile module 107 may create the customized user profile based entirely on the gathered user data 130 and user-defined parameters to compile as complete a picture about each individual user as possible and based on the compiled user data 130 and user-defined parameters identify the user's interests, personality, hobbies, skills, experiences, strengths, etc. within the user profile. The traits of the user as described by the user data 130 and user-defined parameters, can be further matched to historical user profiles maintained by the user profile module 107 and/or the knowledge base 117 to further determine which vocational actions, including which careers, occupations, vocations and/or educational opportunities are most closely aligned with the user profile have been considered interesting by historical users of the historical user profiles. Wherein, the more closely a user profile resembles one or more historical user profiles, the higher the probability that the vocational application 103 would recommend one or more of the vocational action previously recommended to a historical user profile to the current user seeking guidance from the vocational application 103.’).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Rosenkranz’s user profiles by incorporating Varga’s user profile module such that the user profile indicates one or more knowledge base, one or more functions (parameters), one or more templates, and one or more plugins (applications). The combination would allow user profiles to identify user characteristics that can be used to provide vocational action to the user. (Varga: par. 0058)
Regarding claim 2 (dep. on claim 1), the combination of Rosenkranz in view of Varga further teaches:
“wherein the one or more knowledge base comprises a searchable corpus of data” (Varga: par. 0111; ‘Embodiments of the user profile module 107 may query the records of the knowledge base 117 for known vocations, careers and educational options that may (based on historical data) be identified as a suitable match for the user's profile.’).
Regarding claim 3 (dep. on claim 1), the combination of Rosenkranz in view of Varga further teaches:
“wherein the one or more functions comprise one or more formulas usable to calculate and/or derive properties” (Rosenkranz: par. 0074; ‘Embodiments of the user profile module 107 may create a brand-new user profile for each user, select a user profile for each user from an existing profile template that most closely fits the interests, personality and behavior of the user from a pool of user profile templates and/or a hybrid user profile that customizes an existing user profile template using the gathered user data 130 and user-defined parameters.’).
Regarding claim 4 (dep. on claim 1), the combination of Rosenkranz in view of Varga further teaches:
“wherein the one or more templates comprise one or more rules of business logic” (Varga: par. 0085; ‘Embodiments of the rules engine of a knowledge base 117 may be a set of universally applicable rules that may be created based on the experience and knowledge of the practices of experts, developers, programmers and/or contributors to the knowledge base 117.’).
Regarding claim 5 (dep. on claim 4), the combination of Rosenkranz in view of Varga further teaches:
“wherein the one or more rules are defined in natural language” (Varga: par. 0072; ‘Embodiments of the user profile module 107 may parse the text of the user data 130 or use natural language processing techniques to convert the user data 130 into text, and further understand the content of the text by breaking down the text into smaller units, words, and phrases.’ ‘Embodiments of the user profile module 107 may include a lexicon and a set of grammar rules encoded into the user profile module 107 and/or may apply statistical machine learning to the grammar rules to determine the meaning behind the collected user data 130.’).
Regarding claim 6 (dep. on claim 4), the combination of Rosenkranz in view of Varga further teaches:
“wherein at least one of the one or more rules is associated with a data object” (Varga: par. 0085; ‘Embodiments of the rules engine of a knowledge base 117 may be a set of universally applicable rules that may be created based on the experience and knowledge of the practices of experts, developers, programmers and/or contributors to the knowledge base 117.’).
Regarding claim 7 (dep. on claim 1), the combination of Rosenkranz in view of Varga further teaches:
“wherein the one or more plugins comprise one or more data processing tools” (Varga: par. 0074; ‘Wherein, the more closely a user profile resembles one or more historical user profiles, the higher the probability that the vocational application 103 would recommend one or more of the vocational action previously recommended to a historical user profile to the current user seeking guidance from the vocational application 103.’).
Regarding claim 8 (dep. on claim 1), the combination of Rosenkranz in view of Varga further teaches:
“wherein at least one of the plugins is activated prior to providing the prompt to the language model and is configured to provide a plugin output that is at least partially included in the prompt” (Varga: par. 0093; ‘Embodiments of the ranking module 111 may analyze the user data 130, vocational data, user-defined parameters and the user's profile information stored by the knowledge base 117 each time a user runs the vocational application 103.’).
Regarding claim 9 (dep. on claim 1), the combination of Rosenkranz in view of Varga further teaches:
“receiving an output from the language model, responsive to the natural language user input” (Varga: par. 0236; ‘A prefix is a parameter that can be filled with context data, such as data that includes previous output produced by a generative language model. The previous output can include, for instance, a job posting that was previously generated by the generative language model and edited by the posting user via, e.g., user interface 400.’).
Regarding claim 10 (dep. on claim 9), the combination of Rosenkranz in view of Varga further teaches:
“wherein at least one of the plugins is activated after receiving the output and is configured to generate, based on at least a portion of the output, at least a portion of a result provided to the user” (Varga: par. 0093; ‘Embodiments of the ranking module 111 may analyze the user data 130, vocational data, user-defined parameters and the user's profile information stored by the knowledge base 117 each time a user runs the vocational application 103.’).
Regarding claim 11 (dep. on claim 1), the combination of Rosenkranz in view of Varga further teaches:
“wherein at least one of the plugins is configured to access an object database comprising a plurality of objects stored according to an object ontology” (Varga: par. 0060; ‘Examples of tools or data collection solutions that may be implemented by the data collection module 105 include webpage crawling tools, natural language processing of text or videos, data mining, text pattern matching, HTML parsing, document object model parsing, scraping metadata or semantic markups and annotation, etc.’; par. 0075; ‘Embodiments of the ontology may be maintained as part of the knowledge base 117.’).
Regarding claim 12 (dep. on claim 11), the combination of Rosenkranz in view of Varga further teaches:
“wherein the at least one of the plugins is configured to search the object database for an object associated with at least a portion of an output provided by the language model” (Rosenkranz: par. 0093; ‘In this case, the company description is considered inferred data generated by inferred data generator 514 querying the entity graph 510 for content items that mention the company name, formulating a prompt for the generative language model based on the query results, e.g., a prompt that instructs the generative model to create a summary of the query results, receiving output of the generative language model and using the output of the generative language model into a company description.’).
Regarding claim 13 (dep. on claim 11), the combination of Rosenkranz in view of Varga further teaches:
“wherein the at least one of the plugins is configured to search the object database for an object associated with at least a portion of the natural language user input” (Rosenkranz: par. 0080; ‘In this example, the job posting system incorporates input provided by a job poster via, e.g., a graphical user interface, into a query and uses the query to search the data store for a previously auto-generated description that matches or is similar to the query.’).
Regarding claim 14 (dep. on claim 1), the combination of Rosenkranz in view of Varga further teaches:
“wherein the language model is selected based on the determined profile” (Rosenkranz: par. 0074; ‘In response to a selection of GUI control element 308 or GUI control element 312, and a selection of GUI control element 316, the job posting system incorporates skill keywords, which are extracted from the user connection network that contains the user profile of the selected suggested user (e.g., user 306 or user 310), into the prompt for the generative language model and inputs the prompt into the generative language model to cause the generative language model to output a job description that the generative language model has machine-generated based on the skill keywords extracted from the user profile of the selected suggested user in the user connection network.’).
Regarding claim 15 (dep. on claim 1), the combination of Rosenkranz in view of Varga further teaches:
“wherein the one or more plugins are automatically selected according to one or more rules associated with the one or more templates associated with the profile” (Varga: par. 0074; ‘Wherein, the more closely a user profile resembles one or more historical user profiles, the higher the probability that the vocational application 103 would recommend one or more of the vocational action previously recommended to a historical user profile to the current user seeking guidance from the vocational application 103.’).
Regarding claim 16 (dep. on claim 1), the combination of Rosenkranz in view of Varga further teaches:
“wherein the profile further comprises ontology data, wherein the ontology data comprises a semantic knowledge graph of data objects” (Varga: par. 0060; ‘Examples of tools or data collection solutions that may be implemented by the data collection module 105 include webpage crawling tools, natural language processing of text or videos, data mining, text pattern matching, HTML parsing, document object model parsing, scraping metadata or semantic markups and annotation, etc.’).
Regarding claim 17 (dep. on claim 1), the combination of Rosenkranz in view of Varga further teaches:
“wherein generating the prompt comprises: determining, receiving, or accessing a template associated with the profile” (Varga: par. 0074; ‘Embodiments of the user profile module 107 may create a brand-new user profile for each user, select a user profile for each user from an existing profile template that most closely fits the interests, personality and behavior of the user from a pool of user profile templates and/or a hybrid user profile that customizes an existing user profile template using the gathered user data 130 and user-defined parameters.’); and
“generating the prompt based on at least the first natural language user input and the template” (Rosenkranz: par. 0040; ‘These additional, system-inferred parameter values are included in a prompt for a generative language model, to improve the likelihood that the prompt will cause a generative language model (GLM) to output a job description that both meets the requirements of the job poster and needs only minimal human review.’).
Regarding claim 18 (dep. on claim 17), the combination of Rosenkranz in view of Varga further teaches:
“wherein generating the prompt based on at least the first natural language user input and the template further comprises: appending or replacing text in the template based on the first natural language input” (Rosenkranz: par. 0244; ‘In the example prompt template P0, brackets denote parameters that can be filled in or replaced with specific data values, e.g., at runtime.’; par. 0260; ‘In some implementations, the first position data is validated by searching at least one data store for a standardized job title that matches the first position data; retrieving, from the at least one data store, the standardized job title that matches the first position data; and replacing the first position data with the standardized job title.’).
Regarding claim 19 (dep. on claim 18), the combination of Rosenkranz in view of Varga further teaches:
“accessing a first knowledge base of the one or more knowledge bases associated with the profile” (Rosenkranz: par. 0260; ‘In some implementations, the first position data is validated by searching at least one data store for a standardized job title that matches the first position data; retrieving, from the at least one data store, the standardized job title that matches the first position data; and replacing the first position data with the standardized job title.’);
“identifying information within the first knowledge base relevant to the first natural language user input” (Rosenkranz: par. 0260; ‘In some implementations, the first position data is validated by searching at least one data store for a standardized job title that matches the first position data; retrieving, from the at least one data store, the standardized job title that matches the first position data; and replacing the first position data with the standardized job title.’); and
“appending or replacing text in the template based on the identified information” (Rosenkranz: par. 0260; ‘In some implementations, the first position data is validated by searching at least one data store for a standardized job title that matches the first position data; retrieving, from the at least one data store, the standardized job title that matches the first position data; and replacing the first position data with the standardized job title.’).
Regarding claim 20 (dep. on claim 1), the combination of Rosenkranz in view of Varga further teaches:
“wherein said determining the profile comprises: receiving user input identifying the profile” (Rosenkranz: par. 0059; ‘If a selection is received via GUI control element 116, the user's profile page is loaded into the user's display, thereby enabling the user to view their own profile page to, for example, research or recall information needed for the new job post.’).
Conclusion
Other pertinent prior art are cited in the PTO-892 for the applicant's consideration.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MARK VILLENA whose telephone number is (571)270-3191. The examiner can normally be reached 10 am - 6pm EST Monday through Friday.
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, Richemond Dorvil can be reached at (571) 272-7602. 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.
MARK . VILLENA
Examiner
Art Unit 2658
/MARK VILLENA/Examiner, Art Unit 2658