Prosecution Insights
Last updated: October 02, 2026
Application No. 18/666,244

RECURSIVE MULTI-METRIC EXPANSION FOR QUERIES

Non-Final OA §101
Filed
May 16, 2024
Examiner
MOSER, BRUCE M
Art Unit
2154
Tech Center
2100 — Computer Architecture & Software
Assignee
Salesforce Inc.
OA Round
4 (Non-Final)
84%
Grant Probability
Favorable
4-5
OA Rounds
4m
Est. Remaining
99%
With Interview

Examiner Intelligence

Grants 84% — above average
84%
Career Allowance Rate
632 granted / 751 resolved
+29.2% vs TC avg
Strong +20% interview lift
Without
With
+20.1%
Interview Lift
resolved cases with interview
Typical timeline
2y 8m
Avg Prosecution
36 currently pending
Career history
802
Total Applications
across all art units

Statute-Specific Performance

§101
22.7%
-17.3% vs TC avg
§103
25.1%
-14.9% vs TC avg
§102
30.5%
-9.5% vs TC avg
§112
14.3%
-25.7% vs TC avg
Black line = Tech Center average estimate • Based on career data from 751 resolved cases

Office Action

§101
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 . Detailed Action In amendments dated 4/28/26, Applicant amended claims 1, 8, 13, 17, and 19, canceled no claims, and added no new claims. Claims 1, 4-13, 15-19, and 21-24 are presented for examination. Rejections under 35 U.S.C. 101 35 U.S.C. 101 reads as follows: Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title. Claims 1, 4-13, 15-19, and 21-24 are rejected under 35 U.S.C. 101 because the claimed invention is directed to mental processes without significantly more. Independent claims 1, 13, and 19 each recites inputting, by the CRM system to a large language model (LLM), a first generative prompt based at least in part on the natural language query, the LLM outputting a summary of the natural language query for vector embedding; performing, by the CRM system, a recursive expansion of data metrics for the natural language query based at least in part on the data metric, each step of the recursive expansion comprising: inputting, by the CRM system to the LLM, an additional generative prompt associated with an expansion of a set of data metrics of the multi-tenant database system, the LLM outputting a set of additional summaries for the vector embedding in response to the additional generative prompt; identifying, by the CRM system, one or more matched data metrics that correspond to the set of additional query response portions, wherein the one or more matched data metrics affect the data metric, at least one data metric identified in a previous step of the recursive expansion, or any combination thereof; and limiting, by the CRM system, a quantity of steps of the recursive expansion to be equal to a threshold depth for recursion, wherein the quantity of steps of the recursive expansion is limited to be equal to the threshold depth for recursion to satisfy a threshold processing overhead associated with a query answering procedure. Inputting a first generative prompt and an additional generative prompt are each recited broadly and are mental processes accomplishable in the human mind or on paper. Identifying one or more matched data metrics involves evaluating and is a mental process. Performing a recursive expansion of data metrics and limiting a quantity of steps of the recursive expansion are each recited broadly and are mental processes accomplishable in the human mind or on paper. Each claim recites additional elements of receiving, at a customer relationship management (CRM) system from a user device, a natural language query associated with a data metric of a multi-tenant database system; receiving, at the CRM system from a vector database associated with the multi-tenant database system, one or more query response portions based at least in part on respective distances between a vector representing the summary of the natural language query and one or more vectors representing the one or more query response portions; and receiving, by the CRM system from the vector database, a set of additional query response portions based at least in part on respective distances between one or more vectors representing the set of additional summaries and one or more vectors representing the set of additional query response portions being less than or equal to a threshold distance; which are each data gathering steps and insignificant extra-solution activity, and transmitting, by the CRM system to the user device, a response to the natural language query based at least in part on the one or more query response portions and the set of additional query response portions for each step of the recursive expansion, which is an output step and insignificant extra-solution activity. Claim 13 recites an apparatus comprising one or more memories storing processor-executable code and one or more processors, and claim 19 recites a non-transitory computer-readable medium storing code, which are each generic components of a computer. Examiner notes paragraphs 0004 and 0014 describes how CRM systems support natural language queries but “the CRM system may fail to expand the scope of the query to determine underlying factors that can indirectly affect the data metric,” and “searching a full set of CRM data to detect any driving factors may involve a significant processing overhead, effectively reducing the efficiency of answering user queries.” Paragraph 0015 describes some of the steps claimed showing how the invention addresses these drawbacks in the prior art, but the claim steps do not recite inventive details that show a particular improvement in any technology or function of a computer per MPEP 2106.04(d) and do not recite any unconventional steps in the invention per MPEP 2106.05(a). Thus the recited mental processes are not integrated into a practical application. Taking the claims as a whole, the receiving steps are broadly recited and amount to receiving data over a network per network 119 in Figure 1 described in specification paragraph 0019, and are each routine and conventional activity per the list of such activities in MPEP 2106.05(d) part II. The transmitting step is also broadly recited and amounts to sending data over a network per network 119 in Figure 1 described in specification paragraph 0019, and is also routine and conventional activity per the list of such activities in MPEP 2106.05(d) part II. The recited one or more memories storing processor-executable code, one or more processors, and non-transitory computer-readable medium are still generic components of a computer. Thus the claims do not include additional elements that are sufficient to amount to significantly more than the recited mental processes. Claims 4 and 21 each recites receiving, from the user device, an indication of the threshold depth for recursion (receiving an indication is receiving data across a network and is routine and conventional activity per the list of such activities in MPEP 2106.05(d) part II). Claims 5 and 22 each recites setting the threshold depth for recursion to a default value (setting data is a mental process accomplishable in the human mind or on paper). Claims 6 and 15 each recites inputting, to the LLM and for a first step of the recursive expansion, a second generative prompt associated with broadening from the data metric to a first set of additional data metrics, the LLM outputting a set of non-specific metrics relating to the data metric (inputting data to a model is a mental process accomplishable in the human mind or on paper); and receiving, from the vector database, the first set of additional data metrics based at least in part on the set of non-specific metrics relating to the data metric, wherein the additional generative prompt for the first step of the recursive expansion is based at least in part on the first set of additional data metrics (receiving a set of metrics is receiving data across a network and is routine and conventional activity per the list of such activities in MPEP 2106.05(d) part II). Claims 7 and 16 each recites inputting, to the LLM, a second generative prompt based at least in part on the natural language query, the one or more query response portions, and the set of additional query response portions for each step of the recursive expansion, wherein the LLM outputs the response to the natural language query (inputting data to a model is a mental process accomplishable in the human mind or on paper). Claims 8 and 17 each recites retrieving, from the multi-tenant database system, a plurality of data metrics associated with data for the CRM system (retrieving data is routine and conventional activity per the list of such activities in MPEP 2106.05(d) part II); inputting, to the LLM, one or more generative prompts based at least in part on the plurality of data metrics, the LLM outputting a plurality of summaries of the data for the CRM system (inputting data to a model is a mental process accomplishable in the human mind or on paper); and embedding the plurality of summaries as a plurality of vectors in a vector space corresponding to the vector database associated with the multi-tenant database system, wherein the plurality of vectors comprises the one or more vectors representing the one or more query response portions (embedding data as vectors creating or adding data as vectors and is a mental process accomplishable in the human mind or on paper). Claims 9 and 18 each recites updating the plurality of vectors embedded in the vector space based at least in part on an update to the data for the CRM system (updating vectors is saving data in the vectors and is routine and conventional activity per the list of such activities in MPEP 2106.05(d) part II). Claim 10 recites wherein: the data for the CRM system corresponds to a first tenant of a plurality of tenants of the multi-tenant database system (determining data corresponds to a first tenant is a judgement and a mental process); and the vector database corresponds to data summaries for the first tenant (determining stored data corresponds to other data is a mental process). Claims 11 and 23 each recites wherein the natural language query associated with the data metric comprises a question asking why a change occurred to the data metric in the multi-tenant database system (a query asking a question is a mental process). Claims 12 and 24 each recites wherein the one or more query response portions indicate one or more changes to other data metrics in the multi-tenant database system that affected the data metric in the multi-tenant database system (response portions indicating changes to data is a mental process accomplishable in the human mind or on paper). Relevant Prior Art During his search for prior art, Examiner found the following reference to be relevant to Applicant's claimed invention. Said reference is listed on the Notice of References form included in this office action: Cantu et al (US 20250028746) teaches receiving a natural language query from a user and generating a prompt for a LLM comprising a context block for the query, does not teach recursively expanding data metrics for the query of generating summary information and one or more vectors from the LLM (paragraphs 0006, 0015, 0142, 0196-0210 figure 9). Responses to Applicant’s Remarks Regarding rejections of claims 1, 4-13, 15-19, and 21-24 under 35 U.S.C. 101 for the claims being directed to mental processes without significantly more, Applicant’s arguments have been considered but are not persuasive. On pages 11-12 of his Remarks Applicant discusses Step 2A Prong One and note the claim limitations now recite actions being performed by a customer relationship management (CRM) system and thus the claims do not recite a mental processes because they cannot be performed in the human mind. Examiner disagrees as the recited CRM system is a generic computer component and MPEP 2106.05(f)(2) states “Use of a computer or other machinery in its ordinary capacity for economic or other tasks (e.g., to receive, store, or transmit data) or simply adding a general purpose computer or computer components after the fact to an abstract idea (e.g., a fundamental economic practice or mathematical equation) does not integrate a judicial exception into a practical application or provide significantly more.” The inputting step, performing step, second inputting step, and limiting step, along with the amended identifying step have been identified as mental processes in the rejection above. That each step is recited as using a generic computer, specifically a CRM system on the generic computer, to perform each step does not change the steps from being mental processes. On pages 12-18 Applicant discusses Step 2A Prong Two, excerpts and discusses specification paragraphs 0038, 0039, 0014-0015, 0040, 0045-0047, and asserts the amended features “improve the functioning of a CRM system associated with a multi-tenant database by improving search and identification of additional metrics for the generation of a response to a natural language query.” Examiner disagrees as the claim limitations do not recite details from the invention that might show such improvements to the technology of search and identification of additional metrics. Specifically, the claim recites receiving a natural language query about a search, and the claim recites identifying one or more matched data metrics but does not recite how said one or more matched data metrics are identified. While the claim recites receiving “query response portions based at least in part on respective distances between a vector representing the summary of the natural language query and one or more vectors representing the one or more query response portions” and receiving “a set of additional query response portions based at least in part on respective distances between one or more vectors representing the set of additional summaries and one or more vectors representing the set of additional query response portions being less than or equal to a threshold distance,” the details showing how the invention calculates these respective distances are also not claimed. Furthermore, the claim recites “limiting, by the CRM system, a quantity of steps of the recursive expansion based at least in part on to be equal to a threshold depth for recursion” and, while this is mentioned as an improvement in paragraph 0015, details showing how the invention determines this threshold depth and limits the steps of the recursive expansion are not claimed. MPEP 2106.04(d)(1) states, “if the specification sets forth an improvement in technology, the claim must be evaluated to ensure that the claim itself reflects the disclosed improvement. That is, the claim includes the components or steps of the invention that provide the improvement described in the specification.” Conclusion THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a). A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action. Inquiry Any inquiry concerning this communication or earlier communications from the examiner should be directed to BRUCE M MOSER whose telephone number is (571)270-1718. The examiner can normally be reached M-F 9a-5p. 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, Boris Gorney can be reached at 571 270-5626. 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. /BRUCE M MOSER/Primary Examiner, Art Unit 2154 7/8/26
Read full office action

Prosecution Timeline

Show 4 earlier events
Dec 02, 2025
Request for Continued Examination
Dec 10, 2025
Response after Non-Final Action
Jan 28, 2026
Non-Final Rejection mailed — §101
Apr 20, 2026
Examiner Interview Summary
Apr 20, 2026
Applicant Interview (Telephonic)
Apr 28, 2026
Response Filed
Jul 13, 2026
Final Rejection mailed — §101
Sep 14, 2026
Response after Non-Final Action

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12711150
FASTER VIEW CHANGE FOR BLOCKCHAIN
2y 11m to grant Granted Aug 18, 2026
Patent 12669790
BUILDING MANAGEMENT SYSTEM WITH NESTED STREAM GENERATION
2y 0m to grant Granted Jun 30, 2026
Patent 12602403
SCALABLE PARALLEL CONSTRUCTION OF BOUNDING VOLUME HIERARCHIES
4y 2m to grant Granted Apr 14, 2026
Patent 12585717
System and Method for Recommending Users Based on Shared Digital Experiences
2y 6m to grant Granted Mar 24, 2026
Patent 12579198
TEXT STRING COMPARISON FOR DUPLICATE OR NEAR-DUPLICATE TEXT DOCUMENTS IDENTIFIED USING AUTOMATED NEAR-DUPLICATE DETECTION FOR TEXT DOCUMENTS
1y 1m to grant Granted Mar 17, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

Strategy Recommendation AI-generated — please review before filing

Get a prosecution strategy drawn from examiner precedents, rejection analysis, and claim mapping.
Typically takes 5-10 seconds — AI-generated, attorney review required before filing

Prosecution Projections

4-5
Expected OA Rounds
84%
Grant Probability
99%
With Interview (+20.1%)
2y 8m (~4m remaining)
Median Time to Grant
High
PTA Risk
Based on 751 resolved cases by this examiner. Grant probability derived from career allowance rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month