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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 12/17/2025 has been entered.
Claims 1, 14 and 19 have been amended. Claims 1 and 3-21 are pending and have been examined.
Terminal Disclaimer
The terminal disclaimer filed on 12/17/2025 disclaiming the terminal portion of any patent granted on this application which would extend beyond the expiration date of US Patent Application Number 18/777,969has been reviewed and is accepted. The terminal disclaimer has been recorded.
Response to Arguments
Applicant's arguments on p. 22-31 filed 12/17/2025 have been fully considered but they are not persuasive.
On pp. 22-27 of the 12/17/2025 remarks, Applicant essentially argues that cited art of record Lee and Davies fail to teach “first refrigeration system type omitted from the nominal set of refrigeration system types.” In particular, Applicant argues on pp. 23-24 that reliance upon Davies to teach “a system type omitted from the nominal set of refrigeration system types” ignores key language of the limitations that distinguish from the teaching of Lee and Davis. In response to applicant's argument that Davies fails to fully teach the claimed limitations, the test for obviousness is not whether the features of a secondary reference may be bodily incorporated into the structure of the primary reference; nor is it that the claimed invention must be expressly suggested in any one or all of the references. Rather, the test is what the combined teachings of the references would have suggested to those of ordinary skill in the art. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981). As cited in the rejection below, each element of the claims is taught by the combination of Lee in view of Davies. Lee is relied upon for the broad teaching of training a language model to utilize sensor data of a refrigeration unit of a refrigeration system type (e.g. ¶ 0057 and 0076 “receive information regarding an item of equipment to be serviced, such as sensor data”). Note that Lee broadly teaches the use of language models to predict text based upon data that does not yet exist in the training database (see ¶ 0029, 0044, 0067 and 0164-0169 as cited in the rejection below). Davies is relied upon to specifically teach machine maintenance predictions for a model of a machine that is not available (e.g. see ¶ 0068 “… determining that no profile for that specific type of repair operation and that model is available.”). While Davies may not specifically teach predictions regarding refrigeration systems, Lee, not Davies, was relied upon to teach this aspect of the limitations.
Applicant continues on pp. 25-26 to suggest that Davies fails to teach claim limitations regarding “proximity in an embedding space … corrective actions for refrigeration system types …” In response to applicant's arguments against the references individually, one cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986). As noted previously, the rejection is based upon combination of Lee in view of Davies. Lee, not Davies, is generally relied upon to disclose proximity of embeddings and corrective actions for refrigeration system types.
In response to applicant's argument that the references fail to show certain features of the invention, it is noted that the features upon which applicant relies (i.e., see the list of 4 items in section 2 on p. 28 of the remarks) are not recited in the rejected claim(s). Although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims. See In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993).
In response to applicant’s argument that there is no teaching, suggestion, or motivation to combine the references, the examiner recognizes that obviousness may be established by combining or modifying the teachings of the prior art to produce the claimed invention where there is some teaching, suggestion, or motivation to do so found either in the references themselves or in the knowledge generally available to one of ordinary skill in the art. See In re Fine, 837 F.2d 1071, 5 USPQ2d 1596 (Fed. Cir. 1988), In re Jones, 958 F.2d 347, 21 USPQ2d 1941 (Fed. Cir. 1992), and KSR International Co. v. Teleflex, Inc., 550 U.S. 398, 82 USPQ2d 1385 (2007). In this case, both Lee and Davies teach systems to assist in predicting problems/troubleshooting complex mechanical systems. While Lee is specifically directed to building systems such as refrigeration units, and Davies is specifically directed to vehicle production, both references generally utilize predictive analytics to assist in complex equipment troubleshooting and maintenance. As indicated in the rejection, Lee teaches that machine learning models can generate data based upon data that is not present in the training data. And Davies teaches that predictions related to a machine model that is not present can be provided in order to make full use of relevant data even with insufficient records. Therefore, Davies provides the explicit suggestion to one of ordinary skill that such relevant data can be used to provided predictions with respect to a missing type of machine.
On pp. 29-30 of the remarks, Applicant argues that cited art of record Lee fails to disclose limitation related to a series of limitations of claims 5 and 19. These arguments fail to provide any technical reasoning or analysis and are conclusory without any particular rationale. The argument is not persuasive.
Applicant’s remaining arguments on p. 31 are based upon previous arguments and are not persuasive for the reasons provided above.
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.
Claims 1, 5-7, 14-16 and 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent Application Publication 20240403613 by Lee et al. ("Lee") in view of U.S. Patent Application Publication 20210070258 by Davies et al. ("Davies").
In regard to claim 1, Lee discloses:
1. A method comprising: See at least Fig. 8, broadly depicting a method.
during an initial time period:
extracting a set of language concepts from a set of documents comprising refrigeration manuals for a nominal set of refrigeration system types; Lee, ¶ 0028, “refrigeration (HVAC-R) systems and components …” Also ¶ 0049, “For example, the training data can include examples of HVAC-R data, such as operating manuals, technical data sheets, configuration settings, operating setpoints, diagnostic guides, troubleshooting guides, user reports, technician reports.”
aggregating the set of language concepts into a corpus of textual training data comprising descriptors of: Lee Fig. 1 element 112, “Data Sources.”
characteristics of the nominal set of refrigeration system types; anomalous behaviors occurring within refrigeration units of the nominal set of refrigeration system types; root causes of anomalous behaviors occurring within refrigeration units of the nominal set of refrigeration system types; and Lee, ¶ 0035, “Systems and methods in accordance with the present disclosure can leverage the efficiency of language models (e.g., GPT-based models or other pre-trained LLMs) in extracting semantic information (e.g., semantic information identifying faults, causes of faults, and other accurate expert knowledge regarding equipment servicing) from the unstructured data in order to use both the unstructured data and the data relating to equipment operation to generate more accurate outputs regarding equipment servicing.” Also Lee, ¶ 0055, “The engineering data can include specifications or other information regarding operation of items of equipment. The engineering data can include engineering drawings, process flow diagrams, refrigeration cycle parameters (e.g., temperatures, pressures), or various other information relating to structures and functions of items of equipment.”
tools, replacement parts, and procedures for correcting root causes of anomalous behaviors at refrigeration units of the nominal set of refrigeration system types; Lee, ¶ 0036, “The system can use the interface to present information regarding parts and/or tools to service the equipment, as well as instructions for how to use the parts and/or tools to service the equipment.” Also ¶ 0064-0065, “solutions to equipment issues, … parts data … tools …”
training a language model on the corpus of textual training data … See Lee, ¶ 0030, “training.” See Fig. 1, elements 104 and 116 depicting a training process.
… to generate: textual descriptions of possible root causes of anomalous behaviors occurring within a global set of refrigeration system types comprising the nominal set of refrigeration system types; and Lee, ¶ 0036, “accurately generating predictions of root cause.” Also Fig. 12 and ¶ 181, “At step 1204, description of one or more causes and/or solutions are generated.” Also ¶ 0183-0190 providing an example of a generated output. Also ¶ 0049 and 0053, “For example, the training data can include examples of HVAC-R data, such as operating manuals, technical data sheets, configuration settings, operating setpoints, diagnostic guides, troubleshooting guides, user reports, technician reports.” … “For example, the system 100 can determine the second model 116 by modifying the first model 104 using data from the one or more data sources 112.” In one interpretation, a global model 104 is updated to include nominal data 112, resulting in model 116 which provides both the global 104 and the additional elements related to the nominal data in element 112. Also ¶ 0073, “enable the second model 116 to be responsive to analogous information for runtime/inference time operations.”
textual descriptions of tools, replacement parts, and procedures for correcting root causes of anomalous behaviors at the global set of refrigeration units; See ¶ 0049 and 0053 as well as Fig. 12 and ¶0181 as cited above. Also Lee, ¶ 0036, “The system can use the interface to present information regarding parts and/or tools to service the equipment, as well as instructions for how to use the parts and/or tools to service the equipment.” Also ¶ 0082, “generate outputs for presenting service recommendations, such as actions to perform to address the service request.”
during a first time period succeeding the initial time period:
accessing a set of sensor data captured via a set of sensors coupled to a refrigeration unit of a first refrigeration system type …; and ¶ 0033, “The system can couple unstructured service data to other input/output data sources and analytics, such as to relate unstructured data with outputs of timeseries data from equipment (e.g., sensor data; report logs).” Also ¶ 0057, “Warranty data can be provided from a database of warranty claims … for a large number of different equipment units (e.g., greater than 30,000 chillers), for a variety of different equipment types (e.g., greater than 30 chiller types), …” Also ¶ 0076, “The virtual assistant application can receive information regarding an item of equipment to be serviced, such as sensor data, text descriptions, or camera images, and process the received information using the second model 116 to generate corresponding responses.”
Lee discloses the use of machine learning language models to predict text based upon data that does not yet exist in the training database. E.g. see ¶ 0029, “For example, the text information may correspond to different items of equipment or versions of items of equipment to be serviced. The text information, being predefined, may not account for specific technical issues that may be present in the items of equipment to be serviced.” ¶ 0044, “For example, the first model 104 can predict or generate new data (e.g., artificial data; synthetic data; data not explicitly represented in data used for configuring the first model 104).” ¶ 0067, “allow the models 104, 116 to be trained using information indicative of causes of issues across multiple items of equipment (which may have the same or similar causes even if the data regarding the items of equipment is not identical).” ¶ 0164-0169: “Without the teachings here, a large language model may return an error such as “I am not familiar with “YMC2 chiller” rather than providing actionable, particularized information as in the example given here.”
While Lee discloses use of a model that provides analysis of data that is omitted from the training dataset (see above), Lee does not expressly disclose a system type omitted from the nominal set of refrigeration system types. However, this is taught by Davies. See ¶ 0064-0075, e.g. “… determining that no preferred profile matching the set of vehicle records according to primary matching criteria is available. … determining that no profile for that specific type of repair operation and that model is available.” It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Davies’ omitted/backup profile in Lee’s machine learning model training data in order to make full use of available relevant data and provide predictions in case of insufficient records as suggested by Davies (see ¶ 0064 and ¶ 0292).”
Lee also discloses:
based on the set of sensor data, detecting a first anomalous behavior occurring at the refrigeration unit of the first refrigeration system type; Lee, Fig. 8, element 805, e.g. “Monitor Equipment to Detect Equipment Fault Condition.”
in response to detecting the first anomalous behavior occurring at the refrigeration unit:
autonomously generating a first textual descriptor of the first anomalous behavior; Lee Fig. 8 element 820 and ¶ 0144, “For example, one or more of the cause of the fault condition, the fault condition, and an identifier of the equipment can be provided to a language model to cause the language model to generate the prescription. The prescription can have a natural language format.”
accessing a set of characteristics of the refrigeration unit of the first refrigeration system type; Lee, ¶ 0055, “refrigeration cycle parameters (e.g., temperatures, pressures).” Also ¶ 0120, “evaluate data relative to thresholds relating to data including, for example and without limitation, acceptable data ranges, setpoints, temperatures, pressures, flow rates (e.g., mass flow rates), or vibration rates for an item of equipment.” Also ¶ 0141-0143, “The fault condition can be detected responsive to manual and/or automated monitoring of various data sources regarding the item of equipment. … data regarding the equipment used to detect the fault condition.”
generating a first text string describing a first root cause of the first anomalous behavior based on: Lee, Fig. 8 element 815 “Identify Cause of Fault Condition.” Lee ¶ 0068, “The model updater 108 can configure the second models 116, using the data sources 112, to generate outputs (e.g., completions) in response to receiving inputs (e.g., prompts), where the inputs and outputs can be analogous to data of the data sources 112.” Also Fig. 8 element 820 and ¶ 0144, “At 820, a prescription is generated based on the cause of the fault condition. … The prescription can have a natural language format.”
proximity of the set of characteristics of the refrigeration unit of the first refrigeration system type to characteristics of the nominal set of refrigeration system types represented in the language model; and Lee teaches training model to provide an output that is “close” or “proximal” to training data. See ¶ 0071, “evaluation can indicate how closely the candidate outputs generated by the candidate second model 116 correspond to the ground truth represented by the training data.” Lee also teaches a trained model utilizes data including characteristics of refrigeration system types when presented with an input regarding a particular refrigeration unit. Also see ¶ 0053, “… such as data associated with HVAC-R components and procedures including but not limited to installation, operation, configuration, repair, servicing, diagnostics, and/or troubleshooting of HVAC-R components and systems. … The system 100 can determine relations between data from different sources, such as by using timeseries information and identifiers of the sites or buildings at which items of equipment are present to detect relationships between various different data relating to the items of equipment (e.g., to train the models 104, 116 using both timeseries data (e.g., sensor data; outputs of algorithms or models, etc.) regarding a given item of equipment and freeform natural language reports regarding the given item of equipment).”
proximity of the first textual descriptor to troubleshooting descriptions represented in the language model for a subset of analogous refrigeration system types in the nominal set of refrigeration system types; Lee teaches proximity evaluation at least at ¶ 0071 as noted above. Also see Lee ¶ 0053, “… data associated with HVAC-R components and procedures including but not limited to installation, operation, configuration, repair, servicing, diagnostics, and/or troubleshooting of HVAC-R components and systems. … The system 100 can determine relations between data from different sources, such as by using timeseries information and identifiers of the sites or buildings at which items of equipment are present to detect relationships between various different data relating to the items of equipment (e.g., to train the models 104, 116 using both timeseries data (e.g., sensor data; outputs of algorithms or models, etc.) regarding a given item of equipment and freeform natural language reports regarding the given item of equipment).”
Also see ¶ 0068, “The model updater 108 can configure the second models 116, using the data sources 112, to generate outputs (e.g., completions) in response to receiving inputs (e.g., prompts), where the inputs and outputs can be analogous to data of the data sources 112.” Also ¶ 0073, “… enable the second model 116 to be responsive to analogous information for runtime/inference time operations.”
Also ¶ 0111, “For example, the completion evaluator 324 can identify data of the data repository 204 having similar text as the prompts and/or completions (e.g., using any of various natural language processing algorithms), and determine whether the data of the completions is within a range of expected data represented by the data of the data repository 204.” Also ¶ 0143, “For example, at least one of an identifier of the equipment, the fault condition, user text or speech identifying the fault condition (e.g., notes from any of a variety of entities, such as a facility manager, on-site technician, etc.), or data regarding the equipment used to detect the fault condition can be applied as input to the function to enable the function to determine an indication of a cause of the fault condition.”
generating a second text string describing a first set of tools, a first set of replacement parts, and a first sequence of steps of a first procedure for correcting the first anomalous behavior at the refrigeration unit of the first refrigeration system type based on proximity of the first textual descriptor for the first anomalous behavior to corrective action descriptions represented in the language model for the subset of analogous refrigeration units; Lee, ¶ 0036, “The system can use the interface to present information regarding parts and/or tools to service the equipment, as well as instructions for how to use the parts and/or tools to service the equipment.” Also Fig. 8 ¶ 0068, “using the data sources 112, to generate outputs (e.g., completions) in response to receiving inputs (e.g., prompts), where the inputs and outputs can be analogous to data of the data sources 112.” Also ¶ 0111, “For example, the completion evaluator 324 can identify data of the data repository 204 having similar text as the prompts and/or completions (e.g., using any of various natural language processing algorithms), and determine whether the data of the completions is within a range of expected data represented by the data of the data repository 204.”
generating a notification comprising the first textual descriptor, the first text string, and the second text string; and serving the notification to an operator associated with the refrigeration unit. See Fig. 8, element 820. Also ¶ 0032, “The system can enable real-time messaging and/or conversational interfaces for users to provide field data regarding equipment to the system (including presenting targeted queries to users that are expected to elicit relevant responses for efficiently receiving useful response information from users) and guide users, such as service technicians, through relevant service, diagnostic, troubleshooting, and/or repair processes.” Also ¶ 0075, “The applications 120 can receive an input, such as a prompt (e.g., from a user), provide the prompt to the second model 116 to cause the second model 116 to generate an output, such as a completion in response to the prompt, and present an indication of the output.” Also ¶ 0082, “cause the second model 116 to generate outputs for presenting service recommendations.” Also ¶ 0149, “… provide various information such as the service request, prescription, and/or communications between the user and the language model via the application session to the device of the human expert, …”
In regard to claim 5, Lee discloses:
5. The method of claim 1, wherein generating the text string comprises:
generating a query requesting identification of the root cause of the anomalous behavior in the refrigeration unit; Lee, Fig. 8 elements 815 and 820, and ¶ 0144 as cited above. Also ¶ 0075, “The applications 120 can receive an input, such as a prompt.”
generating a first embedding corresponding to the query and representing semantic relationships of words in the query; Lee ¶ 0034, “semantic data.” Also ¶ 0046, “the GPT model can convert the input sequence into a modified input sequence, such as by applying an embedding matrix to the token tokens of the input sequence (e.g., using a neural network embedding function).”
based on the first embedding and a set of embeddings represented in the language model and corresponding to the corpus of textual training data, extracting a first set of language concepts proximal a subset of embeddings, in the set of embeddings, proximal the first embedding; and generating the first text string based on the first set of language concepts. Lee ¶ 0053, 0068, 0073, 0111, 0143 as cited above.
In regard to claim 6, Lee discloses:
6. The method of claim 1, wherein training the language model further comprises:
accessing a set of observed anomalous behaviors exhibited by refrigeration units of the set of nominal refrigeration system types;
accessing a set of known root causes corresponding to the set of observed anomalous behaviors, each known target root cause, in the set of known root causes, corresponding to a particular observed anomalous behavior, in the set of observed anomalous behaviors; and
for each observed anomalous behavior in the set of observed anomalous behaviors:
executing the language model to predict a root cause, in a set of predicted root causes, of the observed anomalous behavior;
characterizing a difference between the root cause and a known root cause, in the set of known root causes, corresponding to the observed anomalous behavior; and
in response to the difference exceeding a threshold difference, modifying parameters of the language model to reduce prediction error.
See Lee, ¶ 0032, “The system can implement various automated and/or expert-based thresholds and data quality management processes to improve the accuracy and quality of generated outputs and update training of the machine learning models accordingly.” Also ¶ 0044, “The parameters of the nodes can be configured by various learning or training operations, such as unsupervised learning, weakly supervised learning, semi-supervised learning, or supervised learning.” Also ¶ 0071, “For example, the model updater 108 can evaluate an objective function of the convergence condition, such as a loss function (e.g., L1 loss, L2 loss, root mean square error, cross-entropy or log loss, etc.) based on the one or more candidate outputs and the training data; this evaluation can indicate how closely the candidate outputs generated by the candidate second model 116 correspond to the ground truth represented by the training data.”
In regard to claim 7, Lee discloses:
7. The method of claim 1:
wherein accessing the set of sensor data capture via the set of sensors comprises accessing a timeseries of temperature data captured by a set of temperature sensors coupled to the refrigeration unit; and ¶ 0053, “The system 100 can determine relations between data from different sources, such as by using timeseries information and identifiers of the sites or buildings at which items of equipment are present to detect relationships between various different data relating to the items of equipment (e.g., to train the models 104, 116 using both timeseries data (e.g., sensor data; outputs of algorithms or models, etc.) regarding a given item of equipment and freeform natural language reports regarding the given item of equipment)”
wherein generating the first textual descriptor in response to detecting the first anomalous behavior based on the set of sensor data comprises:
identifying a series of outlier temperatures in the timeseries of temperature data; ¶ 0120 “For example, the data filters 500 can be used to evaluate data relative to thresholds relating to data including, for example and without limitation, acceptable data ranges, setpoints, temperatures, pressures, flow rates (e.g., mass flow rates), or vibration rates for an item of equipment.”
in response to identifying the series of outlier temperatures in the timeseries of temperature data, detecting the first anomalous behavior at the refrigeration unit; and in response to detecting the first anomalous behavior, generating the first textual descriptor indicating the series of outlier temperatures. Lee, ¶ 0120-0121, e.g. “For example, the data filters 500 can be used to evaluate data relative to thresholds relating to data including, for example and without limitation, acceptable data ranges, setpoints, temperatures, pressures, flow rates (e.g., mass flow rates), or vibration rates for an item of equipment.”
In regard to claim 14, Lee discloses:
14. A method comprising: See at least Fig. 8, broadly depicting a method.
…
Lee discloses the use of machine learning language models to predict text based upon data that does not yet exist in the training database. E.g. see ¶ 0029, “For example, the text information may correspond to different items of equipment or versions of items of equipment to be serviced. The text information, being predefined, may not account for specific technical issues that may be present in the items of equipment to be serviced.” ¶ 0044, “For example, the first model 104 can predict or generate new data (e.g., artificial data; synthetic data; data not explicitly represented in data used for configuring the first model 104).” ¶ 0067, “allow the models 104, 116 to be trained using information indicative of causes of issues across multiple items of equipment (which may have the same or similar causes even if the data regarding the items of equipment is not identical).” ¶ 0164-0169: “Without the teachings here, a large language model may return an error such as “I am not familiar with “YMC2 chiller” rather than providing actionable, particularized information as in the example given here.”
While Lee discloses use of a model that provides analysis of data that is omitted from the training dataset (see above), Lee does not expressly disclose a refrigeration system type excluded from the nominal set of refrigeration system types. However, this is taught by Davies. See ¶ 0064-0075, e.g. “… determining that no preferred profile matching the set of vehicle records according to primary matching criteria is available. … determining that no profile for that specific type of repair operation and that model is available.” It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Davies’ omitted/backup profile in Lee’s machine learning model training data in order to make full use of available relevant data and provide predictions in case of insufficient records as suggested by Davies (see ¶ 0064 and ¶ 0292).”
Lee also discloses:
…
based on the sensor data, in response to detecting the first anomalous behavior occurring at the refrigeration unit of the refrigeration system type excluded from the nominal set of refrigeration system types represented in the language model: generating a first textual descriptor of the first anomalous behavior; Lee Fig. 8 element 820 and ¶ 0144, “For example, one or more of the cause of the fault condition, the fault condition, and an identifier of the equipment can be provided to a language model to cause the language model to generate the prescription. The prescription can have a natural language format.”
…
based on proximity of the first textual descriptor to corrective action descriptions represented in the language model for the subset of analogous refrigeration system types, retrieving a first corrective action description describing a first set of replacement parts for correcting anomalous behaviors, analogous the first anomalous behavior, at refrigeration units of a first refrigeration system type, in the nominal set of refrigeration system types, represented in the language model; Lee, ¶ 0036, “The system can use the interface to present information regarding parts and/or tools to service the equipment, as well as instructions for how to use the parts and/or tools to service the equipment.” Also Fig. 8 ¶ 0068, “using the data sources 112, to generate outputs (e.g., completions) in response to receiving inputs (e.g., prompts), where the inputs and outputs can be analogous to data of the data sources 112.” Also ¶ 0111, “For example, the completion evaluator 324 can identify data of the data repository 204 having similar text as the prompts and/or completions (e.g., using any of various natural language processing algorithms), and determine whether the data of the completions is within a range of expected data represented by the data of the data repository 204.”
converting the first set of replacement parts to a second set of replacement parts for correcting the first anomalous behavior at the refrigeration unit based on the set of characteristics of the refrigeration unit, Lee ¶ 0068, “The model updater 108 can configure the second models 116, using the data sources 112, to generate outputs (e.g., completions) in response to receiving inputs (e.g., prompts), where the inputs and outputs can be analogous to data of the data sources 112.”
Lee does not expressly disclose the refrigeration unit of a second refrigeration system type not represented in the language model. However, this is taught by Davies. See ¶ 0064-0075, e.g. “… determining that no preferred profile matching the set of vehicle records according to primary matching criteria is available. … the backup profile may be a profile for a different model of vehicle, or a model group comprising the vehicle model and at least one other vehicle model.” It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Davies’ omitted/backup profile in Lee’s training data in order to make full use of available data and provide predictions in case of insufficient records as suggested by Davies (see ¶ 0064 and ¶ 0292).”
Lee also discloses:
generating a second text string describing the second set of replacement parts for correcting the first anomalous behavior at the refrigeration unit; … Lee, ¶ 0036, “The system can use the interface to present information regarding parts and/or tools to service the equipment, as well as instructions for how to use the parts and/or tools to service the equipment.” Also ¶ 0064-0065, “solutions to equipment issues, … parts data … tools …”
…
All further limitations of claim 14 have been addressed in the above rejection of claim 1.
In regard to claim 15, Lee discloses:
15. The method of claim 14:
wherein aggregating the set of language concepts into the corpus of textual training data comprising descriptors of replacement parts for correcting root causes of anomalous behaviors at refrigeration units of the nominal set of refrigeration system types comprises aggregating the set of language concepts into the corpus of textual training data comprising descriptors of tools, replacement parts, and procedures for correcting root causes of anomalous behaviors at refrigeration units of the nominal set of refrigeration system types; Lee, ¶ 0036, “The system can use the interface to present information regarding parts and/or tools to service the equipment, as well as instructions for how to use the parts and/or tools to service the equipment.” Also ¶ 0064-0065, “solutions to equipment issues, … parts data … tools …”
wherein training the language model on the corpus of textual training data to generate textual descriptions of replacement parts for correcting root causes of anomalous behaviors occurring within refrigeration units of the global set of refrigeration system types comprises training the language model on the corpus of textual training data to generate textual descriptions of tools, replacement parts, and procedures for correcting root causes of anomalous behaviors occurring within refrigeration units of the global set of refrigeration system types; and See ¶ 0049 and 0053 as cited above.
wherein generating the second text string describing the first set of replacement parts for correcting the anomalous behavior comprises generating the second text string describing the first set of replacement parts, a first set of tools, and a sequence of steps of a first procedure for correcting the anomalous behavior. Lee, ¶ 0036, “The system can use the interface to present information regarding parts and/or tools to service the equipment, as well as instructions for how to use the parts and/or tools to service the equipment.”
In regard to claim 16, Lee discloses:
16. The method of claim 14, further comprising: serving the second text string to a refrigeration repair technician in preparation for repair of the refrigeration unit by the refrigeration repair technician; and automatically scheduling repair of the refrigeration unit by the refrigeration repair technician. Lee, Fig. 8 elements 830-835.
In regard to claim 18, Lee discloses:
18. The method of claim 14:
wherein generating the first text string describing the root cause based on proximity of the first textual descriptor to troubleshooting descriptions represented in the language model for the subset of analogous refrigeration system types comprises generating the first text string describing the root cause based on proximity of the first textual descriptor to troubleshooting descriptions represented in the language model for a first refrigeration system type, in the nominal set of refrigeration system types, exhibiting characteristics proximal the set of characteristics; and Lee ¶ 0053, 0068, 0073, 0111 and 0143 as cited above.
wherein generating the second text string describing the set of replacement parts for correcting the first anomalous behavior at the refrigeration unit further comprises: extracting a first corrective action description describing a first set of replacement parts for correcting anomalous behaviors, analogous the first anomalous behavior, at refrigeration units of the first refrigeration system type; Lee, ¶ 0036, “The system can use the interface to present information regarding parts and/or tools to service the equipment, as well as instructions for how to use the parts and/or tools to service the equipment.” Also ¶ 0064-0065, “solutions to equipment issues, … parts data … tools …” Also see Rich ¶ 0053 as cited above.
converting the first set of replacement parts to the set of replacement parts for correcting the first anomalous behavior at the refrigeration unit based on the set of characteristics of the refrigeration unit; and generating the second text string describing the set of replacement parts. Lee ¶ 0068, “The model updater 108 can configure the second models 116, using the data sources 112, to generate outputs (e.g., completions) in response to receiving inputs (e.g., prompts), where the inputs and outputs can be analogous to data of the data sources 112.”
In regard to claim 19, Lee discloses:
19. A method comprising: See at least Fig. 8, broadly depicting a method.
during an initial time period:
extracting a set of language concepts from a set of documents describing refrigeration unit management, the set of language concepts comprising descriptions of characteristics of refrigeration units, anomalous behaviors of refrigeration units, and repair of refrigeration units of a nominal set of refrigeration system types; Lee, ¶ 0028, “refrigeration (HVAC-R) systems and components …” ¶ 0035, “Systems and methods in accordance with the present disclosure can leverage the efficiency of language models (e.g., GPT-based models or other pre-trained LLMs) in extracting semantic information (e.g., semantic information identifying faults, causes of faults, and other accurate expert knowledge regarding equipment servicing) from the unstructured data in order to use both the unstructured data and the data relating to equipment operation to generate more accurate outputs regarding equipment servicing.” Also ¶ 0049, “For example, the training data can include examples of HVAC-R data, such as operating manuals, technical data sheets, configuration settings, operating setpoints, diagnostic guides, troubleshooting guides, user reports, technician reports.” Also Lee, ¶ 0055, “The engineering data can include specifications or other information regarding operation of items of equipment. The engineering data can include engineering drawings, process flow diagrams, refrigeration cycle parameters (e.g., temperatures, pressures), or various other information relating to structures and functions of items of equipment.”
aggregating the set of language concepts into a corpus of textual training data; Lee Fig. 1 element 112, “Data Sources.”
representing the corpus of textual training data as a set of embeddings in an embedding space; and Lee ¶ 0034, “semantic data.” Also ¶ 0046, “the GPT model can convert the input sequence into a modified input sequence, such as by applying an embedding matrix to the token tokens of the input sequence (e.g., using a neural network embedding function).”
based on the set of embeddings, training a language model to detect patterns of vocabulary, grammar, and semantics in the corpus of textual training data; and Lee, ¶ 0030, “training.” See Fig. 1, elements 104 and 116 along with ¶ 0049 “For example, the training data can include examples of HVAC-R data, such as operating manuals, technical data sheets, configuration settings, operating setpoints, diagnostic guides, troubleshooting guides, user reports, technician reports.” Also ¶ 0045, e.g. “language models.” Also ¶ 0073, “enable the second model 116 to be responsive to analogous information for runtime/inference time operations.”
Lee does not expressly disclose: … of a first refrigeration system type excluded from the nominal set of refrigeration system types: However, this is taught by Davies. See ¶ 0064-0075, e.g. “… determining that no preferred profile matching the set of vehicle records according to primary matching criteria is available. … the backup profile may be a profile for a different model of vehicle, or a model group comprising the vehicle model and at least one other vehicle model.” It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Davies’ omitted/backup profile in Lee’s training data in order to make full use of available data and provide predictions in case of insufficient records as suggested by Davies (see ¶ 0064 and ¶ 0292).”
Lee also discloses:
during an operating period for a refrigeration unit of a first refrigeration system type …: See Lee, Fig. 3 and ¶ 0106, “IG. 3 depicts an example of the system 200, in which the system 200 can perform operations to implement at least one application session 308 for a client device 304.”
Lee discloses the use of machine learning language models to predict text based upon data that does not yet exist in the training database. E.g. see ¶ 0029, “For example, the text information may correspond to different items of equipment or versions of items of equipment to be serviced. The text information, being predefined, may not account for specific technical issues that may be present in the items of equipment to be serviced.” ¶ 0044, “For example, the first model 104 can predict or generate new data (e.g., artificial data; synthetic data; data not explicitly represented in data used for configuring the first model 104).” ¶ 0067, “allow the models 104, 116 to be trained using information indicative of causes of issues across multiple items of equipment (which may have the same or similar causes even if the data regarding the items of equipment is not identical).” ¶ 0164-0169: “Without the teachings here, a large language model may return an error such as “I am not familiar with “YMC2 chiller” rather than providing actionable, particularized information as in the example given here.”
While Lee discloses use of a model that provides analysis of data that is omitted from the training dataset (see above), Lee does not expressly disclose a refrigeration type excluded from the nominal set of refrigeration system types. However, this is taught by Davies. See ¶ 0064-0075, e.g. “… determining that no preferred profile matching the set of vehicle records according to primary matching criteria is available. … determining that no profile for that specific type of repair operation and that model is available.” It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Davies’ omitted/backup profile in Lee’s machine learning model training data in order to make full use of available relevant data and provide predictions in case of insufficient records as suggested by Davies (see ¶ 0064 and ¶ 0292).”
Lee also discloses:
accessing a set of sensor data representing operation of the refrigeration unit; and ¶ 0033, “The system can couple unstructured service data to other input/output data sources and analytics, such as to relate unstructured data with outputs of timeseries data from equipment (e.g., sensor data; report logs).” Also ¶ 0076, “The virtual assistant application can receive information regarding an item of equipment to be serviced, such as sensor data, text descriptions, or camera images, and process the received information using the second model 116 to generate corresponding responses.”
detecting an anomalous behavior occurring at the refrigeration unit based on the set of sensor data; and
in response to detecting the anomalous behavior occurring at the refrigeration unit of the first refrigeration system type excluded from the nominal set of refrigeration system types represented in the language model: Lee, Fig. 8, element 805, e.g. “Monitor Equipment to Detect Equipment Fault Condition.” Note that Davies teaches excluded types as addressed above.
automatically generating a textual descriptor of the anomalous behavior; Lee Fig. 8 element 820 and ¶ 0144, “For example, one or more of the cause of the fault condition, the fault condition, and an identifier of the equipment can be provided to a language model to cause the language model to generate the prescription. The prescription can have a natural language format.”
retrieving a set of characteristics of the refrigeration unit of the first refrigeration system type; Lee, ¶ 0055, “refrigeration cycle parameters (e.g., temperatures, pressures).” Also ¶ 0120, “evaluate data relative to thresholds relating to data including, for example and without limitation, acceptable data ranges, setpoints, temperatures, pressures, flow rates (e.g., mass flow rates), or vibration rates for an item of equipment.” Also ¶ 0143, “data regarding the equipment used to detect the fault condition.”
generating a query requesting identification of a root cause of the anomalous behavior in the refrigeration unit and describing the set of characteristics; Lee, Fig. 8 element 815 “Identify Cause of Fault Condition.” Lee ¶ 0068, “The model updater 108 can configure the second models 116, using the data sources 112, to generate outputs (e.g., completions) in response to receiving inputs (e.g., prompts), where the inputs and outputs can be analogous to data of the data sources 112.” Also ¶ 0075, “The applications 120 can receive an input, such as a prompt.” Also Fig. 8 element 820 and ¶ 0144, “At 820, a prescription is generated based on the cause of the fault condition. … The prescription can have a natural language format.”
generating a first embedding corresponding to the query and representing semantic relationships of words in the query; Lee ¶ 0034, “semantic data.” Also ¶ 0046, “the GPT model can convert the input sequence into a modified input sequence, such as by applying an embedding matrix to the token tokens of the input sequence (e.g., using a neural network embedding function).
identifying a first subset of embeddings, in the set of embeddings, proximal the first embedding within the embedding space; extracting a subset of language concepts, in the set of language concepts, proximal the first subset of embeddings represented in the embedding space; Lee ¶ 0053, 0068, 0073, 0111, 0143 as cited above.
assembling the subset of language concepts into a first text string describing: a first root cause of the anomalous behavior; and Lee, Fig. 8 element 815 “Identify Cause of Fault Condition.” Lee ¶ 0068, “The model updater 108 can configure the second models 116, using the data sources 112, to generate outputs (e.g., completions) in response to receiving inputs (e.g., prompts), where the inputs and outputs can be analogous to data of the data sources 112.” Also ¶ 0108, “The machine learning model 268 can process the input to generate a completion, and provide the completion to the application session 308 to present via the client device 304.” Also Fig. 8 element 820 and ¶ 0144, “At 820, a prescription is generated based on the cause of the fault condition. … The prescription can have a natural language format.”
a first corrective action for correcting the anomalous behavior at the refrigeration unit; ¶ 0061 “The service data can indicate service procedures performed, including associated service procedures with initial service requests and/or sensor data related conditions to trigger service and/or sensor data measured during service processes.”
generating a first notification comprising the first textual descriptor and the first text string; and serving the first notification to a user associated with the refrigeration unit. See Fig. 8, element 820. Also ¶ 0032, “The system can enable real-time messaging and/or conversational interfaces for users to provide field data regarding equipment to the system (including presenting targeted queries to users that are expected to elicit relevant responses for efficiently receiving useful response information from users) and guide users, such as service technicians, through relevant service, diagnostic, troubleshooting, and/or repair processes.” Also ¶ 0075, “The applications 120 can receive an input, such as a prompt (e.g., from a user), provide the prompt to the second model 116 to cause the second model 116 to generate an output, such as a completion in response to the prompt, and present an indication of the output.” Also ¶ 0082, “cause the second model 116 to generate outputs for presenting service recommendations.” Also ¶ 0149, “… provide various information such as the service request, prescription, and/or communications between the user and the language model via the application session to the device of the human expert, …”
In regard to claim 20, Lee discloses:
20. The method of claim 19:
further comprising:
aggregating the set of language concepts into the corpus of textual training data that further contains descriptors of tools, replacement parts, and procedures for correcting root causes of anomalous behaviors at the first set of refrigeration units; Lee, ¶ 0036, “The system can use the interface to present information regarding parts and/or tools to service the equipment, as well as instructions for how to use the parts and/or tools to service the equipment.” Also ¶ 0064-0065, “solutions to equipment issues, … parts data … tools …”
training the language model on the corpus of textual training data to further generate textual descriptions of tools, replacement parts, and procedures for correcting root causes of anomalous behaviors at the first set of refrigeration units and at the second set of refrigeration units; and See ¶ 0049 and 0053 as cited above.
generating a second text string describing a set of tools, a set of replacement parts, and a sequence of steps of a procedure for correcting the anomalous behavior at the refrigeration unit; and wherein generating the notification comprising the textual descriptor and the first text string comprises generating the notification comprising the textual descriptor the first text string, and the second text string. Lee, ¶ 0036, “The system can use the interface to present information regarding parts and/or tools to service the equipment, as well as instructions for how to use the parts and/or tools to service the equipment.”
Claim(s) 3 is/are rejected under 35 U.S.C. 103 as being unpatentable over Lee and Davies as applied above, and further in view of U.S. Patent Application Publication 20200226475 by Ma et al. ("Ma").
In regard to claim 3, Lee discloses:
3. The method of claim 1:
wherein generating the second text string describing the first set of tools, the first set of replacement parts, and the first sequence of steps of the first procedure based on proximity of the first textual descriptor to corrective action descriptions represented in the language model for the subset of analogous refrigeration units comprises generating the second text string describing the first set of tools, the first set of replacement parts, and the first sequence of steps of the first procedure based on proximity of the first textual descriptor to a first corrective action description represented in the language model for a first refrigeration unit in the subset of analogous refrigeration units; Lee ¶ 0053, 0068, 0073, and 0143 as cited above.
Lee does not expressly disclose: further comprising generating a third text string describing a second set of tools, a second set of replacement parts, and a second sequence of steps of a second procedure for correcting the first anomalous behavior at the refrigeration unit based on proximity of the first textual descriptor to a second corrective action description represented in the language model for a second refrigeration unit in the subset of analogous refrigeration units; and However, this is taught by Ma. See Ma, ¶ 0046, “Alternatively, if the response does not satisfy the user's question, as determined by the chatbot by continued queries from the user, the chatbot may continue attempting to match the query to data from a VAE model of the VSDG and send further responses to the user interface 200.” It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Ma’s second response with Lee’s text generation in order to produce an acceptable/appropriate response as suggested by Ma.
Lee also teaches:
wherein generating the notification comprises generating the notification comprising the first textual descriptor, the first text string, the second text string, and the third text string. See Lee Fig. 8, element 820. Also ¶ 0032, 0075, and 0149 as cited above. Also see Ma, Fig. 2 and related text.
Claim(s) 4 and 11 is/are rejected under 35 U.S.C. 103 as being unpatentable over Lee and Davies as applied above, and further in view of U.S. Patent Application Publication 20230259821 by Travalini et al. ("Travalini").
In regard to claim 4, Lee discloses:
4. The method of claim 1:
Lee does not expressly disclose: wherein generating the notification comprising the first textual descriptor and the first text string comprises generating the notification comprising the first textual descriptor, the first text string, the second text string, and a prompt to authorize a work order for correcting the first anomalous behavior occurring at the refrigeration unit; and further comprising, in response to receiving authorization of the work order: initializing the work order for the refrigeration unit; populating the work order with the second text string; and … However, this is taught by Travalini. See Travalini, ¶ 0045, “If the user indicates “no,” the chatbot may offer to schedule a technician visit for the user. In this regard, the chatbot may be able to perform a work order intake using the information provided by the user during the conversation.” Also ¶ 0052, “the taxonomy, signs, diagnosis, and/or recommendation may be submitted as a work order that corresponds to the maintenance request.” It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Travalini’s work order with Lee’s notification in order to resolve a problem quicker as suggested by Travalini (see ¶ 0045).
Lee also discloses:
serving the work order to a technician for repair of the first refrigeration unit according to the work order. See ¶ 0147, “In some implementations, scheduling deployment includes generating a service ticket indicative of the service to be performed, such as to identify the service technician, the parts, and/or the item of equipment.” Also see Travalini, Abstract, “transmit the enriched work order to the plurality of technicians.”
In regard to claim 11, Lee discloses:
11. The method of claim 1:
further comprising, generating a third text string describing a second root cause of the first anomalous behavior based on: Lee, Fig. 12 and ¶ 0181, “At step 1204, description of one or more causes and/or solutions are generated using the fine-tuned generative AI model based on the question.”
proximity of the set of characteristics to characteristics of the nominal set of refrigeration system types represented in the language model; and proximity of the first textual descriptor to troubleshooting descriptions represented in the language model for the subset of analogous refrigeration system types in the nominal set of refrigeration system types; and See Lee ¶ 0053, 0068, 0073, 0111, and 0143 as cited above.
wherein generating the notification comprising the first textual descriptor, the first text string, and the second text string comprises:
generating the notification comprising the first textual descriptor, the first text string, the second text string, and the third text string; and Lee, Fig. 12 and ¶ 0182, “At step 1206, at least one of a service summary, a labelling of services, or an investigative service report based on the one or more solutions are generated based on the description.”
Lee does not expressly disclose: populating the notification with a prompt to further investigate the first anomalous behavior to verify between the first root cause and the second root cause. However, this is taught by Travalini. See ¶ 0046, “After each solution offered, the chatbot may inquire to determine whether the solution resolved the problem. If so, then the interaction between the chatbot and the user may conclude. However, if the solution did not solve the problem, the chatbot may offer another solution.” It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Travalini’s chatbot with Lee’s notification in order to help resolve a problem as suggested by Travalini.
Claim(s) 8 and 21 is/are rejected under 35 U.S.C. 103 as being unpatentable over Lee and Davies as applied above, and further in view of U.S. Patent Application Publication 20230304714 by et al. ("Huchtemann").
In regard to claim 8, Lee discloses:
8. The method of claim 1:
wherein accessing the set of sensor data captured via the set of sensors comprises accessing a timeseries of pressure data captured by a set of pressure sensors coupled to the refrigeration unit; and ¶ 0120, “For example, the data filters 500 can be used to evaluate data relative to thresholds relating to data including, for example and without limitation, acceptable data ranges, setpoints, temperatures, pressures, flow rates (e.g., mass flow rates), or vibration rates for an item of equipment.”
Lee does not expressly disclose: wherein generating the first textual descriptor in response to detecting the first anomalous behavior based on the set of sensor data comprises: based on the timeseries of pressure data, detecting the first anomalous behavior corresponding to a first decrease in pressure at a compressor discharge of the refrigeration unit and a second decrease in pressure at a compressor suction of the refrigeration unit; and However, this is taught by Huchtemann. See Huchtemann, ¶ 0080, “In addition, the control module 34 may be configured to carry out sensor value slope checks based on the knowledge that a sensor value behaves in a certain way upon a certain operation event. … suction pressure decreases after a start-up of a compressor 28 … refrigerant discharge pressure decreases after a shutdown of a compressor 28. Should the sensor values output from the suction line pressure sensor 42 and the discharge line pressure sensor 48 therefore not show the expected behavior upon the start-up or shutdown of a compressor 28, the control module 34 may issue a corresponding warning, e.g. indicating that the suction line pressure sensor 42 and the discharge line pressure sensor 48 have been interchanged.” It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Huchtemann’s compressor pressure sensors with Lee’s data evaluation in order to issue a warning if a compressor is not behaving as expected, as suggested by Huchtemann.
Lee and Huchtemann also teach:
in response to detecting the first anomalous behavior, generating the first textual descriptor indicating the first decrease in pressure at the compressor discharge and the second decrease in pressure at the compressor suction. See Fig. 8, element 820. Also ¶ 0032, ¶ 0075, 0082, and ¶ 0149 as cited above. Also see Huchtemann, ¶ 0080 as cited above.
In regard to claim 21, Lee discloses:
21. The method of Claim 19:
wherein accessing the set of sensor data comprises accessing a timeseries of pressure data captured by a set of pressure sensors coupled to the refrigeration unit; ¶ 0120, “For example, the data filters 500 can be used to evaluate data relative to thresholds relating to data including, for example and without limitation, acceptable data ranges, setpoints, temperatures, pressures, flow rates (e.g., mass flow rates), or vibration rates for an item of equipment.”
Lee does not expressly disclose: wherein detecting the anomalous behavior occurring at the refrigeration unit based on the set of sensor data comprises, based on the timeseries of pressure data, detecting the anomalous behavior corresponding to a first decrease in pressure at a compressor discharge of the refrigeration unit and a second decrease in pressure at a compressor suction of the refrigeration unit; and However, this is taught by Huchtemann. See Huchtemann, ¶ 0080, “In addition, the control module 34 may be configured to carry out sensor value slope checks based on the knowledge that a sensor value behaves in a certain way upon a certain operation event. … suction pressure decreases after a start-up of a compressor 28 … refrigerant discharge pressure decreases after a shutdown of a compressor 28. Should the sensor values output from the suction line pressure sensor 42 and the discharge line pressure sensor 48 therefore not show the expected behavior upon the start-up or shutdown of a compressor 28, the control module 34 may issue a corresponding warning, e.g. indicating that the suction line pressure sensor 42 and the discharge line pressure sensor 48 have been interchanged.” It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Huchtemann’s compressor pressure sensors with Lee’s data evaluation in order to issue a warning if a compressor is not behaving as expected, as suggested by Huchtemann.
Lee and Huchtemann also teach:
wherein automatically generating the textual descriptor of the anomalous behavior comprises automatically generating the textual descriptor indicating the first decrease in pressure at the compressor discharge and the second decrease in pressure at the compressor suction. See Fig. 8, element 820. Also ¶ 0032, ¶ 0075, 0082, and ¶ 0149 as cited above. Also see Huchtemann, ¶ 0080 as cited above.
Claim(s) 9 is/are rejected under 35 U.S.C. 103 as being unpatentable over Lee and Davies as applied above, and further in view of U.S. Patent Application Publication 20230035639 by Zhao et al. ("Zhao").
In regard to claim 9, Lee discloses:
9. The method of claim 1:
further comprising:
generating a set of embeddings in an embedding space representing the set of documents; and representing the set of language concepts in the embedding space; and Lee ¶ 0046, “the GPT model can convert the input sequence into a modified input sequence, such as by applying an embedding matrix to the token tokens of the input sequence (e.g., using a neural network embedding function).”
wherein generating the first text string based on proximity of the set of characteristics of the refrigeration unit to characteristics of the nominal set of refrigeration system types and proximity of the first textual descriptor to troubleshooting descriptions represented in the language model for the subset of analogous refrigeration system types comprises:
generating a query requesting identification of the first root cause of the first anomalous behavior; ¶ 0075 and 0077, “The applications 120 can receive an input, such as a prompt (e.g., from a user), provide the prompt to the second model 116 to cause the second model 116 to generate an output, such as a completion in response to the prompt, and present an indication of the output. … determine a prediction of a cause of the issue of the item of equipment.”
generating a first embedding in the embedding space corresponding to the query; Lee, ¶ 0046, e.g. “the GPT model can convert the input sequence into a modified input sequence, such as by applying an embedding matrix to the token tokens of the input sequence (e.g., using a neural network embedding function).”
Lee does not expressly disclose: for each embedding in the set of embeddings: calculating a distance between the first embedding and the embedding; and in response to the distance falling below a threshold distance, inserting the embedding in a set of target embeddings; However, this is taught by Zhao. See Zhao, ¶ 0015, “An embedding model is applied to the unstructured data of an untransformed transaction to generate a vector. A cluster ID is assigned to the vector by matching the vector with a cluster of vectors. The cluster ID may identify a cluster of vectors that are within a threshold distance of a centroid.” It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Zhao’s embedding model with Lee’s query in order to accelerate a development cycle while maintaining performance as suggested by Zhao (see ¶ 0017).
Lee also discloses: extracting a first set of language concepts, in the set of language concepts, proximal the set of target embeddings in the embedding space; and assembling the first set of language concepts into the first text string. See Lee, at least ¶ 0111 and 0143 as cited above.
Claim(s) 10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Lee and Davies as applied above, and further in view of U.S. Patent Application Publication 20130048264 by Lu et al. ("Lu").
In regard to claim 10, Lee discloses:
10. The method of claim 1: wherein extracting the set of language concepts from the set of documents comprising refrigeration manuals for the nominal set of refrigeration system types comprises extracting the set of language concepts from the set of documents comprising refrigeration manuals for the nominal set of refrigeration system types comprising: Lee, ¶ 0028 and 0049 as cited above.
a second refrigeration system type defining a second set of characteristics for refrigeration units of the second refrigeration system type, the second set of characteristics comprising … and a first configuration for a set of refrigerator components; and a third refrigeration system type defining a third set of characteristics for refrigeration units of the third refrigeration system type, the third set of characteristics comprising … and a second configuration for the set of refrigerator components; Lee e.g. ¶ 0055, “The data sources 112 can include engineering data regarding one or more items of equipment. The engineering data can include manuals, such as installation manuals, instruction manuals, or operating procedure guides. The engineering data can include specifications or other information regarding operation of items of equipment. The engineering data can include engineering drawings, process flow diagrams, refrigeration cycle parameters (e.g., temperatures, pressures), or various other information relating to structures and functions of items of equipment.”
Lee does not expressly disclose: … a first size and … a second size. However, this is taught by Lu. See Lu, Fig. 4 and ¶ 0045, “In some embodiments, the refrigerated compartment 420 may have an approximate interior volume of 40 liters for storing food items, and may be capable of storing 15 wine-bottle sized beverage bottles. In an exemplary embodiment, the refrigerator 400 may weigh approximately 14 kg when empty, and may have external dimensions of approximately 56.1 cm high, 28.5 cm wide, and 56.9 cm deep. Other embodiments may weigh more or less or have different external dimensions, depending on their application.” It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Lu’s refrigerator characteristics with Lee’s refrigerator manuals in order to communicate relevant data as suggested by Lee (see ¶ 0049).
Lee also discloses:
wherein accessing the set of sensor data captured via the set of sensors coupled to the refrigeration unit comprises accessing the set of sensor data captured via the set of sensors coupled to the refrigeration unit defining the set of characteristics comprising a third size and a third configuration for the set of refrigerator components. Lee, ¶ 0029, “For example, the text information may correspond to different items of equipment or versions of items of equipment to be serviced.” Also ¶ 0145, “For example, the language model can have its configuration (e.g., training, etc.) modified according to labels of identifiers or classes of technicians, sites, types of equipment, or other characteristics relating to the item of equipment and/or the service technician, which can enable the prescription to be generated in a manner that is more accurate and/or relevant to the service to be performed.”
Claim(s) 12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Lee, Davies and Travalini as applied above, and further in view of U.S. Patent Application Publication 20200356627 by Pablo et al. ("Pablo").
In regard to claim 12, Lee does not expressly disclose:
12. The method of claim 11, wherein generating the notification comprising the first textual descriptor, the first text string, the second text string, the third text string, and the prompt comprises: calculating a first confidence score for the first root cause based on proximity of the first textual descriptor to troubleshooting descriptions represented in the language model for the subset of analogous refrigeration system types in the first set of refrigeration system types; calculating a second confidence score for the second root cause based on proximity of the first textual descriptor to troubleshooting descriptions represented in the language model for the subset of analogous refrigeration system types in the first set of refrigeration system types; and However, this is taught by Pablo. See Pablo, ¶ 0014, “The process where finding the best match description is a two-step process with a screening step that screens the list of descriptions using the vector representation of the descriptions to get a list of candidate descriptions and a ranking step that further processes the list of candidate descriptions to find the best match description. … The process where finding the best match uses word mover distance. The process where finding the best match is a probabilistic best match.” Note that Travalini specifically teaches confidence values (see ¶ 0080). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use best match ranking and confidence scoring of Pablo and Travalini with Lee’s cause determination in order to provide a “best” output as suggested by Pablo.
in response to the first confidence score exceeding the second confidence score: populating the notification with the first text string and the first confidence score in a first slot; and populating the notification with the second text string and the second confidence score in a second slot succeeding the first slot. See Pablo, ¶ 0014, “ranking.” It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Pablo’s ranking with Lee’s text strings (i.e. Fig. 12 and ¶ 0181 as cited above) ion order to find a probabilistic best match as suggested by Pablo (see ¶ 0014).
Claim(s) 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over Lee and Davies as applied above, and further in view of U.S. Patent Application Publication 20210390194 by Kawai et al. ("Kawai").
In regard to claim 13, Lee does not expressly disclose:
13. The method of claim 1: further comprising: predicting a confidence score for the first root cause; and in response to the confidence score falling below a first threshold score and exceeding a second threshold score, generating … [results]. However, this is taught by Kawai. See Kawai, Fig. 7 and ¶ 0056, “The result determination unit 146 generates a determination result 170.” Also ¶ 0088, “Typically, the determination condition 156 includes a threshold range which is set for the score 154 and indicates that there is a high possibility that any abnormality has occurred in the monitoring target.” It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Kawai’s threshold range with Lee’s in order to trigger supplemental abnormality determination as suggested by Kawai (see ¶ 0088).
Lee also teaches:
generating a second text string describing a sequence of diagnostic steps for investigating occurrence of the first root cause at the refrigeration unit; and wherein generating the notification comprising the first textual descriptor and the first text string comprises generating the notification comprising the first textual descriptor, the first text string, the second text string, the third text string, and a prompt to execute the sequence of diagnostic steps. Lee, ¶ 0077, “For example, the virtual assistant application 120 can provide one or more requests for users such as service technicians, facility managers, or other occupants, and provide the received responses to at least one of the second model 116 or a root cause detection function (e.g., algorithm, model, data structure mapping inputs to candidate causes, etc.) to determine a prediction of a cause of the issue of the item of equipment and/or solutions.”
Claim(s) 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Lee in view of Davies as applied above, and further in view of Ma.
In regard to claim 17, Lee discloses:
17. The method of claim 14:
wherein generating the second text string describing the first set of replacement parts based on proximity of the first textual descriptor to corrective action descriptions represented in the language model for the subset of analogous refrigeration units comprises generating the second text string describing the first set of replacement parts based on proximity of the first textual descriptor to a first corrective action description represented in the language model for a first refrigeration unit in the subset of analogous refrigeration units; Lee ¶ 0053, 0068, 0073, and 0143 as cited above.
Lee does not expressly disclose: further comprising generating a third text string describing a second set of replacement parts for correcting the first anomalous behavior at the refrigeration unit based on proximity of the first textual descriptor to a second corrective action description represented in the language model for a second refrigeration unit in the subset of analogous refrigeration units; and However, this is taught by Ma. See Ma, ¶ 0046, “Alternatively, if the response does not satisfy the user's question, as determined by the chatbot by continued queries from the user, the chatbot may continue attempting to match the query to data from a VAE model of the VSDG and send further responses to the user interface 200.” It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use Ma’s second response with Lee’s text generation in order to produce an acceptable/appropriate response as suggested by Ma.
Lee also teaches:
wherein generating the notification comprises generating the notification comprising the first textual descriptor, the first text string, the second text string, and the third text string. See Lee Fig. 8, element 820. Also ¶ 0032, 0075, and 0149 as cited above. Also see Ma, Fig. 2 and related text.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
U.S. Patent Application Publication 20230349608 by Tiernan et al. teaches refrigeration system anomaly detection (see abstract).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to James D Rutten whose telephone number is (571)272-3703. The examiner can normally be reached M-F 9:00-5:30 ET.
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, Li B Zhen can be reached at (571)272-3768. 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.
/James D. Rutten/Primary Examiner, Art Unit 2121