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 .
Response to Amendments / Arguments
Regarding the rejection(s) of claims under 35 USC 103:
The applicant's arguments filed 02/20/2026, have been fully considered and are not persuasive.
Applicant argues that Li and Bene do not teach "classify a predetermined history included in the behavior history into any of a plurality of groups, based on specification from the first user," "set classification into a predetermined group, of the plurality of groups, as the predetermined extraction condition," and "determine a first extract condition for classification into the predetermined group based on the first settlement history."
In response, Li [0081]-[0083] recites that the apparatus "classifies customers into a plurality of customer clusters by clustering the customers based on customer feature vectors" derived from individual purchase histories. Li [0142] further recites that "the customer item recommending apparatus obtains a user input designating an item category from a target customer and determines the item category based on the user input." This user-directed category input teaches the claimed "based on specification from the first user," as the user's input directly drives classification. Furthermore, once customers are classified into clusters, Li [0083]-[0085] and [0143] demonstrate that those cluster classifications directly drive downstream item retrieval operations, which teaches "setting classification into a predetermined group as a predetermined extraction condition".
Applicant further argues that claim 36's companion identification limitation has no analog in Li as Li's clustering relies solely on individual customer features. In response, Li [0057] discloses cameras covering the physical store FOV and Li [0119] discloses that classification is based on "purchase action information" including "traces of the customer in a physical store... a conversation, and an interaction with an item." The capture of customer interaction information from shared physical environments where multiple individuals are necessarily present encompasses companion related information co-present in the captured image with the first user.
Therefore, the identified claim language is considered to be taught by the combined references, and the rejection is maintained. Further, since Applicant has not presented additional arguments concerning the dependent claims, their rejections are likewise maintained.
DETAILED ACTION
This is a reply to the arguments filed on 02/20/2026, in which, claims 19-24 and 26-36 are pending. Claims 1-18 and 25 are cancelled.
When making claim amendments, the applicant is encouraged to consider the references in their entireties, including those portions that have not been cited by the examiner and their equivalents as they may most broadly and appropriately apply to any particular anticipated claim amendments.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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 19-24 and 26-36 are rejected under 35 U.S.C. 103 as being unpatentable over Li et al. (US 20190205965 A1, referred to as Li), in view of Bene (US 20200019974 A1, referred to as Bene).
In reference to claim 19, A recommendation control device comprising: at least one memory acquiring storing instructions; and at least one processor configured to execute the instructions to (Li: [0184]-[0196] Provides for a recommendation apparatus with memory storing instructions and a processor executing those instructions.) Acquire a captured image of a first user from a photographing device (Li: [0052]-[0058] Provides for acquiring a captured image of a customer using cameras.)
Extract a face feature information from the captured image (Li: [0063]-[0074] Provides for extracting feature vectors from a face image for identification purposes.)
Cause an authentication device to perform face authentication by using the face feature information and In a case where the first user successes in the face authentication: the at least one processor is configured to execute the instructions to (Li: [0063] Provides for using face recognition for identification then a recommendation process once the face recognition is verified.)
Classify a predetermined history included in the behavior history into any of a plurality groups, based on specification from the first user (Li: [0081]-[0083] and [0119]-[0120] Provides for classifying customer purchase histories into different groups/clusters based on customer feature vectors derived from individual purchase histories and image analysis. Li [0142] Provides where user directed category input constitutes specification from the first user driving the classification into groups.)
Set classification into a predetermined group, of the plurality of groups, as a predetermined extraction condition (Li: [0083]-[0085] and [0143] Provides for using cluster classification as the operative basis for downstream item retrieval operations, where the cluster classification directly drives and gates subsequent extraction of relevant items, teaching the setting of classification into a predetermined group as a predetermined extraction condition.)
Extract a first behavior history that satisfies a first extraction condition from a behavior history of the first user (Li: [0117]-[0120] Provides for extracting customer behavior information (including store movement patterns, interactions with items, etc.) and using this along with purchase history to classify customers.)
Identify recommendation information based on the extracted behavior history (Li: [0054] and [0074]-[0077] Provides for identifying recommendation information based on the customer's purchase tendencies and behaviors.)
Transmit the recommendation information to a display terminal owned by the first user (Li: [0154]-[0165] Provides for transmitting recommendation information to a display terminal owned by the user.)
Li does not explicitly disclose extracting a first settlement history in which the first user performs settlement for a predetermined number of times in a predetermined period from a settlement history being registered by an instruction of the first user during settlement and determining a first extract condition based on the first settlement history. However, Bene teaches: Extract a first settlement history in which the first user performs settlement for a predetermined number of times in a predetermined period from a settlement history being registered by an instruction of the first user during settlement (Bene: [0038]-[0039] and [0052] Provides for extracting transaction (settlement) history for users, storing it in a database, and analyzing it over predetermined time periods.)
Determine a first extract condition or classification into the predetermined group based on the first settlement history (Bene: [0060]-[0065] Provides for determining extraction conditions based on settlement history. It analyzes transaction data to determine variances and thresholds that will be used for further extraction and analysis.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Li, which provides a recommendation control device that uses face authentication, behavior history analysis, and recommendation transmission based on user behaviors and purchase tendencies, with the teachings of Bene, which introduces extraction and analysis of settlement transaction history over predetermined periods to determine extraction conditions for further analysis. One of ordinary skill in the art would recognize the ability to incorporate Bene's settlement history analysis into Li's recommendation system to enhance the accuracy and relevance of personalized recommendations. One of ordinary skill in the art would be motivated to make this modification in order to improve recommendation quality by considering actual purchase patterns and transaction frequencies rather than relying solely on browsing behaviors.
In reference to claim 20, The recommendation control device according to claim 1, wherein the at least one memory is configured to store behavior histories of a plurality of users (Li: [0065]-[0067] and [0117]-[0120] Provides for storing customer records including purchase actions and behavior information for multiple customers
and the at least one processor is further configured to execute the instructions to: register a user ID and a behavior history in association with each other in the at least one memory, acquire, from the at least one memory, a behavior history associated with a user ID of a user successful in the face authentication, and extracts a behavior history that satisfies a predetermined extraction condition from the acquired behavior history (Li: [0060]-[0070] and [0117]-[0120] Provides for registering customer IDs in association with their behavior histories (purchase records, browsing records, in-store movements), retrieving this information after identifying the customer through face recognition, and extracting relevant behavior patterns that satisfy certain conditions for classification purposes.)
In reference to claim 21, The recommendation control device according to claim 1, wherein the behavior history includes a plurality of settlement histories of the user, the predetermined extraction condition includes a specific settlement history, and the at least one processor is further configured to execute the instructions to: extract the specific settlement history from among the plurality of settlement histories (Bene: [0027], [0058-0059] and [0075-0076]] Provides for extracting and analyzing transaction (settlement) history based on specific time periods and even specific months (time zones).)
In reference to claim 22, The recommendation control device according to claim 3, wherein the predetermined extraction condition further includes a predetermined time zone in which settlement is performed, and the at least one processor is further configured to execute the instructions to: extract a settlement history in which the user performs settlement in the predetermined time zone from among the plurality of settlement histories (Bene: [0027], [0058-0059] and [0075-0076] Provides for extracting and analyzing transaction (settlement) history based on specific time periods and even specific months (time zones).)
In reference to claim 23, The recommendation control device according to claim 3, wherein the predetermined extraction condition further includes a predetermined time zone in which settlement is performed, and the at least one processor is further configured to execute the instructions to: extract a settlement history in which the user performs settlement in the predetermined time zone from among the plurality of settlement histories (Bene: [0027] and [0075-0076] Provides for extracting and analyzing transaction data based on when transactions occurred during specific time periods.)
In reference to claim 24, The recommendation control device according to claim 1, wherein, when the at least one processor receives specification for excluding a specific behavior history from the user, the at least one processor is further configured to execute the instructions to adds a condition for excluding the specified specific behavior history to the predetermined extraction condition (Bene: [0055], [0059] and [0067-0068] Provides for analyzing spending patterns and comparing actual spending to anticipated spending to identify variances.)
In reference to claim 26, The recommendation control device according to claim 1, wherein the behavior history includes at least one of a settlement history, an enter/exit history, and a participation history of the user (Bene: [0026]-[0028] and [0035]-[0040] Provides for using settlement history (transaction data) as the primary form of behavior history analyzed by the system.)
In reference to claim 27, A recommendation control system comprising (Li: [0184]-[0196] Provides for a recommendation apparatus with memory storing instructions and a processor executing those instructions.) A predetermined photographing device configured to capture an image including a face area of a user a recommendation control device configured to be communicable with the predetermined photographing device; and an authentication device configured to store face feature information about the user, and be communicable with the recommendation control device, wherein the recommendation control device includes acquisition means for acquiring a captured image being captured by a predetermined photographing device (Li: [0052]-[0058] Provides for acquiring a captured image of a customer using cameras.)
Extract a face feature information from the captured image (Li: [0063]-[0074] Provides for extracting feature vectors from a face image for identification purposes.)
Cause an authentication device to perform face authentication by using the face feature information and In a case where the first user successes in the face authentication: the at least one processor is configured to execute the instructions to (Li: [0063] Provides for using face recognition for identification then a recommendation process once the face recognition is verified.)
Classify a predetermined history included in the behavior history into any of a plurality groups, based on specification from the first user (Li: [0081]-[0083] and [0119]-[0120] Provides for classifying customer purchase histories into different groups/clusters based on customer feature vectors derived from individual purchase histories and image analysis. Li [0142] Provides where user directed category input constitutes specification from the first user driving the classification into groups.)
Set classification into a predetermined group, of the plurality of groups, as a predetermined extraction condition (Li: [0083]-[0085] and [0143] Provides for using cluster classification as the operative basis for downstream item retrieval operations, where the cluster classification directly drives and gates subsequent extraction of relevant items, teaching the setting of classification into a predetermined group as a predetermined extraction condition.)
Extract a first behavior history that satisfies a first extraction condition from a behavior history of the first user (Li: [0117]-[0120] Provides for extracting customer behavior information (including store movement patterns, interactions with items, etc.) and using this along with purchase history to classify customers.)
Identify recommendation information based on the extracted behavior history (Li: [0054] and [0074]-[0077] Provides for identifying recommendation information based on the customer's purchase tendencies and behaviors.)
Transmit the recommendation information to a display terminal owned by the first user (Li: [0154]-[0165] Provides for transmitting recommendation information to a display terminal owned by the user.)
Li does not explicitly disclose extracting a first settlement history in which the first user performs settlement for a predetermined number of times in a predetermined period from a settlement history being registered by an instruction of the first user during settlement and determining a first extract condition based on the first settlement history. However, Bene teaches: Extract a first settlement history in which the first user performs settlement for a predetermined number of times in a predetermined period from a settlement history being registered by an instruction of the first user during settlement (Bene: [0038]-[0039] and [0052] Provides for extracting transaction (settlement) history for users, storing it in a database, and analyzing it over predetermined time periods.)
Determine a first extract condition or classification into the predetermined group based on the first settlement history (Bene: [0060]-[0065] Provides for determining extraction conditions based on settlement history. It analyzes transaction data to determine variances and thresholds that will be used for further extraction and analysis.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Li, which provides a recommendation control device that uses face authentication, behavior history analysis, and recommendation transmission based on user behaviors and purchase tendencies, with the teachings of Bene, which introduces extraction and analysis of settlement transaction history over predetermined periods to determine extraction conditions for further analysis. One of ordinary skill in the art would recognize the ability to incorporate Bene's settlement history analysis into Li's recommendation system to enhance the accuracy and relevance of personalized recommendations. One of ordinary skill in the art would be motivated to make this modification in order to improve recommendation quality by considering actual purchase patterns and transaction frequencies rather than relying solely on browsing behaviors.
In reference to claim 28, The recommendation control device according to claim 27, wherein the at least one memory is configured to store behavior histories of a plurality of users; and the at least one processor is further configured to execute the instructions to: resister a user ID and a behavior history in association with each other in the at least one memory, acquire, from the at least one memory, a behavior history associated with a user ID of a user successful in the face authentication, and extracts a behavior history that satisfies a predetermined extraction condition from the acquired behavior history (Li: [0060]-[0070] and [0117]-[0120] Provides for registering customer IDs in association with their behavior histories (purchase records, browsing records, in-store movements), retrieving this information after identifying the customer through face recognition, and extracting relevant behavior patterns that satisfy certain conditions for classification purposes.)
In reference to claim 29, A recommendation control method comprising, by a computer:
(Li: [0184]-[0196] Provides for a recommendation apparatus with memory storing instructions and a processor executing those instructions.) A step of acquiring a captured image of a first user from a photographing device (Li: [0052]-[0058] Provides for acquiring a captured image of a customer using cameras.)
A step of extracting a face feature information from the captured image (Li: [0063]-[0074] Provides for extracting feature vectors from a face image for identification purposes.)
A step of causing an authentication device to perform face authentication by using the face feature information and In a case where the first user successes in the face authentication: the at least one processor is configured to execute the instructions to (Li: [0063] Provides for using face recognition for identification then a recommendation process once the face recognition is verified.)
A step of classifying a predetermined history included in the behavior history into any of a plurality groups, based on specification from the first user (Li: [0081]-[0083] and [0119]-[0120] Provides for classifying customer purchase histories into different groups/clusters based on customer feature vectors derived from individual purchase histories and image analysis. Li [0142] Provides where user directed category input constitutes specification from the first user driving the classification into groups.)
A step of setting classification into a predetermined group, of the plurality of groups, as a predetermined extraction condition (Li: [0083]-[0085] and [0143] Provides for using cluster classification as the operative basis for downstream item retrieval operations, where the cluster classification directly drives and gates subsequent extraction of relevant items, teaching the setting of classification into a predetermined group as a predetermined extraction condition.)
A step of extracting a first behavior history that satisfies a first extraction condition from a behavior history of the first user (Li: [0117]-[0120] Provides for extracting customer behavior information (including store movement patterns, interactions with items, etc.) and using this along with purchase history to classify customers.)
A step of identifying recommendation information based on the extracted behavior history (Li: [0054] and [0074]-[0077] Provides for identifying recommendation information based on the customer's purchase tendencies and behaviors.)
A step of transmitting the recommendation information to a display terminal owned by the first user (Li: [0154]-[0165] Provides for transmitting recommendation information to a display terminal owned by the user.)
Li does not explicitly disclose extracting a first settlement history in which the first user performs settlement for a predetermined number of times in a predetermined period from a settlement history being registered by an instruction of the first user during settlement and determining a first extract condition based on the first settlement history. However, Bene teaches: A step of extracting a first settlement history in which the first user performs settlement for a predetermined number of times in a predetermined period from a settlement history being registered by an instruction of the first user during settlement (Bene: [0038]-[0039] and [0052] Provides for extracting transaction (settlement) history for users, storing it in a database, and analyzing it over predetermined time periods.)
A step of determining a first extract condition or classification into the predetermined group based on the first settlement history (Bene: [0060]-[0065] Provides for determining extraction conditions based on settlement history. It analyzes transaction data to determine variances and thresholds that will be used for further extraction and analysis.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Li, which provides a recommendation control device that uses face authentication, behavior history analysis, and recommendation transmission based on user behaviors and purchase tendencies, with the teachings of Bene, which introduces extraction and analysis of settlement transaction history over predetermined periods to determine extraction conditions for further analysis. One of ordinary skill in the art would recognize the ability to incorporate Bene's settlement history analysis into Li's recommendation system to enhance the accuracy and relevance of personalized recommendations. One of ordinary skill in the art would be motivated to make this modification in order to improve recommendation quality by considering actual purchase patterns and transaction frequencies rather than relying solely on browsing behaviors.
In reference to claim 30, A non-transitory computer-readable medium configured to store a recommendation control program causing a computer to execute:
(Li: [0184]-[0196] Provides for a recommendation apparatus with memory storing instructions and a processor executing those instructions.) a step of acquiring a captured image being captured by a predetermined photographing device (Li: [0052]-[0058] Provides for acquiring a captured image of a customer using cameras.)
Authentication control means for extracting a face area or face feature information from the captured image (Li: [0063]-[0074] Provides for extracting feature vectors from a face image for identification purposes.)
causing an authentication device to perform face authentication (Li: [0063] Provides for using face recognition for identification then a recommendation process once the face recognition is verified.)
A step of classifying a predetermined history included in the behavior history into any of a plurality groups, based on specification from the first user (Li: [0081]-[0083] and [0119]-[0120] Provides for classifying customer purchase histories into different groups/clusters based on customer feature vectors derived from individual purchase histories and image analysis. Li [0142] Provides where user directed category input constitutes specification from the first user driving the classification into groups.)
A step of setting classification into a predetermined group, of the plurality of groups, as a predetermined extraction condition (Li: [0083]-[0085] and [0143] Provides for using cluster classification as the operative basis for downstream item retrieval operations, where the cluster classification directly drives and gates subsequent extraction of relevant items, teachingthe setting of classification into a predetermined group as a predetermined extraction condition.)
a step of extracting a behavior history that satisfies a predetermined extraction condition from a behavior history of a user successful in the face authentication (Li: [0117]-[0120] Provides for extracting customer behavior information (including store movement patterns, interactions with items, etc.) and using this along with purchase history to classify customers.)
a step of identifying recommendation information, based on the extracted behavior history (Li: [0054] and [0074]-[0077] Provides for identifying recommendation information based on the customer's purchase tendencies and behaviors.)
a step of transmitting the identified recommendation information to a predetermined display terminal (Li: [0154]-[0165] Provides for transmitting recommendation information to a display terminal owned by the user.)
Li does not explicitly disclose extracting a first settlement history in which the first user performs settlement for a predetermined number of times in a predetermined period from a settlement history being registered by an instruction of the first user during settlement and determining a first extract condition based on the first settlement history. However, Bene teaches: A step of extracting a first settlement history in which the first user performs settlement for a predetermined number of times in a predetermined period from a settlement history being registered by an instruction of the first user during settlement (Bene: [0038]-[0039] and [0052] Provides for extracting transaction (settlement) history for users, storing it in a database, and analyzing it over predetermined time periods.)
A step of determining a first extract condition or classification into the predetermined group based on the first settlement history (Bene: [0060]-[0065] Provides for determining extraction conditions based on settlement history. It analyzes transaction data to determine variances and thresholds that will be used for further extraction and analysis.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Li, which provides a recommendation control device that uses face authentication, behavior history analysis, and recommendation transmission based on user behaviors and purchase tendencies, with the teachings of Bene, which introduces extraction and analysis of settlement transaction history over predetermined periods to determine extraction conditions for further analysis. One of ordinary skill in the art would recognize the ability to incorporate Bene's settlement history analysis into Li's recommendation system to enhance the accuracy and relevance of personalized recommendations. One of ordinary skill in the art would be motivated to make this modification in order to improve recommendation quality by considering actual purchase patterns and transaction frequencies rather than relying solely on browsing behaviors.
In reference to claim 31, A recommendation control device comprising: (Li: [0184]-[0196] Provides for a recommendation apparatus with memory storing instructions and a processor executing those instructions.) Acquire a captured image being captured by a predetermined photographing device (Li: [0052]-[0058] Provides for acquiring a captured image of a customer using cameras.)
Extracting a face area or face feature information from the captured image (Li: [0063]-[0074] Provides for extracting feature vectors from a face image for identification purposes.)
perform face authentication, based on the face area or the face feature information (Li: [0063] Provides for using face recognition for identification then a recommendation process once the face recognition is verified.)
Classify a predetermined history included in the behavior history into any of a plurality groups, based on specification from the first user (Li: [0081]-[0083] and [0119]-[0120] Provides for classifying customer purchase histories into different groups/clusters based on customer feature vectors derived from individual purchase histories and image analysis. Li [0142] Provides where user directed category input constitutes specification from the first user driving the classification into groups.)
Set classification into a predetermined group, of the plurality of groups, as a predetermined extraction condition (Li: [0083]-[0085] and [0143] Provides for using cluster classification as the operative basis for downstream item retrieval operations, where the cluster classification directly drives and gates subsequent extraction of relevant items, teachingthe setting of classification into a predetermined group as a predetermined extraction condition.)
extract a behavior history that satisfies a predetermined extraction condition from a behavior history of a user successful in the face authentication (Li: [0117]-[0120] Provides for extracting customer behavior information (including store movement patterns, interactions with items, etc.) and using this along with purchase history to classify customers.)
identify recommendation information, based on the extracted behavior history (Li: [0054] and [0074]-[0077] Provides for identifying recommendation information based on the customer's purchase tendencies and behaviors.)
transmit the identified recommendation information to a predetermined display terminal (Li: [0154]-[0165] Provides for transmitting recommendation information to a display terminal owned by the user.)
Li does not explicitly disclose extracting a first settlement history in which the first user performs settlement for a predetermined number of times in a predetermined period from a settlement history being registered by an instruction of the first user during settlement and determining a first extract condition based on the first settlement history. However, Bene teaches: Extract a first settlement history in which the first user performs settlement for a predetermined number of times in a predetermined period from a settlement history being registered by an instruction of the first user during settlement (Bene: [0038]-[0039] and [0052] Provides for extracting transaction (settlement) history for users, storing it in a database, and analyzing it over predetermined time periods.)
Determine a first extract condition or classification into the predetermined group based on the first settlement history (Bene: [0060]-[0065] Provides for determining extraction conditions based on settlement history. It analyzes transaction data to determine variances and thresholds that will be used for further extraction and analysis.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Li, which provides a recommendation control device that uses face authentication, behavior history analysis, and recommendation transmission based on user behaviors and purchase tendencies, with the teachings of Bene, which introduces extraction and analysis of settlement transaction history over predetermined periods to determine extraction conditions for further analysis. One of ordinary skill in the art would recognize the ability to incorporate Bene's settlement history analysis into Li's recommendation system to enhance the accuracy and relevance of personalized recommendations. One of ordinary skill in the art would be motivated to make this modification in order to improve recommendation quality by considering actual purchase patterns and transaction frequencies rather than relying solely on browsing behaviors.
In reference to claim 32, The recommendation control device according to claim 31, wherein the at least one memory is configured to store behavior histories of a plurality of users; and the at least one processor is further configured to execute the instructions to: resister a user ID and a behavior history in association with each other in the at least one memory, acquire, from the at least one memory, a behavior history associated with a user ID of a user successful in the face authentication, and extracts a behavior history that satisfies a predetermined extraction condition from the acquired behavior history (Li: [0060]-[0070] and [0117]-[0120] Provides for registering customer IDs in association with their behavior histories (purchase records, browsing records, in-store movements), retrieving this information after identifying the customer through face recognition, and extracting relevant behavior patterns that satisfy certain conditions for classification purposes.)
In reference to claim 33, A recommendation control method comprising, by a computer:
(Li: [0184]-[0196] Provides for a recommendation apparatus with memory storing instructions and a processor executing those instructions.) a step of acquiring a captured image being captured by a predetermined photographing device (Li: [0052]-[0058] Provides for acquiring a captured image of a customer using cameras.)
Authentication control means for extracting a face area or face feature information from the captured image (Li: [0063]-[0074] Provides for extracting feature vectors from a face image for identification purposes.)
causing an authentication device to perform face authentication (Li: [0063] Provides for using face recognition for identification then a recommendation process once the face recognition is verified.)
A step of classifying a predetermined history included in the behavior history into any of a plurality groups, based on specification from the first user (Li: [0081]-[0083] and [0119]-[0120] Provides for classifying customer purchase histories into different groups/clusters based on customer feature vectors derived from individual purchase histories and image analysis. Li [0142] Provides where user directed category input constitutes specification from the first user driving the classification into groups.)
A step of setting classification into a predetermined group, of the plurality of groups, as a predetermined extraction condition (Li: [0083]-[0085] and [0143] Provides for using cluster classification as the operative basis for downstream item retrieval operations, where the cluster classification directly drives and gates subsequent extraction of relevant items, teaching the setting of classification into a predetermined group as a predetermined extraction condition.)
a step of extracting a behavior history that satisfies a predetermined extraction condition from a behavior history of a user successful in the face authentication (Li: [0117]-[0120] Provides for extracting customer behavior information (including store movement patterns, interactions with items, etc.) and using this along with purchase history to classify customers.)
a step of identifying recommendation information, based on the extracted behavior history (Li: [0054] and [0074]-[0077] Provides for identifying recommendation information based on the customer's purchase tendencies and behaviors.)
a step of transmitting the identified recommendation information to a predetermined display terminal (Li: [0154]-[0165] Provides for transmitting recommendation information to a display terminal owned by the user.)
Li does not explicitly disclose extracting a first settlement history in which the first user performs settlement for a predetermined number of times in a predetermined period from a settlement history being registered by an instruction of the first user during settlement and determining a first extract condition based on the first settlement history. However, Bene teaches: A step of extracting a first settlement history in which the first user performs settlement for a predetermined number of times in a predetermined period from a settlement history being registered by an instruction of the first user during settlement (Bene: [0038]-[0039] and [0052] Provides for extracting transaction (settlement) history for users, storing it in a database, and analyzing it over predetermined time periods.)
A step of determining a first extract condition or classification into the predetermined group based on the first settlement history (Bene: [0060]-[0065] Provides for determining extraction conditions based on settlement history. It analyzes transaction data to determine variances and thresholds that will be used for further extraction and analysis.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Li, which provides a recommendation control device that uses face authentication, behavior history analysis, and recommendation transmission based on user behaviors and purchase tendencies, with the teachings of Bene, which introduces extraction and analysis of settlement transaction history over predetermined periods to determine extraction conditions for further analysis. One of ordinary skill in the art would recognize the ability to incorporate Bene's settlement history analysis into Li's recommendation system to enhance the accuracy and relevance of personalized recommendations. One of ordinary skill in the art would be motivated to make this modification in order to improve recommendation quality by considering actual purchase patterns and transaction frequencies rather than relying solely on browsing behaviors.
In reference to claim 34, A non-transitory computer-readable medium configured to store a recommendation control program causing a computer to execute:
(Li: [0184]-[0196] Provides for a recommendation apparatus with memory storing instructions and a processor executing those instructions.) a step of acquiring a captured image being captured by a predetermined photographing device (Li: [0052]-[0058] Provides for acquiring a captured image of a customer using cameras.)
Authentication control means for extracting a face area or face feature information from the captured image (Li: [0063]-[0074] Provides for extracting feature vectors from a face image for identification purposes.)
causing an authentication device to perform face authentication (Li: [0063] Provides for using face recognition for identification then a recommendation process once the face recognition is verified.)
A step of classifying a predetermined history included in the behavior history into any of a plurality groups, based on specification from the first user (Li: [0081]-[0083] and [0119]-[0120] Provides for classifying customer purchase histories into different groups/clusters based on customer feature vectors derived from individual purchase histories and image analysis. Li [0142] Provides where user directed category input constitutes specification from the first user driving the classification into groups.)
A step of setting classification into a predetermined group, of the plurality of groups, as a predetermined extraction condition (Li: [0083]-[0085] and [0143] Provides for using cluster classification as the operative basis for downstream item retrieval operations, where the cluster classification directly drives and gates subsequent extraction of relevant items, teachingthe setting of classification into a predetermined group as a predetermined extraction condition.)
a step of extracting a behavior history that satisfies a predetermined extraction condition from a behavior history of a user successful in the face authentication (Li: [0117]-[0120] Provides for extracting customer behavior information (including store movement patterns, interactions with items, etc.) and using this along with purchase history to classify customers.)
a step of identifying recommendation information, based on the extracted behavior history (Li: [0054] and [0074]-[0077] Provides for identifying recommendation information based on the customer's purchase tendencies and behaviors.)
a step of transmitting the identified recommendation information to a predetermined display terminal (Li: [0154]-[0165] Provides for transmitting recommendation information to a display terminal owned by the user.)
Li does not explicitly disclose extracting a first settlement history in which the first user performs settlement for a predetermined number of times in a predetermined period from a settlement history being registered by an instruction of the first user during settlement and determining a first extract condition based on the first settlement history. However, Bene teaches: A step of extracting a first settlement history in which the first user performs settlement for a predetermined number of times in a predetermined period from a settlement history being registered by an instruction of the first user during settlement (Bene: [0038]-[0039] and [0052] Provides for extracting transaction (settlement) history for users, storing it in a database, and analyzing it over predetermined time periods.)
A step of determining a first extract condition or classification into the predetermined group based on the first settlement history (Bene: [0060]-[0065] Provides for determining extraction conditions based on settlement history. It analyzes transaction data to determine variances and thresholds that will be used for further extraction and analysis.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Li, which provides a recommendation control device that uses face authentication, behavior history analysis, and recommendation transmission based on user behaviors and purchase tendencies, with the teachings of Bene, which introduces extraction and analysis of settlement transaction history over predetermined periods to determine extraction conditions for further analysis. One of ordinary skill in the art would recognize the ability to incorporate Bene's settlement history analysis into Li's recommendation system to enhance the accuracy and relevance of personalized recommendations. One of ordinary skill in the art would be motivated to make this modification in order to improve recommendation quality by considering actual purchase patterns and transaction frequencies rather than relying solely on browsing behaviors.
In reference to claim 35. The recommendation control device according to Claim 19, wherein the predetermined extraction condition is selected based on a date and time at which the face authentication is performed, information included in a captured image, And the at least one processor is further configured to acquire a result of face authentication using the face feature information extracted from the captured image (Li: [0063], [0074], [0118], [0163] Provides for using face recognition for customer identification and extracting feature information from facial images.)
In reference to claim 36, The recommendation control device according to claim 19, wherein the behavior history is classified into the plurality of groups based on information identifying one or more companions included in the captured image together with the first user (Li: [0057], [0119]-[0120] Provides for cameras covering the physical store field of view capturing customer interactions in a shared physical environment, where classification is based on purchase action information including traces, conversations, and interactions with items occurring in the shared space, encompassing information about individuals co-present in the captured image together with the first user.)
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. See PTO-892.
Applicant’s amendment necessitated the new ground(s) of rejection presented in this office action. Accordingly, 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 extension fee 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.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AIDAN EDWARD SHAUGHNESSY whose telephone number is (703)756-1423. The examiner can normally be reached on Monday-Friday from 7:30am to 5pm.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Jeffrey Nickerson, can be reached at telephone number (469) 295-9235. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from Patent Center and the Private Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from Patent Center or Private PAIR. Status information for unpublished applications is available through Patent Center and Private PAIR for authorized users only. Should you have questions about access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free).
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) Form at https://www.uspto.gov/patents/usptoautomated-interview-request-air-form.
/A.E.S./Examiner, Art Unit 2432
/Jeffrey Nickerson/Supervisory Patent Examiner, Art Unit 2432
Prosecution Insights