DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
The information disclosure statement (IDS) document submitted on May 17, 2023 is in compliance with the provisions of 37 CFR 1.97 and is being considered by the examiner.
Claim Objections
Claims 1, 9 and 10 are objected to because of the following informalities: “based on the user victor”
“There is misspelling in the word “victor”. It should read as “vector”.
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitation(s) is/are:
“a position data acquisition unit configured to…;
a feature acquisition unit configured to…;
a user vector generation unit configured to…;
a sequence vector generation unit configured to…,
a prediction unit configured to” as recited in claim 1.
“a training unit configured to” as recited in claim 6.
“a Provision unit configured to” as recited in claim 8.
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
Claim Rejections – 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claim 9 rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. The claim(s) does/do not fall within at least one of the four categories of patent eligible subject matter because the claim recites “An information processing apparatus comprising: …” making this claim a system claim, however, this system claim does not recite any hardware making this claim as being software per se. Appropriate correction is required.
Claims 1-10 are rejected under 35 U.S.C. 101 because the claimed invention is directed to abstract idea (mental process) without significantly more.
Claim 1:
Regarding claim 1, in step 1 of the 101-analysis set forth in MPEP 2106, the claim recites “An information processing apparatus comprising: a position data acquisition unit configured to acquire data on positions of a user accompanying movement of the user; a feature acquisition unit configured to acquire a user feature representing a feature of the user; a user vector generation unit configured to generate a user vector representing a feature of the movement of the user based on the position data and the user feature; a sequence vector generation unit configured to generate a sequence vector representing a sequence of locations visited by the user based on the position data; and a prediction unit configured to predict a next location that the user will visit based on the user victor and the sequence vector through machine learning.”
In step 2A prong 1 of the 101- analysis set forth in the MPEP 2106, the examiner has determined that the following limitations recite a process that, under the broadest reasonable interpretation, covers a mental process but for recitation of generic computer components:
“generate a user vector representing a feature of the movement of the user based on the position data and the user feature”, (mental process, a person can create a vector based on looking at a person for their user features as well as seeing where they are for position data, see MPEP 2106.04(a)(2)(III)),
“generate a sequence vector representing a sequence of locations visited by the user based on the position data”, (mental process, a person can generate a vector based off seeing a sequence of where a person has gone and track it themselves, see MPEP 2106.04(a)(2)(III)),
“predict a next location that the user will visit based on the user victor and the sequence vector”, (mental process, a person can predict the next location someone will be at based on their previous locations, see MPEP 2106.04(a)(2)(III)),
If claim limitations, under their broadest reasonable interpretation, covers performance of the
limitations as a mental process but for the recitation of generic computer components, then it falls within the mental process grouping of abstract ideas. Accordingly, the claim “recites” an abstract idea.
In step 2A prong 2 of the 101-analysis set forth in MPEP 2106, the examiner has determined that the following additional elements do not integrate this judicial exception into a practical application:
“acquire data on positions of a user accompanying movement of the user”, (This limitation is an insignificant extra solution activity of mere data gathering, see MPEP 2106.05(g))
“acquire a user feature representing a feature of the user”, (This limitation is an insignificant extra solution activity of mere data gathering, see MPEP 2106.05(g))
“a position data acquisition unit, feature acquisition unit, user vector generation unit, sequence vector generation unit and prediction unit”, (mere instructions to apply the judicial exception using generic computer components, MPEP 2106.05(f)).
“predict … through machine learning.”, (mere instructions to apply the judicial exception using generic computer components, MPEP 2106.05(f)).
Since the claim as a whole, looking at the additional elements individually and in combination, does not contain any other additional elements that are indicative of integration into a practical application, the claim is “directed” to an abstract idea.
In step 2B of the 101-analysis set forth in the 2019 PEG, the examiner has determined that the claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
For elements iv and v, this insignificant extra solution activity is well understood routine and conventional activity. See Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362. As discussed above, addition elements vi and vii is mere instructions to apply the judicial exception using generic computer components, which are not indicative of significantly more.
Considering the additional elements individually and in combination, and the claim as a whole, the additional elements do not provide significantly more than the abstract idea. Therefore, the claim is not patent eligible.
Claim 2:
Regarding claim 2, it is dependent upon claim 1, and thereby incorporates the limitations of, and corresponding analysis applied to claim 1. Further, claim 2 recites the following additional elements:
“generates a region-of-interest vector that represents a geographical feature of a pattern of the movement of the user, and a location-of-interest vector that represents a feature of a location of interest for the user through the locations that the user has moved to, and generates the user vector by combining the region- of-interest vector and the location-of-interest vector.”, (In step 2A, Prong 1, a mental process, the person can generate the region-of-interest vector and a location-of-interest vector and then generate the user vector by combining these two vectors, see MPEP 2106.04(a)(2)(III)) .
“the user vector generation unit”, (Under Step 2A prong II and step 2B, mere instructions to apply the judicial exception using generic computer components, MEP 2106.05(f)).
Since the claim recites a limitation that can practically be performed in the human mind, with or without the use of a physical aid such as pen and paper, the limitation falls within the mental processes grouping, and the claim recites an abstract idea. Since the claim does not recite additional elements that either integrate the judicial exception into a practical application, nor provide significantly more than the judicial exception, the claim is not patent eligible.
Claim 3:
Regarding claim 3, it is dependent upon claim 1, and thereby incorporates the limitations of, and corresponding analysis applied to claim 1. Further, claim 3 recites the following additional elements:
“generates a region-of-interest vector that represents a geographical feature of a pattern of the movement of the user, a location- of-interest vector that represents a feature of a location of interest for the user through the movement of the user, and a transportation vector representing a feature of a transportation used by the user through the movement of the user, and generates the user vector by combining the region-of-interest vector, the location-of-interest vector, and the transportation vector.”, (In step 2A, Prong 1, a mental process, the person can generate the region-of-interest vector, a location-of-interest vector and a transportation vector and then generate the user vector by combining these three vectors, see MPEP 2106.04(a)(2)(III)) .
“the user vector generation unit”, (Under Step 2A prong II and step 2B, mere instructions to apply the judicial exception using generic computer components, MEP 2106.05(f)).
Since the claim recites a limitation that can practically be performed in the human mind, with or without the use of a physical aid such as pen and paper, the limitation falls within the mental processes grouping, and the claim recites an abstract idea. Since the claim does not recite additional elements that either integrate the judicial exception into a practical application, nor provide significantly more than the judicial exception, the claim is not patent eligible.
Claim 4:
Regarding claim 4, it is dependent upon claim 2, which is dependent upon claim 1, and thereby incorporates the limitations of, and corresponding analysis applied to claim 1 and claim 2. Further, claim 4 recites the following additional elements:
“uses the sequence of the locations visited by the user based on the position data and the user feature to generate the region-of-interest vector.”, (In step 2A, Prong 1, a mental process, a person can mentally see where a user has been and create a vector, see MPEP 2106.04(a)(2)(III)).
“the user vector generation unit”, (Under Step 2A prong II and step 2B, mere instructions to apply the judicial exception using generic computer components, MEP 2106.05(f)).
Since the claim recites a limitation that can practically be performed in the human mind, with or without the use of a physical aid such as pen and paper, the limitation falls within the mental processes grouping, and the claim recites an abstract idea. Since the claim does not recite additional elements that either integrate the judicial exception into a practical application, nor provide significantly more than the judicial exception, the claim is not patent eligible.
Claim 5:
Regarding claim 5, it is dependent upon claim 2, which is dependent upon claim 1, and thereby incorporates the limitations of, and corresponding analysis applied to claim 1 and claim 2. Further, claim 5 recites the following additional elements:
“uses names of the locations visited by the user based on the position data, land use types of the locations, and the user feature to generate the location-of- interest vector.”, (In step 2A, Prong 1, a mental process, a person can mentally see the names of where a user has been and create a vector, see MPEP 2106.04(a)(2)(III)).
“the user vector generation unit”, (Under Step 2A prong II and step 2B, mere instructions to apply the judicial exception using generic computer components, MEP 2106.05(f)).
Since the claim recites a limitation that can practically be performed in the human mind, with or without the use of a physical aid such as pen and paper, the limitation falls within the mental processes grouping, and the claim recites an abstract idea. Since the claim does not recite additional elements that either integrate the judicial exception into a practical application, nor provide significantly more than the judicial exception, the claim is not patent eligible.
Claim 6:
Regarding claim 6, it is dependent upon claim 1, and thereby incorporates the limitations of, and corresponding analysis applied to claim 1. Further, claim 6 recites the following additional elements:
“configured to train a learning model for the machine learning, the training unit uses the user vectors and the sequence vectors for a plurality of other users different from the user to train the learning model.”, (In step 2A, Prong 2 and Step 2B, additional element of mere instructions to apply the judicial exception using generic computer components, see MPEP 2106.04(a)(2)(III)).
“a training unit”, (In step 2A, Prong 2 and Step 2B, additional element of mere instructions to apply the judicial exception using generic computer components, see MPEP 2106.04(a)(2)(III)).
Since the claim recites a limitation that can practically be performed in the human mind, with or without the use of a physical aid such as pen and paper, the limitation falls within the mental processes grouping, and the claim recites an abstract idea. Since the claim does not recite additional elements that either integrate the judicial exception into a practical application, nor provide significantly more than the judicial exception, the claim is not patent eligible.
Claim 7:
Regarding claim 7, it is dependent upon claim 1, and thereby incorporates the limitations of, and corresponding analysis applied to claim 1. Further, claim 7 recites the following additional elements:
“wherein the user feature is a factual feature of the user”, (Under Step 2A prong II and step 2B, amounts to merely indicating a field of use or technological environment in which to apply a judicial exception, see MPEP 2106.05(h)).
Since the claim does not recite additional elements that either integrate the judicial exception into a practical application, nor provide significantly more than the judicial exception, the claim is not patent eligible.
Claim 8:
Regarding claim 8, it is dependent upon claim 1, and thereby incorporates the limitations of, and corresponding analysis applied to claim 1. Further, claim 8 recites the following additional elements:
“… provide to the user an advertisement relating to information of the location predicted by the prediction unit.”, (In step 2A, Prong 2, this recites mere data gathering, which is considered insignificant extra-solution activity, see MPEP 2106.05(g), In step 2B, this insignificant extra solution activity is well understood routine and conventional activities, see Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362, see MPEP 2106.05(d(2))),
“a provision unit configured to generate … an advertisement relating to information of the location predicted by the prediction unit.” (Under Step 2A prong II and step 2B, this is considered mere instructions to apply an exception using generic computer components, see MPEP 2106.05(f))
Since the claim does not recite additional elements that either integrate the judicial exception into a practical application, nor provide significantly more than the judicial exception, the claim is not patent eligible.
Claim 9:
Regarding claim 1, in step 1 of the 101-analysis set forth in MPEP 2106, the claim recites “An information processing apparatus comprising: acquiring data on positions of a user accompanying movement of the user; acquiring a user feature representing a feature of the user; generating a user vector representing a feature of the movement of the user based on the position data and the user feature; generating a sequence vector representing a sequence of locations visited by the user based on the position data; and predicting a next location that the user will visit based on the user victor and the sequence vector through machine learning.”
In step 2A prong 1 of the 101- analysis set forth in the MPEP 2106, the examiner has determined that the following limitations recite a process that, under the broadest reasonable interpretation, covers a mental process but for recitation of generic computer components:
“generating a user vector representing a feature of the movement of the user based on the position data and the user feature”, (mental process, a person can create a vector based on looking at a person for their user features as well as seeing where they are for position data, see MPEP 2106.04(a)(2)(III)),
“generating a sequence vector representing a sequence of locations visited by the user based on the position data”, (mental process, a person can generate a vector based off seeing a sequence of where a person has gone and track it themselves, see MPEP 2106.04(a)(2)(III)),
“predicting a next location that the user will visit based on the user victor and the sequence vector through machine learning”, (mental process, a person can predict the next location someone will be at based on their previous locations, see MPEP 2106.04(a)(2)(III)),
If claim limitations, under their broadest reasonable interpretation, covers performance of the
limitations as a mental process but for the recitation of generic computer components, then it falls within the mental process grouping of abstract ideas. Accordingly, the claim “recites” an abstract idea.
In step 2A prong 2 of the 101-analysis set forth in MPEP 2106, the examiner has determined that the following additional elements do not integrate this judicial exception into a practical application:
“acquiring data on positions of a user accompanying movement of the user”, (This limitation is an insignificant extra solution activity of mere data gathering, see MPEP 2106.05(g))
“acquiring a user feature representing a feature of the user”, (This limitation is an insignificant extra solution activity of mere data gathering, see MPEP 2106.05(g))
“predict … through machine learning.”, (mere instructions to apply the judicial exception using generic computer components, MPEP 2106.05(f)).
Since the claim as a whole, looking at the additional elements individually and in combination, does not contain any other additional elements that are indicative of integration into a practical application, the claim is “directed” to an abstract idea.
In step 2B of the 101-analysis set forth in the 2019 PEG, the examiner has determined that the claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
For elements iv and v, this insignificant extra solution activity is well understood routine and conventional activity. See Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362. As discussed above, addition element addition element vi is mere instructions to apply the judicial exception using generic computer components, which are not indicative of significantly more.
Considering the additional elements individually and in combination, and the claim as a whole, the additional elements do not provide significantly more than the abstract idea. Therefore, the claim is not patent eligible.
Claim 10:
Regarding claim 1, in step 1 of the 101-analysis set forth in MPEP 2106, the claim recites “ A non-transitory computer readable medium storing a computer program for causing a computer to execute processing comprising: position data acquisition processing for acquiring data on positions of a user accompanying movement of the user; feature acquisition processing for acquiring a user feature representing a feature of the user; user vector generating processing for generating a user vector representing a feature of the movement of the user based on the position data and the user feature; sequence vector generation processing for generating a sequence vector representing a sequence of locations visited by the user from the position data; and prediction processing for predicting a next location that the user will visit based on the user victor and the sequence vector through machine learning.”
In step 2A prong 1 of the 101- analysis set forth in the MPEP 2106, the examiner has determined that the following limitations recite a process that, under the broadest reasonable interpretation, covers a mental process but for recitation of generic computer components:
“user vector generating processing for generating a user vector representing a feature of the movement of the user based on the position data and the user feature”, (mental process, a person can create a vector based on looking at a person for their user features as well as seeing where they are for position data, see MPEP 2106.04(a)(2)(III)),
“sequence vector generation processing for generating a sequence vector representing a sequence of locations visited by the user from the position data”, (mental process, a person can generate a vector based off seeing a sequence of where a person has gone and track it themselves, see MPEP 2106.04(a)(2)(III)),
“prediction processing for predicting a next location that the user will visit based on the user victor and the sequence vector”, (mental process, a person can predict the next location someone will be at based on their previous locations, see MPEP 2106.04(a)(2)(III)),
If claim limitations, under their broadest reasonable interpretation, covers performance of the
limitations as a mental process but for the recitation of generic computer components, then it falls within the mental process grouping of abstract ideas. Accordingly, the claim “recites” an abstract idea.
In step 2A prong 2 of the 101-analysis set forth in MPEP 2106, the examiner has determined that the following additional elements do not integrate this judicial exception into a practical application:
“position data acquisition processing for acquiring data on positions of a user accompanying movement of the user”, (This limitation is an insignificant extra solution activity of mere data gathering, see MPEP 2106.05(g))
“feature acquisition processing for acquiring a user feature representing a feature of the user”, (This limitation is an insignificant extra solution activity of mere data gathering, see MPEP 2106.05(g))
“predict … through machine learning.”, (mere instructions to apply the judicial exception using generic computer components, MPEP 2106.05(f)).
“A non-transitory computer readable medium storing a computer program for causing a computer to execute processing”, (this is considered mere instructions to apply an exception using generic computer components, see MPEP 2106.05(f))
Since the claim as a whole, looking at the additional elements individually and in combination, does not contain any other additional elements that are indicative of integration into a practical application, the claim is “directed” to an abstract idea.
In step 2B of the 101-analysis set forth in the 2019 PEG, the examiner has determined that the claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
For elements iv and v, this insignificant extra solution activity is well understood routine and conventional activity. See Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362.
As discussed above, addition element addition element vi and vii are mere instructions to apply the judicial exception using generic computer components, which are not indicative of significantly more.
Considering the additional elements individually and in combination, and the claim as a whole, the additional elements do not provide significantly more than the abstract idea. Therefore, the claim is not patent eligible.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1, 2, 4, 5, 6, 7, 8, 9 and 10 are rejected under 35 U.S.C. 103 as being unpatentable over Grzywaczewski et al., “User Text Content Correlation with Location” (US PG Pub No 20170013408) published on January 12, 2017 further in view of YANG “Ranking nearby destinations based on visit likelihoods and predicting future visits to places from location” (U.S. Patent No 10332019) and further in view of Li et al. “VISITING POSITION PREDICTION METHOD BASED ON USER TRAVEL MODE” (AU Patent No 2021104609) published on September 23, 2021. (hereafter, Grzywaczewski, YANG and Li).
Claim 1:
Grzywaczewski teaches “An information processing apparatus comprising: a position data acquisition unit configured to acquire data on positions of a user accompanying movement of the user;”
See Grzywaczewski, [0014], “According a one aspect of the present invention there is provided a predictive modelling system for predicting location data from user textual data comprising: an input for receiving user data, the user data comprising user textual data and location data; a pre-processing module arranged to correlate user textual data with location data to form a set of correlated data; a training module arranged to use the set of correlated data to train a machine learning algorithm such that the algorithm is arranged to output predicted location data from an input textual query.” Grzywaczewski [0055] “As described below the present invention provides a mechanism for a predictive model to “learn” a user's particular vocabulary from their historical movements and textual content.”. Grzywaczewski talks about a system for predicting a future location based on the user textual and location data. User textual data fully correlates with user feature based on the applicant’s specifications by using things such as social media, emails, etc. The second quote describes a predictive model learning and acquiring data from the movements of the user and its textual context.
Grzywaczewski teaches “a feature acquisition unit configured to acquire a user feature representing a feature of the user.”
See Grzywaczewski [Abstract], “A predictive modelling system for predicting location data from user textual data comprising: an input for receiving user data, the user data comprising user textual data and location data;” Grzywaczewski talks about a system for predicting a future location based on the user textual and location data. User textual data fully correlates with user feature based on the applicant’s specifications by using things such as social media, emails, etc.
Grzywaczewski does not explicitly disclose “a user vector generation unit configured to generate a user vector representing a feature of the movement of the user based on the position data and the user feature; a sequence vector generation unit configured to generate a sequence vector representing a sequence of locations visited by the user based on the position data; and a prediction unit configured to predict a next location that the user will visit based on the user victor and the sequence vector through machine learning.”
However, YANG et al. teaches “a user vector generation unit configured to generate a user vector representing a feature of the movement of the user based on the position data and the user feature.”
See YANG et al., “A location-based service is an information or entertainment service, which is accessible on mobile devices through a mobile network and which uses information on the geographical position of the mobile device. First generation location-based services can include services to identify a location of a person or object, such as discovering the nearest banking cash machine or the whereabouts of a friend. Such services can also include mobile commerce, for example, by providing coupons or advertising directed at customers based on their current location. They could further include personalized weather services and even location-based games (Column 1 Lines 31-42). Having such information might allow users to “check in” using the name of the business that they are visiting when they choose to check in” (Column 1 Lines 50 - 54) and “when executed, cause at least one processor of a computing device to receive a location history associated with a user, and determine, based at least in part on the location history, a visit vector comprising a plurality of vector elements, each respective vector element corresponding to a respective past instance of a timeslot and having a value indicating that the user visited a place during the respective past instance of the timeslot or a value indicating that the user did not visit the place during the respective past instance of the timeslot” (Column 3 Lines 23 – 28). YANG teaches a location based service which uses information based on the position data of a person. This application allows users to “check in” to businesses using names as user features. This is then put into a visit vector that tracks the historical data of the user.
It would have been obvious to a person of ordinary skill in art before the effective filling date of the invention to implement the function of YANG into the method of Grzywaczewski to teach user vector generation based on a user feature. The modification would have been obvious because one of the ordinary skills of the art would be motivated to utilize the feature of YANG as all the references are in the field of machine learning and LLMs, making these references analogous. A person of ordinary skill of the art would have been motivated to perform the combination of being able to generate vectors based on user features and creating an application in which the user features can be obtained to help create systems and techniques that can determine whether a user is likely to visit a place during a future instance of a timeslot based at least in part on a location history associated with the user. (YANG [Abstract])
Grzywaczewski and Yang do not explicitly disclose “a sequence vector generation unit configured to generate a sequence vector representing a sequence of locations visited by the user based on the position data; a prediction unit configured to predict a next location that the user will visit based on the user victor and the sequence vector through machine learning.”
However, Li et al. teaches “a sequence vector generation unit configured to generate a sequence vector representing a sequence of locations visited by the user based on the position data;”
See Li et al., [Abstract], “the second stage is modeling of a user historical visiting behavior pattern based on geographical features; the third stage is prediction of a user visiting position based on a recurrent neural network model; and the visiting position vector and the user travel mode feature vector obtained by pretraining are integrated as the input of the recurrent neural network model so as to realize the prediction of the next user visiting position”. Li teaches predicting the next location of the user based on a position which is interpreted as the user vector and a travel vector interpreted as a sequence vector which is inputted into a machine learning model.
Li et al. teaches “a prediction unit configured to predict a next location that the user will visit based on the user victor and the sequence vector through machine learning.”
See Li et al., [Abstract], “the third stage is prediction of a user visiting position based on a recurrent neural network model; and the visiting position vector and the user travel mode feature vector obtained by pretraining are integrated as the input of the recurrent neural network model so as to realize the prediction of the next user visiting position”. Li teaches predicting the next location of the user based on a position which is interpreted as the user vector and a travel vector interpreted as a sequence vector which is inputted into a machine learning model.
It would have been obvious to a person of ordinary skill in art before the effective filling date of the invention to implement the function of Li et al. into the method of Grzywaczewski and YANG to teach user vector generation and user’s next location prediction. The modification would have been obvious because one of the ordinary skills of the art would be motivated to utilize the feature of Li et al. as all the references are in the field of machine learning and LLMs, making these references analogous. A person of ordinary skill of the art would have been motivated to perform the combination of being able to generate vectors based on movements and add features making it extremely convenient to obtain geographic position data of a user, which has led to the emergence of position-based services. Many useful values can be obtained by mining and analyzing the data, and individual services are further optimized. It is of great research significance and practical application value to predict the next visiting position based on analysis of user historical visiting positions. (Li [Background])
Claim 9:
Grzywaczewski teaches “An information processing apparatus comprising: acquiring data on positions of a user accompanying movement of the user;”
See Grzywaczewski, [0014], “According a one aspect of the present invention there is provided a predictive modelling system for predicting location data from user textual data comprising: an input for receiving user data, the user data comprising user textual data and location data; a pre-processing module arranged to correlate user textual data with location data to form a set of correlated data; a training module arranged to use the set of correlated data to train a machine learning algorithm such that the algorithm is arranged to output predicted location data from an input textual query.” Grzywaczewski [0055] “As described below the present invention provides a mechanism for a predictive model to “learn” a user's particular vocabulary from their historical movements and textual content.”. Grzywaczewski talks about a system for predicting a future location based on the user textual and location data. User textual data fully correlates with user feature based on the applicant’s specifications by using things such as social media, emails, etc. The second quote describes a predictive model learning and acquiring data from the movements of the user and its textual context .
Grzywaczewski teaches “acquiring a user feature representing a feature of the user”
See Grzywaczewski [Abstract], “A predictive modelling system for predicting location data from user textual data comprising: an input for receiving user data, the user data comprising user textual data and location data;” Grzywaczewski talks about a system for predicting a future location based on the user textual and location data. User textual data fully correlates with user feature based on the applicant’s specifications by using things such as social media, emails, etc.
Grzywaczewski does not explicitly disclose “generating a user vector representing a feature of the movement of the user based on the position data and the user feature; generating a sequence vector representing a sequence of locations visited by the user based on the position data; and predicting a next location that the user will visit based on the user victor and the sequence vector through machine learning.”
However, YANG et al. teaches “generating a user vector representing a feature of the movement of the user based on the position data and the user feature;”
See YANG et al., “A location-based service is an information or entertainment service, which is accessible on mobile devices through a mobile network and which uses information on the geographical position of the mobile device. First generation location-based services can include services to identify a location of a person or object, such as discovering the nearest banking cash machine or the whereabouts of a friend. Such services can also include mobile commerce, for example, by providing coupons or advertising directed at customers based on their current location. They could further include personalized weather services and even location-based games. (Column 1 Lines 31 - 42) Having such information might allow users to “check in” using the name of the business that they are visiting when they choose to check in” (Column 1 Lines 50 - 54) and “when executed, cause at least one processor of a computing device to receive a location history associated with a user, and determine, based at least in part on the location history, a visit vector comprising a plurality of vector elements, each respective vector element corresponding to a respective past instance of a timeslot and having a value indicating that the user visited a place during the respective past instance of the timeslot or a value indicating that the user did not visit the place during the respective past instance of the timeslot” (Column 3 Lines 23 – 28). YANG teaches a location based service which uses information based on the position data of a person. This application allows users to “check in” to businesses using names as user features. This is then put into a visit vector that tracks the historical data of the user.
It would have been obvious to a person of ordinary skill in art before the effective filling date of the invention to implement the function of YANG into the method of Grzywaczewski to teach user vector generation based on a user feature. The modification would have been obvious because one of the ordinary skills of the art would be motivated to utilize the feature of YANG as all the references are in the field of machine learning and LLMs, making these references analogous. A person of ordinary skill of the art would have been motivated to perform the combination of being able to generate vectors based on user features and creating an application in which the user features can be obtained to help create systems and techniques that can determine whether a user is likely to visit a place during a future instance of a timeslot based at least in part on a location history associated with the user. (YANG [Abstract])
Grzywaczewski and Yang do not explicitly disclose “a sequence vector generation unit configured to generate a sequence vector representing a sequence of locations visited by the user based on the position data; a prediction unit configured to predict a next location that the user will visit based on the user victor and the sequence vector through machine learning.”
Li et al. teaches “generating a sequence vector representing a sequence of locations visited by the user based on the position data;”
See Li et al., [Abstract], “the second stage is modeling of a user historical visiting behavior pattern based on geographical features; the third stage is prediction of a user visiting position based on a recurrent neural network model; and the visiting position vector and the user travel mode feature vector obtained by pretraining are integrated as the input of the recurrent neural network model so as to realize the prediction of the next user visiting position”. Li teaches predicting the next location of the user based on a position which is interpreted as the user vector and a travel vector interpreted as a sequence vector which is inputted into a machine learning model.
Li et al. teaches “predicting a next location that the user will visit based on the user victor and the sequence vector through machine learning.”
See Li et al., [Abstract], “the third stage is prediction of a user visiting position based on a recurrent neural network model; and the visiting position vector and the user travel mode feature vector obtained by pretraining are integrated as the input of the recurrent neural network model so as to realize the prediction of the next user visiting position”. Li teaches predicting the next location of the user based on a position and a travel vector which is inputted into a machine learning model.
It would have been obvious to a person of ordinary skill in art before the effective filling date of the invention to implement the function of Li et al. into the method of Grzywaczewski and YANG to teach user vector generation and user’s next location prediction. The modification would have been obvious because one of the ordinary skills of the art would be motivated to utilize the feature of Li et al. as all the references are in the field of machine learning and LLMs, making these references analogous. A person of ordinary skill of the art would have been motivated to perform the combination of being able to generate vectors based on movements and add features making it extremely convenient to obtain geographic position data of a user, which has led to the emergence of position-based services. Many useful values can be obtained by mining and analyzing the data, and individual services are further optimized. It is of great research significance and practical application value to predict the next visiting position based on analysis of user historical visiting positions. (Li [Background])
Claim 10:
Grzywaczewski teaches “A non-transitory computer readable medium storing a computer program for causing a computer to execute processing comprising: position data acquisition processing for acquiring data on positions of a user accompanying movement of the user;”.
See Grzywaczewski [0124], “A non-transitory computer readable medium storing a program for controlling a computing device to carry out the method of paragraph 19.” and Grzywaczewski [0120] “A method of training a machine learning algorithm comprising: [0121] receiving user data, the user data comprising user textual data and location data; [0122] correlating user textual data with location data to form a set of correlated data; [0123] using the set of correlated data to train a machine learning algorithm such that the algorithm is arranged to output predicted location data from an input textual query.” Grzywaczewski teaches the non-transitory computer readable medium that stores the program that is being used.
See Grzywaczewski, [0014], “According a one aspect of the present invention there is provided a predictive modelling system for predicting location data from user textual data comprising: an input for receiving user data, the user data comprising user textual data and location data; a pre-processing module arranged to correlate user textual data with location data to form a set of correlated data; a training module arranged to use the set of correlated data to train a machine learning algorithm such that the algorithm is arranged to output predicted location data from an input textual query.” Grzywaczewski [0055] “As described below the present invention provides a mechanism for a predictive model to “learn” a user's particular vocabulary from their historical movements and textual content.”. Grzywaczewski talks about a system for predicting a future location based on the user textual and location data. User textual data fully correlates with user feature based on the applicant’s specifications by using things such as social media, emails, etc. The second quote describes a predictive model learning and acquiring data from the movements of the user and its textual context.
Grzywaczewski teaches “feature acquisition processing for acquiring a user feature representing a feature of the user”
See Grzywaczewski [Abstract], “A predictive modelling system for predicting location data from user textual data comprising: an input for receiving user data, the user data comprising user textual data and location data;” Grzywaczewski talks about a system for predicting a future location based on the user textual and location data. User textual data fully correlates with user feature based on the applicant’s specifications by using things such as social media, emails, etc.
Grzywaczewski does not explicitly disclose “user vector generating processing for generating a user vector representing a feature of the movement of the user based on the position data and the user feature; sequence vector generation processing for generating a sequence vector representing a sequence of locations visited by the user from the position data; and prediction processing for predicting a next location that the user will visit based on the user victor and the sequence vector through machine learning.”
However, YANG et al. teaches “user vector generating processing for generating a user vector representing a feature of the movement of the user based on the position data and the user feature;”
See YANG et al., “A location-based service is an information or entertainment service, which is accessible on mobile devices through a mobile network and which uses information on the geographical position of the mobile device. First generation location-based services can include services to identify a location of a person or object, such as discovering the nearest banking cash machine or the whereabouts of a friend. Such services can also include mobile commerce, for example, by providing coupons or advertising directed at customers based on their current location. They could further include personalized weather services and even location-based games. (Column 1 Lines 31 - 42) Having such information might allow users to “check in” using the name of the business that they are visiting when they choose to check in” (Column 1 Lines 50 - 54) and “when executed, cause at least one processor of a computing device to receive a location history associated with a user, and determine, based at least in part on the location history, a visit vector comprising a plurality of vector elements, each respective vector element corresponding to a respective past instance of a timeslot and having a value indicating that the user visited a place during the respective past instance of the timeslot or a value indicating that the user did not visit the place during the respective past instance of the timeslot” (Column 3 Lines 23 – 28). YANG teaches a location based service which uses information based on the position data of a person. This application allows users to “check in” to businesses using names as user features. This is then put into a visit vector that tracks the historical data of the user.
It would have been obvious to a person of ordinary skill in art before the effective filling date of the invention to implement the function of YANG into the method of Grzywaczewski to teach user vector generation based on a user feature. The modification would have been obvious because one of the ordinary skills of the art would be motivated to utilize the feature of YANG as all the references are in the field of machine learning and LLMs, making these references analogous. A person of ordinary skill of the art would have been motivated to perform the combination of being able to generate vectors based on user features and creating an application in which the user features can be obtained to help create systems and techniques that can determine whether a user is likely to visit a place during a future instance of a timeslot based at least in part on a location history associated with the user. (YANG [Abstract])
Grzywaczewski and Yang do not explicitly disclose “sequence vector generation processing for generating a sequence vector representing a sequence of locations visited by the user from the position data; prediction processing for predicting a next location that the user will visit based on the user victor and the sequence vector through machine learning.”
Li et al. teaches “sequence vector generation processing for generating a sequence vector representing a sequence of locations visited by the user from the position data;”
See Li et al., [Abstract], “the second stage is modeling of a user historical visiting behavior pattern based on geographical features; the third stage is prediction of a user visiting position based on a recurrent neural network model; and the visiting position vector and the user travel mode feature vector obtained by pretraining are integrated as the input of the recurrent neural network model so as to realize the prediction of the next user visiting position”. Li teaches predicting the next location of the user based on a position which is interpreted as the user vector and a travel vector interpreted as a sequence vector which is inputted into a machine learning model.
Li et al. teaches “prediction processing for predicting a next location that the user will visit based on the user victor and the sequence vector through machine learning.”
See Li et al., [Abstract], “the third stage is prediction of a user visiting position based on a recurrent neural network model; and the visiting position vector and the user travel mode feature vector obtained by pretraining are integrated as the input of the recurrent neural network model so as to realize the prediction of the next user visiting position”. Li teaches predicting the next location of the user based on a position and a travel vector which is inputted into a machine learning model.
It would have been obvious to a person of ordinary skill in art before the effective filling date of the invention to implement the function of Li et al. into the method of Grzywaczewski and YANG to teach user vector generation and user’s next location prediction. The modification would have been obvious because one of the ordinary skills of the art would be motivated to utilize the feature of Li et al. as all the references are in the field of machine learning and LLMs, making these references analogous. A person of ordinary skill of the art would have been motivated to perform the combination of being able to generate vectors based on movements and add features making it extremely convenient to obtain geographic position data of a user, which has led to the emergence of position-based services. Many useful values can be obtained by mining and analyzing the data, and individual services are further optimized. It is of great research significance and practical application value to predict the next visiting position based on analysis of user historical visiting positions. (Li [Background])
Claim 2:
Regarding claim 2, Grzywaczewski, YANG and Li teach the limitations in claim 1.
Grzywaczewski does not explicitly disclose “The information processing apparatus according to claim 1, wherein based on the position data and the user feature, the user vector generation unit generates a region-of-interest vector that represents a geographical feature of a pattern of the movement of the user, and a location-of-interest vector that represents a feature of a location of interest for the user through the locations that the user has moved to, and generates the user vector by combining the region- of-interest vector and the location-of-interest vector.”
However, YANG teaches “The information processing apparatus according to claim 1, wherein based on the position data and the user feature, the user vector generation unit generates a region-of-interest vector that represents a geographical feature of a pattern of the movement of the user, and a location-of-interest vector that represents a feature of a location of interest for the user through the locations that the user has moved to, and generates the user vector by combining the region- of-interest vector and the location-of-interest vector.”
See YANG, [Column 22 Lines 25-43], “In a further aspect, a technique is provided for sorting, in order of decreasing visit likelihood, possible destinations visited by a user based on a geographic location from a user's location history. For a geographic location from a user's location history, a processor conducts a local search for destinations proximate to that geographic location, where the geographic location has a time vector associated with it (the time vector including start and end times for a plurality of visits) and the search provides at least a name for the destination and a distance from the geographic location. The processor computes, for each destination returned by the local search a visit likelihood, a visit likelihood as a function of at least the distance between the destination and the geographic location and a comparison between the time vector associated with the geographic location and a visit likelihood distribution across time. The processor sorts at least some of the destinations returned by the local search in decreasing order of visit likelihood to select the most likely visited destination for that geographic location.” Visit vector (Column 20 Lines 28-35), “First, the machine learning system is provided with a training set of various vectors followed by a yes or a no. The training vectors can be visit vectors selected from a variety of sources (e.g., the current user's location history, the location history for all users, the location history for all users of a particular demographic, location history for a particular place, location history for places of a particular type, and so forth). Second, the machine learning system is provided with a query vector. The query vector can be the vector of the current user's past visits to the place in question. The machine learning system looks at past occurrences of this vector in the training set and at what happened after this vector was encountered (e.g., whether and when a subsequent visit occurred). The machine learning system follows a series of decision trees, as opposed to merely calculating a probability, and outputs a prediction as to whether the user is likely to visit the place in the next week, two weeks, month, etc.” This teaches the region-of-interest vector by using the comparison between a time vector and a geographic location in order to create a visit likelihood distribution across time. The location of interest vector is also being taught by using the same time vector which includes the start and end times of visits, name and distance of a location of interest combined with the user’s location history. The machine then combines these two vectors with a series of decision trees in order to create an accurate prediction of whether the user will visit a certain place.
It would have been obvious to a person of ordinary skill in art before the effective filling date of the invention to implement the function of YANG into the method of Grzywaczewski to teach combining the visit vector and location of interest vector to create the most accurate prediction. The modification would have been obvious because one of the ordinary skills of the art would be motivated to utilize the feature of YANG as all the references are in the field of machine learning and LLMs, making these references analogous. A person of ordinary skill of the art would have been motivated to perform the combination of being able to combine vectors to create a machine learning system follows a series of decision trees, as opposed to merely calculating a probability, and outputs a prediction as to whether the user is likely to visit the place in the next week, two weeks, month, etc. (Column 20 Lines 28-35) with a more-granular understanding of a user's location information, (e.g., personalized and history aware location information), that can allow more sophisticated services to be provided (Yang [0004]).
Claim 4:
Regarding claim 4, Grzywaczewski, YANG and Li teach the limitations in claim 2.
YANG further teaches “The information processing apparatus according to claim 2 wherein the user vector generation unit uses the sequence of the locations visited by the user based on the position data and the user feature to generate the region-of-interest vector.”
See YANG, [Column 20 Lines 17-24], “First, the machine learning system is provided with a training set of various vectors followed by a yes or a no. The training vectors can be visit vectors selected from a variety of sources (e.g., the current user's location history, the location history for all users, the location history for all users of a particular demographic, location history for a particular place, location history for places of a particular type, and so forth).” It talks about the sequences of locations visited, user features and the position data of the user to be used as training for visit vectors.
It would have been obvious to a person of ordinary skill in art before the effective filling date of the invention to implement the function of YANG. into the method of Grzywaczewski to teach using location information in order to generate a region-of-interest vector. The modification would have been obvious because one of the ordinary skills of the art would be motivated to utilize the feature of YANG as all the references are in the field of machine learning and LLMs, making these references analogous. A person of ordinary skill of the art would have been motivated to perform the combination of a query vector and position acquisition unit. The query vector can be the vector of the current user's past visits to the place in question. (Column 20 Lines 25-30) This integrated into a position acquisition data unit creates a more accurate location output for the user.
Claim 5:
Regarding claim 5, Grzywaczewski, YANG and Li teach the limitations in claim 2.
YANG further teaches “The information processing apparatus according to claim 2 wherein the user vector generation unit uses names of the locations visited by the user based on the position data, land use types of the locations, and the user feature to generate the location-of- interest vector.”
See YANG, [Column 20 Lines 17-35],” First, the machine learning system is provided with a training set of various vectors followed by a yes or a no. The training vectors can be visit vectors selected from a variety of sources (e.g., the current user's location history, the location history for all users, the location history for all users of a particular demographic, location history for a particular place, location history for places of a particular type, and so forth). Second, the machine learning system is provided with a query vector. The query vector can be the vector of the current user's past visits to the place in question. The machine learning system looks at past occurrences of this vector in the training set and at what happened after this vector was encountered (e.g., whether and when a subsequent visit occurred). The machine learning system follows a series of decision trees, as opposed to merely calculating a probability, and outputs a prediction as to whether the user is likely to visit the place in the next week, two weeks, month, etc.” and see YANG [Column 4 Lines 15 - 23], “In some examples, a geographic location from a user’s location history can be used to perform a local search to find businesses or other destinations that are proximate to the user’s geographical location. A technique that includes a time-based visit likelihood distribution can be applied to calculate a likelihood that the user actually visited the nearby destinations, and the destinations can be ranked based on this likelihood so that the most likely destinations can be used in further applications”, see YANG [Column 7 Lines 66-67 and Column 8 Lines 1-6], “In general , the local search can return the names of businesses within the radius . The local search might also return the distance between the business and the geographic location ( or otherwise specify its relative position with respect to the geographic location ) . The local search might also return a category for each business located . For example , a restaurant might return a category of “food" while a hotel might return a category of "accommodation ".”. It talks about using location information, the names of the locations interpreted by the location history for a particular place, land use types based on the location history of a particular type and the current user’s past visits in order to create a probability and output a prediction to whether the user is likely to visit this place, which a location-of-interest vector represents a feature of a location of interest for the user through the movement of the user that use names of the locations visited by the user and/or land use types of the locations while the local search is used for the visit likelihood measurement used in the user vector generation unit to generate the location of interest vector shown in YANG [Fig 2.].
It would have been obvious to a person of ordinary skill in art before the effective filling date of the invention to implement the function of YANG. into the method of Grzywaczewski to teach using location information in order to predict a user likely visiting an area. The modification would have been obvious because one of the ordinary skills of the art would be motivated to utilize the feature of YANG as all the references are in the field of machine learning and LLMs, making these references analogous. A person of ordinary skill of the art would have been motivated to perform the combination of being able to combine vectors to create a machine learning system follows a series of decision trees, as opposed to merely calculating a probability, and outputs a prediction as to whether the user is likely to visit the place in the next week, two weeks, month, etc. (Column 20 Lines 28-35) with a more-granular understanding of a user's location information, (e.g., personalized and history aware location information), that can allow more sophisticated services to be provided (Column 1 Lines 43 - 45).
Claim 6:
Regarding claim 6, Grzywaczewski, YANG and Li teach the limitations in claim 1.
Grzywaczewski does not explicitly disclose “The information processing apparatus according to claim 1, further comprising a training unit configured to train a learning model for the machine learning, wherein the training unit uses the user vectors and the sequence vectors for a plurality of other users different from the user to train the learning model.”
However, YANG teaches “The information processing apparatus according to claim 1, further comprising a training unit configured to train a learning model for the machine learning, wherein the training unit uses the user vectors and the sequence vectors for a plurality of other users different from the user to train the learning model.”
See YANG, [Column 19 Lines 27-39], “If there is still insufficient information to make a confident prediction, the visit prediction module 602 can base its prediction on location history data for other users of the prediction server 150. For example, the visit prediction module 602 can rely on visits to the particular place by all other users. The visit prediction module 602 can also rely on visits to the particular place by other users that are of a similar demographic to the current user (e.g., other users who also have children, or other users of the same age). The visit prediction module 602 can also rely on visits to places of the same type by other users (e.g., visits to Italian restaurants generally as opposed to visits to the particular restaurant in question).” It teaches that if the trained model does not have enough data, it will use previous history from other users within a prediction server to form visit vector which are used to create the visit prediction module.
It would have been obvious to a person of ordinary skill in art before the effective filling date of the invention to implement the function of YANG. into the method of Grzywaczewski to teach combining the visit vector and location of interest vector to create the most accurate prediction. The modification would have been obvious because one of the ordinary skills of the art would be motivated to utilize the feature of YANG as all the references are in the field of machine learning and LLMs, making these references analogous. A person of ordinary skill of the art would have been motivated to perform the combination of being able to combine vectors to create a machine learning system follows a series of decision trees, as opposed to merely calculating a probability, and outputs a prediction as to whether the user is likely to visit the place in the next week, two weeks, month, etc. (Column 20 Lines 28-35) with a more-granular understanding of a user's location information, (e.g., personalized and history aware location information), that can allow more sophisticated services to be provided (Column 1 Lines 43 - 45).
Claim 7:
Regarding claim 7, Grzywaczewski, YANG and Li teach the limitations in claim 1.
Grzywaczewski does not explicitly disclose “wherein the user feature is a factual feature of the user.”
However, YANG teaches “wherein the user feature is a factual feature of the user.”
See YANG, [Column 1 Lines 21-30], “Mobile devices such as smartphones and tablets have opened up a variety of new services that can be provided to users on the go. The geographic location of a mobile device can be determined using any of several technologies for determining its position, including by referencing cellular network towers, WiFi locations, or GPS. Where users opt in to allowing services to use their geographic location, location-based services can be provided through the local device.” The application states the user features are any information related to the user which is obtained and achieved through the local device provided.
It would have been obvious to a person of ordinary skill in art before the effective filling date of the invention to implement the function of YANG. into the method of Grzywaczewski to teach using services to get information on the user. The modification would have been obvious because one of the ordinary skills of the art would be motivated to utilize the feature of YANG as all the references are in the field of machine learning and LLMs, making these references analogous. A person of ordinary skill of the art would have been motivated to perform the combination of being able to creating location-based services that can identify a location of a person or object, such as discovering the nearest banking cash machine or the whereabouts of a friend. Such services can also include mobile commerce, for example, by providing coupons or advertising directed at customers based on their current location. (Column 1 Lines 35 -40) with the location prediction unit with a more-granular understanding of a user's location information, (e.g., personalized and history aware location information), that can allow more sophisticated services to be provided (Column 1 Lines 43 - 45).
Claim 8:
Regarding claim 8, Grzywaczewski, YANG and Li teach the limitations in claim 1.
Grzywaczewski does not explicitly disclose “further comprising a provision unit configured to generate and provide to the user an advertisement relating to information of the location predicted by the prediction unit.”
However, YANG teaches “further comprising a provision unit configured to generate and provide to the user an advertisement relating to information of the location predicted by the prediction unit.”
See YANG, [Column 25 Lines 19-36], “Having such information might allow users to “check in” using social applications more easily by presenting the user with the name of the business that they are visiting when they choose to check in. E-commerce applications might include delivery coupons or advertising relating to businesses that the user actually visits.” It explains “E-commerce” applications that would generate and provide advertisements from the places already visited by the user.
It would have been obvious to a person of ordinary skill in art before the effective filling date of the invention to implement the function of YANG. into the method of Grzywaczewski to teach using services on mobile devices in order to get information on the user. The modification would have been obvious because one of the ordinary skills of the art would be motivated to utilize the feature of YANG as all the references are in the field of machine learning and LLMs, making these references analogous. A person of ordinary skill of the art would have been motivated to perform the combination of being able to creating location-based services that can identify a location of a person or object, such as discovering the nearest banking cash machine or the whereabouts of a friend. Such services can also include mobile commerce, for example, by providing coupons or advertising directed at customers based on their current location. (Column 1 Lines 35 -40) with the location prediction unit with a more-granular understanding of a user's location information, (e.g., personalized and history aware location information), that can allow more sophisticated services to be provided (Column 1 Lines 43 - 45).
Claim 3 is rejected under 35 U.S.C. 103 as being unpatentable over Grzywaczewski et al., “User Text Content Correlation with Location” (U.S. PG Pub No 20170013408) published on January 12, 2017, in view of YANG “Ranking nearby destinations based on visit likelihoods and predicting future visits to places from location” (U.S. Patent No 10332019) in view of Li et al. “VISITING POSITION PREDICTION METHOD BASED ON USER TRAVEL MODE” (AU Patent No 2021104609) published on September 23 2021, and further in view of Coates "Frustratingly Easy Meta-Embedding– Computing Meta-Embeddings by Averaging Source Word Embeddings" published on April 14, 2018.
Claim 3:
Regarding claim 3, Grzywaczewski, YANG and Li teach the limitations in claim 1.
Grzywaczewski does not explicitly disclose “The information processing apparatus according to claim 1, wherein based on the position data and the user feature, the user vector generation unit generates a region-of-interest vector that represents a geographical feature of a pattern of the movement of the user; a location- of-interest vector that represents a feature of a location of interest for the user through the movement of the user, and a transportation vector representing a feature of a transportation used by the user through the movement of the user, and generates the user vector by combining the region-of-interest vector, the location-of-interest vector, and the transportation vector.”
However, YANG teaches “The information processing apparatus according to claim 1, wherein based on the position data and the user feature, the user vector generation unit generates a region-of-interest vector that represents a geographical feature of a pattern of the movement of the user; a location- of-interest vector that represents a feature of a location of interest for the user through the movement of the user … and generates the user vector”
See YANG, [Column 22 Lines 25-43], “In a further aspect, a technique is provided for sorting, in order of decreasing visit likelihood, possible destinations visited by a user based on a geographic location from a user's location history. For a geographic location from a user's location history, a processor conducts a local search for destinations proximate to that geographic location, where the geographic location has a time vector associated with it (the time vector including start and end times for a plurality of visits) and the search provides at least a name for the destination and a distance from the geographic location. The processor computes, for each destination returned by the local search a visit likelihood, a visit likelihood as a function of at least the distance between the destination and the geographic location and a comparison between the time vector associated with the geographic location and a visit likelihood distribution across time. The processor sorts at least some of the destinations returned by the local search in decreasing order of visit likelihood to select the most likely visited destination for that geographic location.” Visit vector “First, the machine learning system is provided with a training set of various vectors followed by a yes or a no. The training vectors can be visit vectors selected from a variety of sources (e.g., the current user's location history, the location history for all users, the location history for all users of a particular demographic, location history for a particular place, location history for places of a particular type, and so forth). Second, the machine learning system is provided with a query vector. The query vector can be the vector of the current user's past visits to the place in question. The machine learning system looks at past occurrences of this vector in the training set and at what happened after this vector was encountered (e.g., whether and when a subsequent visit occurred). The machine learning system follows a series of decision trees, as opposed to merely calculating a probability, and outputs a prediction as to whether the user is likely to visit the place in the next week, two weeks, month, etc.” (Column 20 Lines 28-35). “The technique begins at step 800 where the user's location history is received or retrieved by the location history module 600. It will be appreciated that the location history module 600 can itself maintain the user's location history, in which case it may not be necessary to actively receive or retrieve it. Next, in step 802, the visit prediction module 602 makes future visit predictions for each visited place in the user's location history for each of one or more timeslots. The visit prediction module 602 can generate a prediction for each place/timeslot combination, e.g., in the form of a percentage likelihood that a user will visit the place during the timeslot as described above with respect to the technique of FIG. 7.” (Column 21 Lines 23-35). This teaches the region-of-interest vector by using the comparison between a time vector and a geographic location in order to create a visit likelihood distribution across time. The location of interest vector is also being taught by using the same time vector which includes the start and end times of visits, name and distance of a location of interest combined with the user’s location history.
It would have been obvious to a person of ordinary skill in art before the effective filling date of the invention to implement the functions of YANG into the method of Grzywaczewski, to teach user vector generation based on position data, user feature and movement of the user. The modification would have been obvious because one of the ordinary skills of the art would be motivated to utilize the feature of YANG as all the references are in the field of machine learning and LLMs, making these references analogous. A person of ordinary skill of the art would have been motivated to perform the combination of a user’s geographic location with a time vector associated with it and a comparison with a visit likelihood distribution across time (Column 22 Lines 25 - 40).
Grzywaczewski and YANG do not explicitly disclose “a transportation vector representing a feature of a transportation used by the user through the movement of the user” and “combining the region-of-interest vector, the location-of-interest vector, and the transportation vector”
However, Li teaches “a transportation vector representing a feature of a transportation used by the user through the movement of the user”
See Li, [Summary], “To overcome the above defects, the present invention proposes a visiting position prediction method based on a user travel mode, in which weighting of geospatial influence is introduced at the same time of using the time sequence transfer law between visiting positions to comprehensively consider factors of public transport and geospatial distance so as to model user's historical behaviors and improve the prediction accuracy. The method mainly introduces a time window to capture the subsequence structure of a user visiting position and to reduce the screening range of position prediction, then calculates the feature influence weight in comprehensive consideration of factors of public transport and geospatial distance, and models the user behavior pattern in the time window based on the weight so as to realize prediction.” and (Li [Background] ), “A visiting position prediction method based on a user travel mode, comprises three stages: establishment of a sequence chart of user visiting positions and learning of vector representation; modeling of a user historical visiting behavior pattern based on geographical features; and prediction of a user visiting position based on a
recurrent neural network model.”. It talks about using geospatial distance between locations and the factors of public transport as weights within the user travel mode vector (Abstract) in order to enhance the models’ prediction within a time window while the second quote talks about how the method is based off of a vector representation.
Li teaches predicting the next location of the user based on a historical position combined with the current position. The machine then combines this vector with the location of interest and region of interest vectors taught earlier with a series of decision trees in order to create an accurate prediction of whether the user will visit a certain place.
It would have been obvious to a person of ordinary skill in art before the effective filling date of the invention to implement the functions of Li et al. into the method of Grzywaczewski and YANG to teach combining predicting a user’s next location with location of interest and region of interest vectors. The modification would have been obvious because one of the ordinary skills of the art would be motivated to utilize the feature of Li et al. as all the references are in the field of machine learning and LLMs, making these references analogous. A person of ordinary skill of the art would have been motivated to perform the combination of a visiting position prediction method based on a user travel mode using geospatial influence at the same time of using the time sequence transfer law between visiting positions to comprehensively consider factors of public transport and geospatial distance to improve the prediction accuracy (Li [Summary]) with the location of interest and region of interest taught in the earlier documents.
Grzywaczewski, YANG and, Li does not teach “combining the region-of-interest vector, the location-of-interest vector, and the transportation vector”
However, Coates teaches “combining the region-of-interest vector, the location-of-interest vector, and the transportation vector”
See Coates [Conclusion], “We have presented an argument for averaging as a valid meta-embedding technique, and found experimental performance to be close to, or in some cases better than that of concatenation, with the additional benefit of reduced dimensionality. We propose that when conducting meta-embedding, both concatenation and averaging should be considered as methods of combining embedding spaces, and their individual advantages considered.”. Coates teaches combining multiple vectors using addition and subtraction, which are both different forms of vector combination.
It would have been obvious to a person of ordinary skill in art before the effective filling date of the invention to implement the functions of Coates into the method of Grzywaczewski, YANG and Li et al. to teach combining the visit vector and location of interest vector to create the most accurate prediction. The modification would have been obvious because one of the ordinary skills of the art would be motivated to utilize the feature of Coates as all the references are in the field of machine learning and LLMs, making these references analogous. A person of ordinary skill of the art would have been motivated to perform the combination to provide an approximation of the performance of concatenation without increasing the dimension of the embeddings and to highlight the validity of averaging across distinct word embedding sets, such that it may be considered as a tool in future meta-embedding endeavours (Coates [Introduction]).
Conclusion
Any inquiry concerning this communication or earlier communications from the
examiner should be directed to SAICHARAN PARTHASARATHY whose telephone number is (571)-272-8865. The examiner can normally be reached Monday-Thursday, 8am-6pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner's
supervisor, Usmaan Saeed can be reached at (571) 272-4046. 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/docxt 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.
/SAICHARAN PARTHASARATHY/
Examiner, Art Unit 2146
/USMAAN SAEED/Supervisory Patent Examiner, Art Unit 2146
Prosecution Insights