DETAILED ACTION
This correspondence is responsive to the application and preliminary amendment filed on July 20, 2022. Claims 1-9, 19-20, 22-30 are pending in the case, with claims 1, 6, 19-20, 27 and 30 in independent form. The preliminary amendment cancels claims 10-18 and 21, amends claims 3-5, 9, 19-20, and adds new claims 22-30.
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 .
Summary of Detailed Action
Claims 5, 26 are objected to regarding informalities.
Claims 1, 3-6, 8, 19-20, 22-23, 25-27 and 29-30 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Claims 1-2, 4, 6-8, 19-20, 24 and 27-30 are rejected under 35 U.S.C. 103 as being unpatentable over Oonishi et al. (Pub. No. 2022/0254279 A1, filed July 22, 2020) hereinafter Oonishi in view of Lakshmi Narayanan et al.
Claims 3, 9 are rejected under 35 U.S.C. 103 as being unpatentable over Oonishi et al. in view of Lakshmi Narayanan et al., and further in view of Wang et al., “Urban2Vec: Incorporating Street View Imagery and POIs for Multi-Modal Urban Neighborhood Embedding.”
Claim Objections
Claim 5 and 26 are objected to because of the following informalities:
Claim 5, line 7, “the embedding network” should be “the embedding networks”.
Claim 26, line 6, “the embedding network” should be “the embedding networks”.
Appropriate correction is required.
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.
Claims 1, 3-6, 8, 19-20, 22-23, 25-27 and 29-30 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claims recite a method for establishing an encoding model, comprising: training the encoding model using the training data, the encoding model performing the following operations on each sample: performing embedding on at least one kind of geographic function information and at least one kind of surface-feature distribution information of the sample, and fusing vector representations obtained by the embedding to obtain an encoding result of the sample; wherein the encoding model has training targets of minimizing a distance between the encoding result of the anchor sample and the encoding result of the positive sample in the triplet, and maximizing a distance between the encoding result of the anchor sample and the encoding result of the negative sample in the triplet, which are Mathematical Concepts including mathematical relationships, mathematical formulas or equations, and mathematical calculations. See MPEP 2106.04(a)(2)(I).
This judicial exception is not integrated into a practical application and the claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Claims 1-9, 19-20 and 22-30 recite one of the four statutory categories of patent able subject matter and belong to the statutory class(es) of a process (method claims 1-9, 22-23), a machine (system/apparatus claims 19, 24-29), and an article of manufacture (non-transitory computer readable media claims 20, 30).
Claim 1 recites a method, thus a process and one of the four statutory categories of patentable subject matter. However, claim 1 further recites for establishing an encoding model, comprising: training the encoding model using the training data, the encoding model performing the following operations on each sample: performing embedding on at least one kind of geographic function information and at least one kind of surface-feature distribution information of the sample, and fusing vector representations obtained by the embedding to obtain an encoding result of the sample; wherein the encoding model has training targets of minimizing a distance between the encoding result of the anchor sample and the encoding result of the positive sample in the triplet, and maximizing a distance between the encoding result of the anchor sample and the encoding result of the negative sample in the triplet, which are Mathematical Concepts including mathematical relationships, mathematical formulas or equations, and mathematical calculations. See MPEP 2106.04(a)(2)(I).
The claim does not include any additional elements which integrate the abstract idea into a practical application since the additional elements consist of:
acquiring training data, the training data comprising at least one triplet, and the triplet comprising an anchor sample, a positive sample and a negative sample of geographic location regions (An additional element of extra-solution activity that courts have identified is well understood, routine and conventional activity for receiving or transmitting data over a network, e.g., using the internet to gather data. See also, MPEP 2106.05(d)(II), MPEP 2106.05(g), 2019 Guidance, 84 FR 50 at 55, 2019 Guidance, 84 FR 50, footnote 31.).
Thus, the claim is directed to the abstract idea.
Further, the additional elements, alone or in combination, do not provide significantly more than the abstract idea itself, because transmitting data over a network is well-understood, routine and conventional (MPEP 2106.05(d) and the combination of additional elements does not provide an inventive concept. Thus, the claim is ineligible.
Claim 3, dependent on claim 1, recites additional mental processes for selecting a neighbor geographic location region of the anchor sample as the positive sample, and selecting a non-neighbor geographic location region of the anchor sample as the negative sample, which are mental processes or concepts that can be performed in the human mind, including observation, evaluation, judgment, or opinion, or by a human with pen and paper. See MPEP 210604(a)(2)(III).
Claim 3 does not include any additional elements which integrate the abstract idea into a practical application since the additional elements consist of:
wherein the acquiring training data comprises: acquiring the anchor sample of a geographic location region (An additional element of extra-solution activity that courts have identified is well understood, routine and conventional activity for receiving or transmitting data over a network, e.g., using the internet to gather data. See also, MPEP 2106.05(d)(II), MPEP 2106.05(g), 2019 Guidance, 84 FR 50 at 55, 2019 Guidance, 84 FR 50, footnote 31.).
Claim 4, dependent on claim 1, recites additional mathematical concepts for pre-dividing the geographic location region according to preset precision, which are Mathematical Concepts including mathematical relationships, mathematical formulas or equations, and mathematical calculations. See MPEP 2106.04(a)(2)(I).
Claim 5, dependent on claim 1, recites additional mathematical concepts for wherein the at least one kind of geographic function information and the at least one kind of surface-feature distribution information extracted from the sample are input; the embedding is performed on the input information to obtain the corresponding vector representations; and the vector representations output are fused, so as to obtain the encoding result of the sample; when the encoding model is trained, model parameters of the embedding network and the fusion network are iteratively updated according to values of a loss function, and the loss function is pre-constructed according to the training target, which are Mathematical Concepts including mathematical relationships, mathematical formulas or equations, and mathematical calculations. See MPEP 2106.04(a)(2)(I).
Claim 5 does not include any additional elements which integrate the abstract idea into a practical application since the additional elements consist of:
encoding model comprises at least two embedding networks and a fusion network (This additional element amounts to merely the words to “apply it” (or an equivalent) or are mere instructions to implement an abstract idea or other exception on a computer. MPEP 2106.05(f).) Also, this additional element amounts to no more than generally linking the use of the judicial exception to a particular technologic environment or field of use - The application or use of the judicial exception in this manner does not meaningfully limit the claim by going beyond generally linking the use of the judicial exception to a particular technological environment. MPEP 2106.05(h)).
into the embedding networks respectively (This additional element amounts to merely the words to “apply it” (or an equivalent) or are mere instructions to implement an abstract idea or other exception on a computer. MPEP 2106.05(f).) Also, this additional element amounts to no more than generally linking the use of the judicial exception to a particular technologic environment or field of use - The application or use of the judicial exception in this manner does not meaningfully limit the claim by going beyond generally linking the use of the judicial exception to a particular technological environment. MPEP 2106.05(h)).
by the embedding network (This additional element amounts to merely the words to “apply it” (or an equivalent) or are mere instructions to implement an abstract idea or other exception on a computer. MPEP 2106.05(f).) Also, this additional element amounts to no more than generally linking the use of the judicial exception to a particular technologic environment or field of use - The application or use of the judicial exception in this manner does not meaningfully limit the claim by going beyond generally linking the use of the judicial exception to a particular technological environment. MPEP 2106.05(h)).
by the embedding networks (This additional element amounts to merely the words to “apply it” (or an equivalent) or are mere instructions to implement an abstract idea or other exception on a computer. MPEP 2106.05(f).) Also, this additional element amounts to no more than generally linking the use of the judicial exception to a particular technologic environment or field of use - The application or use of the judicial exception in this manner does not meaningfully limit the claim by going beyond generally linking the use of the judicial exception to a particular technological environment. MPEP 2106.05(h)).
by the fusion network (This additional element amounts to merely the words to “apply it” (or an equivalent) or are mere instructions to implement an abstract idea or other exception on a computer. MPEP 2106.05(f).) Also, this additional element amounts to no more than generally linking the use of the judicial exception to a particular technologic environment or field of use - The application or use of the judicial exception in this manner does not meaningfully limit the claim by going beyond generally linking the use of the judicial exception to a particular technological environment. MPEP 2106.05(h)).
Claim 22, dependent on claim 1, recites additional mental processes for selecting another geographic location region as the negative sample, which are mental processes or concepts that can be performed in the human mind, including observation, evaluation, judgment, or opinion, or by a human with pen and paper. See MPEP 210604(a)(2)(III).
Claim 22 does not include any additional elements which integrate the abstract idea into a practical application since the additional elements consist of:
wherein the acquiring training data comprises: from a navigation log, acquiring a geographic location region where a navigation starting point is located and a geographic location region where a navigation ending point is located as the anchor sample and the positive sample of the geographic location regions respectively (An additional element of extra-solution activity that courts have identified is well understood, routine and conventional activity for receiving or transmitting data over a network, e.g., using the internet to gather data. See also, MPEP 2106.05(d)(II), MPEP 2106.05(g), 2019 Guidance, 84 FR 50 at 55, 2019 Guidance, 84 FR 50, footnote 31.).
Claim 23, dependent on claim 1, recites additional mental processes for selecting another geographic location region as the negative sample, which are mental processes or concepts that can be performed in the human mind, including observation, evaluation, judgment, or opinion, or by a human with pen and paper. See MPEP 210604(a)(2)(III).
Claim 23 does not include any additional elements which integrate the abstract idea into a practical application since the additional elements consist of:
wherein the acquiring training data comprises: from a retrieval log, acquiring a geographic location region where an initiating location of retrieval is located and a geographic location region where a target location of the retrieval is located as the anchor sample and the positive sample of the geographic location regions respectively (An additional element of extra-solution activity that courts have identified is well understood, routine and conventional activity for receiving or transmitting data over a network, e.g., using the internet to gather data. See also, MPEP 2106.05(d)(II), MPEP 2106.05(g), 2019 Guidance, 84 FR 50 at 55, 2019 Guidance, 84 FR 50, footnote 31.).
Claim 6 recites a method, thus a process and one of the four statutory categories of patentable subject matter. However, claim 6 further recites for encoding a geographic location region, comprising: determining a to-be-encoded geographic location region; inputting the acquired geographic function information and the acquired surface-feature distribution information into an encoding model, the encoding model performing embedding on the geographic function information and the surface-feature distribution information, and fusing vector representations obtained by the embedding to obtain an encoding result of the geographic location region, which are mathematical concepts and mental processes. Additionally, the recitation of determining a to-be-encoded geographic location region is also a mental process or concept that can be performed in the human mind, including observation, evaluation, judgment, or opinion, or by a human with pen and paper. See MPEP 210604(a)(2)(III). The recitations for encoding a geographic location region, inputting the acquired geographic function information and the acquired surface-feature distribution information into an encoding model, the encoding model performing embedding on the geographic function information and the surface-feature distribution information, and fusing vector representations obtained by the embedding to obtain an encoding result of the geographic location region, are mathematical concepts including mathematical relationships, mathematical formulas or equations, and mathematical calculations. See MPEP 210604(a)(2)(I).
Claim 6 does not include any additional elements which integrate the abstract idea into a practical application since the additional elements consist of:
acquiring at least one kind of geographic function information and at least one kind of surface-feature distribution information of the geographic location region (An additional element of extra-solution activity that courts have identified is well understood, routine and conventional activity for receiving or transmitting data over a network, e.g., using the internet to gather data. See also, MPEP 2106.05(d)(II), MPEP 2106.05(g), 2019 Guidance, 84 FR 50 at 55, 2019 Guidance, 84 FR 50, footnote 31.).
Thus, the claim is directed to the abstract idea.
Further, the additional elements, alone or in combination, do not provide significantly more than the abstract idea itself, because transmitting data over a network is well-understood, routine and conventional (MPEP 2106.05(d) and the combination of additional elements does not provide an inventive concept. Thus, the claim is ineligible.
Claim 8, dependent on claim 6, recites additional mathematical concepts and mental processes for pre-dividing the geographic location region according to preset precision, which are Mathematical Concepts including mathematical relationships, mathematical formulas or equations, and mathematical calculations. See MPEP 2106.04(a)(2)(I), wherein the determining the to-be-encoded geographic location region comprises determining the geographic location region where the geographic location coordinate is located as the to-be-encoded geographic location region, which are mental processes or concepts that can be performed in the human mind, including observation, evaluation, judgment, or opinion, or by a human with pen and paper. See MPEP 210604(a)(2)(III).
Claim 8 does not include any additional elements which integrate the abstract idea into a practical application since the additional elements consist of:
acquiring an input geographic location coordinate (An additional element of extra-solution activity that courts have identified is well understood, routine and conventional activity for receiving or transmitting data over a network, e.g., using the internet to gather data. See also, MPEP 2106.05(d)(II), MPEP 2106.05(g), 2019 Guidance, 84 FR 50 at 55, 2019 Guidance, 84 FR 50, footnote 31.).
Claim 19 recites a device, thus a machine and one of the four statutory categories of patentable subject matter.
The claim does not include any additional elements which integrate the abstract idea into a practical application since the additional elements consist of:
An electronic device, comprising: at least one processor; and a memory connected with the at least one processor communicatively; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method according to claim 1 (An additional element(s) that amounts to no more than mere instructions to apply an exception. This additional element(s) amounts to merely the words “apply it” (or an equivalent) or are mere instructions to implement an abstract idea or the exception on a computer. MPEP 2106.05(f)). These limitations are recited at a high level of generality, i.e., as generic computer components performing generic computer functions. Accordingly, these additional elements do not impose any meaningful limitations on the practicing the abstract idea.)
Thus, the claim is directed to the abstract idea.
Further, the additional elements, alone or in combination, do not provide significantly more than the abstract idea itself, because implementation on a computer (MPEP 2106.05(f)) cannot provide significantly more, and transmitting data over a network is well-understood, routine and conventional (MPEP 2106.05(d) and the combination of additional elements does not provide an inventive concept. Thus, the claim is ineligible.
Claim 25, dependent on claim 19, recites mental processes for selecting a neighbor geographic location region of the anchor sample as the positive sample, and selecting a non-neighbor geographic location region of the anchor sample as the negative sample, and selecting another geographic location region as the negative sample, and selecting another geographic location region as the negative sample, which are mental processes or concepts that can be performed in the human mind, including observation, evaluation, judgment, or opinion, or by a human with pen and paper. See MPEP 210604(a)(2)(III).
Claim 25 does not include any additional elements which integrate the abstract idea into a practical application since the additional elements consist of:
wherein the acquiring training data comprises: acquiring the anchor sample of a geographic location region (An additional element of extra-solution activity that courts have identified is well understood, routine and conventional activity for receiving or transmitting data over a network, e.g., using the internet to gather data. See also, MPEP 2106.05(d)(II), MPEP 2106.05(g), 2019 Guidance, 84 FR 50 at 55, 2019 Guidance, 84 FR 50, footnote 31.).
or from a navigation log, acquiring a geographic location region where a navigation starting point is located and a geographic location region where a navigation ending point is located as the anchor sample and the positive sample of the geographic location regions respectively (An additional element of extra-solution activity that courts have identified is well understood, routine and conventional activity for receiving or transmitting data over a network, e.g., using the internet to gather data. See also, MPEP 2106.05(d)(II), MPEP 2106.05(g), 2019 Guidance, 84 FR 50 at 55, 2019 Guidance, 84 FR 50, footnote 31.).
or from a retrieval log, acquiring a geographic location region where an initiating location of retrieval is located and a geographic location region where a target location of the retrieval is located as the anchor sample and the positive sample of the geographic location regions respectively (An additional element of extra-solution activity that courts have identified is well understood, routine and conventional activity for receiving or transmitting data over a network, e.g., using the internet to gather data. See also, MPEP 2106.05(d)(II), MPEP 2106.05(g), 2019 Guidance, 84 FR 50 at 55, 2019 Guidance, 84 FR 50, footnote 31.).
Claim 26, dependent on claim 19, recites mathematical concepts for wherein the at least one kind of geographic function information and the at least one kind of surface-feature distribution information extracted from the sample are input; the embedding is performed on the input information to obtain the corresponding vector representations; and the vector representations output are fused so as to obtain the encoding result of the sample; when the encoding model is trained, model parameters are iteratively updated according to values of a loss function, and the loss function is pre-constructed according to the training target, which are mathematical concepts including mathematical relationships, mathematical formulas or equations, and mathematical calculations. See MPEP 210604(a)(2)(I).
Claim 26 does not include any additional elements which integrate the abstract idea into a practical application since the additional elements consist of:
wherein the encoding model comprises at least two embedding networks and a fusion network (This additional element amounts to merely the words to “apply it” (or an equivalent) or are mere instructions to implement an abstract idea or other exception on a computer. MPEP 2106.05(f).) Also, this additional element amounts to no more than generally linking the use of the judicial exception to a particular technologic environment or field of use - The application or use of the judicial exception in this manner does not meaningfully limit the claim by going beyond generally linking the use of the judicial exception to a particular technological environment. MPEP 2106.05(h)).
into the embedding networks respectively (This additional element amounts to merely the words to “apply it” (or an equivalent) or are mere instructions to implement an abstract idea or other exception on a computer. MPEP 2106.05(f).) Also, this additional element amounts to no more than generally linking the use of the judicial exception to a particular technologic environment or field of use - The application or use of the judicial exception in this manner does not meaningfully limit the claim by going beyond generally linking the use of the judicial exception to a particular technological environment. MPEP 2106.05(h)).
by the embedding network (This additional element amounts to merely the words to “apply it” (or an equivalent) or are mere instructions to implement an abstract idea or other exception on a computer. MPEP 2106.05(f).) Also, this additional element amounts to no more than generally linking the use of the judicial exception to a particular technologic environment or field of use - The application or use of the judicial exception in this manner does not meaningfully limit the claim by going beyond generally linking the use of the judicial exception to a particular technological environment. MPEP 2106.05(h)).
by the embedding networks (This additional element amounts to merely the words to “apply it” (or an equivalent) or are mere instructions to implement an abstract idea or other exception on a computer. MPEP 2106.05(f).) Also, this additional element amounts to no more than generally linking the use of the judicial exception to a particular technologic environment or field of use - The application or use of the judicial exception in this manner does not meaningfully limit the claim by going beyond generally linking the use of the judicial exception to a particular technological environment. MPEP 2106.05(h)).
by the fusion network (This additional element amounts to merely the words to “apply it” (or an equivalent) or are mere instructions to implement an abstract idea or other exception on a computer. MPEP 2106.05(f).) Also, this additional element amounts to no more than generally linking the use of the judicial exception to a particular technologic environment or field of use - The application or use of the judicial exception in this manner does not meaningfully limit the claim by going beyond generally linking the use of the judicial exception to a particular technological environment. MPEP 2106.05(h)).
of the embedding network and the fusion network (This additional element amounts to merely the words to “apply it” (or an equivalent) or are mere instructions to implement an abstract idea or other exception on a computer. MPEP 2106.05(f).) Also, this additional element amounts to no more than generally linking the use of the judicial exception to a particular technologic environment or field of use - The application or use of the judicial exception in this manner does not meaningfully limit the claim by going beyond generally linking the use of the judicial exception to a particular technological environment. MPEP 2106.05(h)).
Claim 20 recites a non-transitory computer readable storage medium, thus an article of manufacture and one of the four statutory categories of patentable subject matter.
The claim does not include any additional elements which integrate the abstract idea into a practical application since the additional elements consist of:
A non-transitory computer readable storage medium with computer instructions stored thereon, wherein the computer instructions are used for causing a computer to perform the method according to claim 1 (An additional element(s) that amounts to no more than mere instructions to apply an exception. This additional element(s) amounts to merely the words “apply it” (or an equivalent) or are mere instructions to implement an abstract idea or the exception on a computer. MPEP 2106.05(f)). These limitations are recited at a high level of generality, i.e., as generic computer components performing generic computer functions. Accordingly, these additional elements do not impose any meaningful limitations on the practicing the abstract idea.)
Thus, the claim is directed to the abstract idea.
Further, the additional elements, alone or in combination, do not provide significantly more than the abstract idea itself, because implementation on a computer (MPEP 2106.05(f)) cannot provide significantly more, and transmitting data over a network is well-understood, routine and conventional (MPEP 2106.05(d) and the combination of additional elements does not provide an inventive concept. Thus, the claim is ineligible.
Claim 27 recites a device, thus a machine and one of the four statutory categories of patentable subject matter.
The claim does not include any additional elements which integrate the abstract idea into a practical application since the additional elements consist of:
An electronic device, comprising: at least one processor; and a memory connected with the at least one processor communicatively; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method according to claim 6 (An additional element(s) that amounts to no more than mere instructions to apply an exception. This additional element(s) amounts to merely the words “apply it” (or an equivalent) or are mere instructions to implement an abstract idea or the exception on a computer. MPEP 2106.05(f)). These limitations are recited at a high level of generality, i.e., as generic computer components performing generic computer functions. Accordingly, these additional elements do not impose any meaningful limitations on the practicing the abstract idea.)
Thus, the claim is directed to the abstract idea.
Further, the additional elements, alone or in combination, do not provide significantly more than the abstract idea itself, because implementation on a computer (MPEP 2106.05(f)) cannot provide significantly more, and transmitting data over a network is well-understood, routine and conventional (MPEP 2106.05(d) and the combination of additional elements does not provide an inventive concept. Thus, the claim is ineligible.
Claim 29, dependent on claim 27, recites additional mathematical concepts and mental processes for pre-dividing the geographic location region according to preset precision, which are mathematical concepts including mathematical relationships, mathematical formulas or equations, and mathematical calculations. See MPEP 210604(a)(2)(I),wherein the determining the to-be-encoded geographic location region and determining the geographic location region where the geographic location coordinate is located as the to-be-encoded geographic location region, which are mental processes or concepts that can be performed in the human mind, including observation, evaluation, judgment, or opinion, or by a human with pen and paper. See MPEP 210604(a)(2)(III).
Claim 29 does not include any additional elements which integrate the abstract idea into a practical application since the additional elements consist of:
acquiring an input geographic location coordinate (An additional element of extra-solution activity that courts have identified is well understood, routine and conventional activity for receiving or transmitting data over a network, e.g., using the internet to gather data. See also, MPEP 2106.05(d)(II), MPEP 2106.05(g), 2019 Guidance, 84 FR 50 at 55, 2019 Guidance, 84 FR 50, footnote 31.).
Claim 30 recites a non-transitory computer readable storage medium, thus an article of manufacture and one of the four statutory categories of patentable subject matter.
The claim does not include any additional elements which integrate the abstract idea into a practical application since the additional elements consist of:
A non-transitory computer readable storage medium with computer instructions stored thereon, wherein the computer instructions are used for causing a computer to perform the method according to claim 6 (An additional element(s) that amounts to no more than mere instructions to apply an exception. This additional element(s) amounts to merely the words “apply it” (or an equivalent) or are mere instructions to implement an abstract idea or the exception on a computer. MPEP 2106.05(f)). These limitations are recited at a high level of generality, i.e., as generic computer components performing generic computer functions. Accordingly, these additional elements do not impose any meaningful limitations on the practicing the abstract idea.)
Thus, the claim is directed to the abstract idea.
Further, the additional elements, alone or in combination, do not provide significantly more than the abstract idea itself, because implementation on a computer (MPEP 2106.05(f)) cannot provide significantly more, and transmitting data over a network is well-understood, routine and conventional (MPEP 2106.05(d) and the combination of additional elements does not provide an inventive concept. Thus, the claim is ineligible.
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.
Claim(s) 1-2, 4, 6-8, 19-20, 24 and 27-30 are rejected under 35 U.S.C. 103 as being unpatentable over Oonishi et al. (Pub. No. 2022/0254279 A1, filed July 22, 2020) hereinafter Oonishi in view of Lakshmi Narayanan et al. (Pub. No. US 2020/0086879 A1, published March 19, 2020) hereinafter Lakshmi.
Regarding claim 1, teaches:
A method for establishing an encoding model (i.e., Generation of the geographical feature generation model md1 (method for establishing an encoding model) will be described now. … As illustrated in FIG. 5, the model generating unit 15 includes a training data acquiring unit 151, a vector generating unit 152, and a model training unit 153.Oonishi, Figs 1, 3-6, para 49), comprising:
acquiring training data, the training data comprising at least one triplet, and the triplet comprising an anchor sample, a positive sample and a negative sample of geographic location regions (i.e., The map image is, for example, an image of a map of an area with a square of 250 m or a square of 500 m centered on the position indicated by the position information. Oonishi, para 42. As illustrated in FIG. 4, the acquisition unit 11 acquires a first map image rp1 including a first POI from the map image storage unit 30. For example, the first map image rp1 includes a plurality of layers such as terrain information rp11, genre information rp12, and a road map rp13. Oonishi, para 45. The training data acquiring unit 151 acquires anchor training data rpa, positive-example training data rpp, and negative-example training data rpn which are provided for training the geographical feature generation model md1 as a set of training data (acquiring training data, training data comprising at least one triplet, and the triplet comprising an anchor sample, a positive sample and a negative sample of geographic location regions (map image of position areas, geographical location regions, para 42, 45, 51-54)).Oonishi, Figs 1, 3-6, para 50, 42, 45, 49-54.); and
training the encoding model using the training data, the encoding model performing the following operations on each sample: performing embedding on at least one kind of geographic function information and at least one kind of surface-feature distribution information of the sample, and
Oonishi teaches that, The training data acquiring unit 151 acquires the map images of the first area, the second area, and the third area as the anchor training data rpa, the positive-example training data rpp, and the negative-example training data rpn from the map image storage unit 30. Various attribute values for each area may be correlated with the corresponding map image. Specifically, daytime population for each area, the number of facilities (the number of POIs) for each category, and the like may be correlated with the corresponding map image. Accordingly, the training data acquiring unit 151 can acquire various attribute values correlated with the first area, the second area, and the third area along with the anchor training data rpa, the positive-example training data rpp, and the negative-example training data rpn (training the encoding model using the training data, the encoding model performing the following operations on each sample: performing embedding on at least one kind of geographic function information (geographic function POI information) and at least one kind of surface-feature distribution information of the sample (map image surface-feature terrain, genre, road distribution information, para 43-45)). Oonishi, Figs 1, 3-6, para 54, 54-58, 42-45.
The training data acquiring unit 151 can extract the number of POIs belonging to each category for each of the first area, the second area, and the third area based on the category ID and the position information with reference to the POI information storage unit 20. Then, the training data acquiring unit 151 can add the extracted number of POIs as an attribute value (at least one kind of geographic function information (at least one kind of geographic function POI information) of the sample) for the corresponding area to the anchor training data rpa, the positive-example training data rpp, and the negative-example training data rpn. Oonishi, Figs 1, 3-6, para 55, 54-58, 42-45.
The map image may be constituted by a plurality of layers. That is, the map image may include a plurality of layers such as terrain information, genre information, and a road map associated with the area (at least one kind of surface-feature distribution information (map image surface-feature distribution terrain, genre, road information) of the sample).[0044] The generation unit 12 inputs the map image to a trained geographical feature generation model and generates a feature vector indicating geographical features of the map image. The geographical feature generation model is a model that is constructed by machine learning with a map image as an input and with a feature vector indicating geographical features of the map image as an output. Oonishi, Figs 1, 3-6, para 42-45, 54-58.
[0057] The vector generating unit 152 inputs the anchor training data rpa, the positive-example training data rpp, and the negative-example training data rpn to the geographical feature generation model md1 and generates an anchor feature vector va, a positive-example feature vector vp, and a negative-example feature vector vn (training the encoding model using the training data, the encoding model performing the following operations on each sample: performing embedding on at least one kind of geographic function information (geographic function POI information) and at least one kind of surface-feature distribution information of the sample (map image surface-feature terrain, genre, road distribution information), and ). That is, the anchor feature vector va, the positive-example feature vector vp, and the negative-example feature vector vn are distributed expressions of the anchor training data rpa, the positive-example training data rpp, and the negative-example training data rpn. As illustrated in FIG. 6, the geographical feature generation models md1 to which the anchor training data rpa, the positive-example training data rpp, and the negative-example training data rpn are input share parameters. Oonishi, Figs 1, 3-6, para 57, 54-58, 42-45.
wherein the encoding model has training targets of minimizing a distance between the encoding result of the anchor sample and the encoding result of the positive sample in the triplet, and maximizing a distance between the encoding result of the anchor sample and the encoding result of the negative sample in the triplet.
Oonishi teaches that, The model training unit 153 adjusts parameters of a neural network (CNN) which is included in the geographical feature generation model md1 such that a difference between the anchor feature vector va and the positive-example feature vector vp approaches zero and a difference between the anchor feature vector va and the negative-example feature vector vn increases (wherein the encoding model has training targets of minimizing a distance (minimizing distance approaches zero) between the encoding result of the anchor sample and the encoding result of the positive sample in the triplet, and maximizing a distance (maximizing, increasing distance) between the encoding result of the anchor sample and the encoding result of the negative sample in the triplet). Oonishi, Figs 1, 3-6, para 58, 54-58, 42-45.
Thus, as discussed above, Oonishi teaches a method for establishing an encoding model, comprising: acquiring training data, the training data comprising at least one triplet, and the triplet comprising an anchor sample, a positive sample and a negative sample of geographic location regions; and training the encoding model using the training data, the encoding model performing the following operations on each sample: performing embedding on at least one kind of geographic function information and at least one kind of surface-feature distribution information of the sample, and
Oonishi does not specifically disclose fusing vector representations.
However, Lakshmi teaches in the field related to scene classification and prediction, Lakshmi, Abstract, para 2-3. Lakshmi, which is analogous to the claimed invention because Lakshmi is directed to scene image understanding and classification, teaches that, [0142] According to one aspect, the system 1500 for scene classification may be a system for scene classification and prediction. According to this aspect, the system may be implemented in a manner similar to the system 1500 for scene classification except that one or more feature vectors (e.g., a first feature vector, a second feature vector, a third feature vector, etc.) may be generated (e.g., via the convolutor 1516 or the temporal classifier 1518) and fused or concatenated by the concatenator 1540 (fusing vector representations). The scene classifier 1520 may classify image frames accordingly and generate an associated scene prediction based on the fusion element produced by the data fusion of the feature vectors (fusing vector representations). Lakshmi, para 142.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to implement the method for establishing an encoding model of Oonishi using the fusing vector representations of Lakshmi, with a reasonable expectation of success, in order to provide understanding and classification of complex scene using optimal learning based algorithms. Laksmi, para 2-3, 142. This would have provided the advantages of combining information from multiple sources to create a more accurate comparisons between geographic regions.
Regarding claim 2, which depends from claim 1 and recites:
wherein the geographic function information comprises at least one of: point of interest information, user information, or place query terms initiated at the geographic location region; and the surface-feature distribution information comprises at least one of: a map image or a real-scene image.
Oonishi in view of Lakshmi teaches the method of claim 1 from which claim 2 depends, including the geographic function information and the surface-feature distribution information. As similarly discussed above with respect to claim 1, Oonishi in at least Figures 1, 3-6 and paragraphs 42-45, teaches that the geographic function information comprises at least one of: point of interest information, user information, or place query terms initiated at the geographic location region. Oonishi in at least Figures 1, 3-6 and para 54-58 teaches that the surface-feature distribution information comprises at least one of: a map image or a real-scene image. Oonishi, Figs 1, 3-6, para 42-45, 54-58.
Regarding claim 4, which depends from claim 1 and further recites:
pre-dividing the geographic location region according to preset precision.
Oonishi in view of Lakshmi teaches the method of claim 1 from which claim 4 depends, including the geographic location regions. Oonishi teaches that, [0042] The map image storage unit 30 is constituted by a storage device that stores a map image. The acquisition unit 11 acquires a map image with reference to the map image storage unit 30 based on position information. The map image is, for example, an image of a map of an area with a square of 250 m or a square of 500 m centered on the position indicated by the position information (pre-dividing the geographic location region according to preset precision (pre-dividing the map image area according to a preset square 250m or square 500 m precision)). The size of an area of the map image is not limited to the illustrated size. Oonishi, Figs 1, 3-6, para 42.
Regarding claim 6, Oonishi teaches:
A method for encoding a geographic location region (i.e., FIG. 4 is a diagram schematically illustrating an example in which a feature vector indicating geographical features of a POI is generated (method for encoding a geographic location region). As illustrated in FIG. 4, the acquisition unit 11 acquires a first map image rp1 including a first POI from the map image storage unit 30 (method for encoding a geographic location region). For example, the first map image rp1 includes a plurality of layers such as terrain information rp11, genre information rp12, and a road map rp13. The acquisition unit 11 acquires a second map image rp2 including a second POI from the map image storage unit 30. For example, the second map image rp2 includes a plurality of layers such as terrain information rp21, genre information rp22, and a road map rp23. Oonishi, Figs 1,3-6, para 45, 46-48.), comprising:
determining a to-be-encoded geographic location region (i.e., FIG. 4 is a diagram schematically illustrating an example in which a feature vector indicating geographical features of a POI is generated. As illustrated in FIG. 4, the acquisition unit 11 acquires a first map image rp1 including a first POI from the map image storage unit 30 (determining a to-be-encoded geographic location region). For example, the first map image rp1 includes a plurality of layers such as terrain information rp11, genre information rp12, and a road map rp13. The acquisition unit 11 acquires a second map image rp2 including a second POI from the map image storage unit 30. For example, the second map image rp2 includes a plurality of layers such as terrain information rp21, genre information rp22, and a road map rp23. Oonishi, Figs 1,3-6, para 45, 46-48.);
acquiring at least one kind of geographic function information and at least one kind of surface-feature distribution information of the geographic location region (i.e., FIG. 4 is a diagram schematically illustrating an example in which a feature vector indicating geographical features of a POI is generated. As illustrated in FIG. 4, the acquisition unit 11 acquires a first map image rp1 including a first POI from the map image storage unit 30. For example, the first map image rp1 includes a plurality of layers such as terrain information rp11, genre information rp12, and a road map rp13 (acquiring at least one kind of geographic function information (POI geographic function information) and at least one kind of surface-feature distribution information (terrain, genre, road surface-feature distribution information) of the geographic location region (of the map image geographical location region)). The acquisition unit 11 acquires a second map image rp2 including a second POI from the map image storage unit 30. For example, the second map image rp2 includes a plurality of layers such as terrain information rp21, genre information rp22, and a road map rp23. Oonishi, Figs 1,3-6, para 45, 46-48).; and
inputting the acquired geographic function information and the acquired surface-feature distribution information into an encoding model, the encoding model performing embedding on the geographic function information and the surface-feature distribution information, and
Oonishi teaches that, FIG. 4 is a diagram schematically illustrating an example in which a feature vector indicating geographical features of a POI is generated (inputting the acquired geographic function information (POI geographical function information) and the acquired surface-feature distribution information (terrain, genre, road surface-feature distribution information) into an encoding model (geographical feature vector generation encoding model, Fig 4, para 46-48), the encoding model performing embedding on the geographic function information and the surface-feature distribution information, and fusing vector representations obtained by the embedding to obtain an encoding result of the geographic location region (the geographical feature vector generation encoding model, Fig 4, para 46-48, performing encoding on the geographical function POI information and the terrain, genre, road surface feature distribution information and generating vector representations obtained by the embedding to obtain an encoding result of the geographical map image location region)). As illustrated in FIG. 4, the acquisition unit 11 acquires a first map image rp1 including a first POI from the map image storage unit 30. For example, the first map image rp1 includes a plurality of layers such as terrain information rp11, genre information rp12, and a road map rp13. The acquisition unit 11 acquires a second map image rp2 including a second POI from the map image storage unit 30. For example, the second map image rp2 includes a plurality of layers such as terrain information rp21, genre information rp22, and a road map rp23. Oonishi,