DETAILED ACTION
Amendment received 4 May 2026 is acknowledged. Claims 1 and 3-19 amended 4 May 2026 are pending and have been considered as follows.
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:
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;
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
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 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 is: “storage module configured to store” in Claim 1.
Because this claim limitation is being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it is 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 limitation 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 to avoid it 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 recites sufficient structure to perform the claimed function so as to avoid it being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 13-19 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
As per Claim 13, “wherein computing the ETA of each candidate route through the ETA prediction module” in line 8-9 does not clearly relate to the method steps in line 3-5 in that these methods do not necessarily involve “computing the ETA of each candidate route” as per line 8-9. Clarification is required. Claims 14-19 depending from Claim 13 are therefore rejected.
As per Claim 13, “each candidate route” in line 8 and 10 lacks proper antecedent basis. Clarification is required. Claims 14-19 depending from Claim 13 are therefore rejected.
As per Claim 13, “the candidate routes” in line 11 lacks proper antecedent basis. Clarification is required. Claims 14-19 depending from Claim 13 are therefore rejected.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1 and 3-19 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Huang (WO 2021/218131 A1; citations to US Pub. No. 2023/0154327).
As per Claim 1, Huang discloses an apparatus (101, 103, 104; Fig. 7) for searching for a route (as per S to F in Fig. 5) using estimated time of arrival prediction (as per “Arrived before” in Fig. 5) based on a graph neural network (as per “GCN” in ¶44, 48-50, 54, 57-59), the apparatus (101, 103, 104; Fig. 7) comprising:
a storage module (104; 702) configured to store digital map data (as per “the server 104 may collect and maintain, in advance, user trajectory data uploaded by the terminal devices … and these data my constitute traffic flow feature data of a road network” in ¶33; as per “the storage data region may store data created according to the use of the electronic device” in ¶147) (Figs. 1, 7; ¶30-35, 143-147); and
a processor (104; 701) configured to perform a route search (as per “the apparatus for route planning is disposed in and runs in the server 104” in ¶33; as per “The processor 701 … implements the method for route planning” in ¶146) based on an ETA prediction model (as per determination of “estimated arrival time” in ¶114-115, 141) according to a route exploration request (as per “When the user inputs a starting position and a finishing position to perform route planning” in ¶87) (Figs. 1-2, 5, 7; ¶30-41, 86-87, 111-116, 143-146),
wherein the ETA prediction model (as per determination of “estimated arrival time” in ¶114-115, 141) is generated based on a graph neural network (as per “GCN” in ¶44, 48-50, 54, 57-59) formed by converting (as per “To fit an association relationship between different road segments, the association relationship may be built using the GCN, and vector representations obtained from the encoding and a road network link relationship are input to the GCN. The vector representations output by the GCN may be concatenated with the road attribute feature data and the environment feature data in the second historical time slice and then input to the fully-connected layer. The fully-connected layer obtains the predicted passage duration on the road segment in the second historical time slice” in ¶48) road information (as per “road segments” in ¶48) into a graph (as per “Graph Convolutional Network” in ¶44; as per “a mesh-like topological diagram is built from all road segments on the road network” in ¶87) (Figs. 1-3, 5; ¶30-50, 54, 57-59, 86-87, 111-116, 141), and
wherein the ETA prediction model (as per determination of “estimated arrival time” in ¶114-115, 141) is generated (as per “At 203, route planning is performed” in ¶86, as per “if the planned route recommended to the user includes a road segment with a congested state change risk, a second estimated arrival time of the route may be determined using a predicted passage duration of the road segment including the congested state change risk; an interval of the estimated arrival time of the road segment is displayed using a first estimated arrival time determined when the congested state change risk is not considered, and the second estimated arrival time” in ¶114) by converting a link of road information (as per “road segments” in ¶48) into a node (as per “Nodes in the topological diagram are crossings” in ¶87) of a graph (as per “a mesh-like topological diagram is built from all road segments on the road network” in ¶87) and converting connectivity between links into edges (as per “edges are road segments” in ¶87) of the graph (as per “a mesh-like topological diagram is built from all road segments on the road network” in ¶87).
As per Claim 3, Huang further discloses wherein the ETA prediction model (as per determination of “estimated arrival time” in ¶114-115, 141) is generated based on a graph neural network (as per “GCN” in ¶44, 48-50, 54, 57-59) including features (as per “user data trajectory data uploaded by the terminal devices … during use of the map-like application and traffic flow data uploaded by various traffic sensors, and these data my constitute traffic flow feature data of a road network” in ¶33) of the route (as per S to F in Fig. 5) as global attributes (as per “The obtained traffic flow feature data” in ¶39.
As per Claim 4, Huang further discloses wherein a feature of the node (as per “Nodes in the topological diagram are crossings” in ¶87) of the graph (as per “a mesh-like topological diagram is built from all road segments on the road network” in ¶87) includes information (as per “The obtained traffic flow feature data may include one of or any combination of traffic flow statistics data, speed data and times of sudden deceleration on the road segments” in ¶39) on a past speed or a passage time of a link (as per “road segments” in ¶48) corresponding to a node (as per “Nodes in the topological diagram are crossings” in ¶87) of the graph (as per “a mesh-like topological diagram is built from all road segments on the road network” in ¶87).
As per Claim 5, Huang further discloses wherein a weight (as per “weighting coefficients” in ¶84) configured to predict a value (as per weighted risk coefficients in ¶82-84) that is greater (as per “manually-set empirical value or experimental value” in ¶84 that is revised upward) than a predicted value that is smaller (as per “manually-set empirical value or experimental value” in ¶84 before being revised upward) than a correct answer (as per updated weight in ¶90-94), and
wherein the weight (as per “weighting coefficients” in ¶84) is configured to be applied (as per “route planning is performed using the state change risk information of the route segments” in ¶86 and “if the planned route recommended to the user includes a road segment with a congested state change risk, a second estimated arrival time of the route may be determined using a predicted passage duration of the road segment including the congested state change risk; an interval of the estimated arrival time of the road segment is displayed using a first estimated arrival time determined when the congested state change risk is not considered, and the second estimated arrival time” in ¶114) to the ETA prediction model (as per determination of “estimated arrival time” in ¶114-115, 141).
As per Claim 6, Huang further discloses wherein a weight (as per “weighting coefficients” in ¶84) is configured to increase an influence of a preset time zone (as per effect of weight on each risk coefficient of each segment in ¶78-84) on an output value of the ETA prediction model (as per determination of “estimated arrival time” in ¶114-115, 141), and
wherein the weight (as per “weighting coefficients” in ¶84) is configured to be applied (as per “route planning is performed using the state change risk information of the route segments” in ¶86 and “if the planned route recommended to the user includes a road segment with a congested state change risk, a second estimated arrival time of the route may be determined using a predicted passage duration of the road segment including the congested state change risk; an interval of the estimated arrival time of the road segment is displayed using a first estimated arrival time determined when the congested state change risk is not considered, and the second estimated arrival time” in ¶114) to the ETA prediction model (as per determination of “estimated arrival time” in ¶114-115, 141).
As per Claim 7, Huang further discloses wherein the processor (104; 701) is further configured to:
compute a plurality of candidate routes (as per “The candidate routes obtained by looking up are sorted” in ¶87; as per “obtain at least one candidate route” in ¶94) according to a route search request (as per “When the user inputs a starting position and a finishing position to perform route planning” in ¶87); and
compute an ETA (as per “sorted according to any one of or any combination of a plurality of dimensions such as passage duration” in ¶87) of each candidate route (as per “The candidate routes obtained by looking up are sorted” in ¶87; as per “obtain at least one candidate route” in ¶94) through the ETA prediction model (as per determination of “estimated arrival time” in ¶114-115, 141).
As per Claim 8, Huang further discloses wherein the processor (104; 701) is further configured to compute a cost of each candidate route (as per “The candidate routes obtained by looking up are sorted” in ¶87; as per “obtain at least one candidate route” in ¶94) based on the computed ETA (as per “sorted according to any one of or any combination of a plurality of dimensions such as passage duration” in ¶87) of each candidate route (as per “The candidate routes obtained by looking up are sorted” in ¶87; as per “obtain at least one candidate route” in ¶94).
As per Claim 9, Huang discloses a method (Fig. 2) of generating an estimated time of arrival prediction model (as per determination of “estimated arrival time” in ¶114-115, 141), the method comprising:
converting, by a processor (104; 701), links of road information (as per “road segments” in ¶48) into nodes (as per “Nodes in the topological diagram are crossings” in ¶87) into nodes and converting connectivity between the links into edges (as per “edges are road segments” in ¶87) of a graph (as per “a mesh-like topological diagram is built from all road segments on the road network” in ¶87) to convert the road information (as per “road segments” in ¶48) into the graph (as per “a mesh-like topological diagram is built from all road segments on the road network” in ¶87);
inserting, by the processor (104; 701), related data into a global attribute (as per “The obtained traffic flow feature data” in ¶39) of the graph (as per “a mesh-like topological diagram is built from all road segments on the road network” in ¶87), a node attribute (as per “user data trajectory data uploaded by the terminal devices … during use of the map-like application and traffic flow data uploaded by various traffic sensors, and these data my constitute traffic flow feature data of a road network” in ¶33 for each “Nodes in the topological diagram are crossings” in ¶87) of the graph (as per “a mesh-like topological diagram is built from all road segments on the road network” in ¶87), and an edge attribute as per “user data trajectory data uploaded by the terminal devices … during use of the map-like application and traffic flow data uploaded by various traffic sensors, and these data my constitute traffic flow feature data of a road network” in ¶33 for each “edges are road segments” in ¶87) of the graph (as per “a mesh-like topological diagram is built from all road segments on the road network” in ¶87); and
learning (as per “training data is obtained” in ¶45), by the processor (104; 701), an ETA prediction model (as per determination of “estimated arrival time” in ¶114-115, 141) by using the global attribute (as per “The obtained traffic flow feature data” in ¶39) of the graph (as per “a mesh-like topological diagram is built from all road segments on the road network” in ¶87), the node attribute (as per “user data trajectory data uploaded by the terminal devices … during use of the map-like application and traffic flow data uploaded by various traffic sensors, and these data my constitute traffic flow feature data of a road network” in ¶33 for each “Nodes in the topological diagram are crossings” in ¶87) of the graph (as per “a mesh-like topological diagram is built from all road segments on the road network” in ¶87), and the edge attribute (as per “user data trajectory data uploaded by the terminal devices … during use of the map-like application and traffic flow data uploaded by various traffic sensors, and these data my constitute traffic flow feature data of a road network” in ¶33 for each “edges are road segments” in ¶87) of the graph (as per “a mesh-like topological diagram is built from all road segments on the road network” in ¶87) as input values (Figs. 2-3, 5; ¶36-51, 86-105, 111-116).
As per Claim 10, Huang further discloses wherein:
the global attribute (as per “The obtained traffic flow feature data” in ¶39) of the graph (as per “a mesh-like topological diagram is built from all road segments on the road network” in ¶87) includes past ETA information (as per historical information of the road segments in the road network” in ¶45) for a route (as per “user trajectory data uploaded by the terminal devices … during use of the map-like application” in ¶33);
the node attribute (as per “user data trajectory data uploaded by the terminal devices … during use of the map-like application and traffic flow data uploaded by various traffic sensors, and these data my constitute traffic flow feature data of a road network” in ¶33 for each “Nodes in the topological diagram are crossings” in ¶87) of the graph (as per “a mesh-like topological diagram is built from all road segments on the road network” in ¶87) includes information (as per “The obtained traffic flow feature data may include one of or any combination of traffic flow statistics data, speed data and times of sudden deceleration on the road segments” in ¶39) on a past speed or a passage time of a link (as per “road segments” in ¶48) corresponding to a node (as per “Nodes in the topological diagram are crossings” in ¶87) of the graph (as per “a mesh-like topological diagram is built from all road segments on the road network” in ¶87); and
the edge attribute (as per “user data trajectory data uploaded by the terminal devices … during use of the map-like application and traffic flow data uploaded by various traffic sensors, and these data my constitute traffic flow feature data of a road network” in ¶33 for each “edges are road segments” in ¶87) of the graph (as per “a mesh-like topological diagram is built from all road segments on the road network” in ¶87) includes information on connectivity (as per “factors for making the road segment impassible” in ¶61) between the nodes (as per “Nodes in the topological diagram are crossings” in ¶87) and information on whether a road type is changed (as per “The road attribute feature data may include information such as a length and a road class of the road segment” in ¶56).
As per Claim 11, Huang further discloses outputting, by the ETA prediction model (as per determination of “estimated arrival time” in ¶114-115, 141), a link passage time (as per “Less than 40 minutes” in Fig. 5) as an output value (Fig. 5).
As per Claim 12, Huang further discloses outputting, by the ETA prediction model (as per determination of “estimated arrival time” in ¶114-115, 141), ETA values (as per “Arrived before” in Fig. 5) for a route (Fig. 5).
As per Claim 13, Huang discloses a method (Fig. 2) of searching for a route (as per S to F in Fig. 5) using estimated time of arrival prediction (as per “Arrived before” in Fig. 5) based on a graph neural network (as per “GCN” in ¶44, 48-50, 54, 57-59), the method (Fig. 2) comprising:
receiving, by a processor (104; 701), a route search request (as per “When the user inputs a starting position and a finishing position to perform route planning” in ¶87) (Figs. 1-2, 5, 7; ¶30-41, 86-87, 111-116, 143-146);
performing, by the processor (104; 701), route search (as per “the apparatus for route planning is disposed in and runs in the server 104” in ¶33; as per “The processor 701 … implements the method for route planning” in ¶146) based on an ETA prediction model (as per determination of “estimated arrival time” in ¶114-115, 141) (Figs. 1-2, 5, 7; ¶30-41, 86-87, 111-116, 143-146); and
providing, the processor (104; 701), a route search result (as per 204; as per Fig. 5) (Figs. 1-2, 5, 7; ¶30-41, 86-87, 106-116, 143-146),
wherein the ETA prediction model (as per determination of “estimated arrival time” in ¶114-115, 141) is generated based on a graph neural network (as per “GCN” in ¶44, 48-50, 54, 57-59) formed by converting (as per “To fit an association relationship between different road segments, the association relationship may be built using the GCN, and vector representations obtained from the encoding and a road network link relationship are input to the GCN. The vector representations output by the GCN may be concatenated with the road attribute feature data and the environment feature data in the second historical time slice and then input to the fully-connected layer. The fully-connected layer obtains the predicted passage duration on the road segment in the second historical time slice” in ¶48) road information (as per “road segments” in ¶48) into a graph (as per “Graph Convolutional Network” in ¶44; as per “a mesh-like topological diagram is built from all road segments on the road network” in ¶87) (Figs. 1-3, 5; ¶30-50, 54, 57-59, 86-87, 111-116, 141), and
wherein computing the ETA (as per “sorted according to any one of or any combination of a plurality of dimensions such as passage duration” in ¶87) of each candidate route (as per “The candidate routes obtained by looking up are sorted” in ¶87; as per “obtain at least one candidate route” in ¶94) through the ETA prediction model (as per determination of “estimated arrival time” in ¶114-115, 141) includes:
converting, by the processor (104; 701), each candidate route (as per “The candidate routes obtained by looking up are sorted” in ¶87; as per “obtain at least one candidate route” in ¶94) into a respective graph (as per “a mesh-like topological diagram is built from all road segments on the road network” in ¶87) by converting links (as per “road segments” in ¶48) of the candidate routes (as per “The candidate routes obtained by looking up are sorted” in ¶87; as per “obtain at least one candidate route” in ¶94) into nodes (as per “Nodes in the topological diagram are crossings” in ¶87) of the graph (as per “a mesh-like topological diagram is built from all road segments on the road network” in ¶87) and by converting connectivity between the links into edges (as per “edges are road segments” in ¶87) of the graph (as per “a mesh-like topological diagram is built from all road segments on the road network” in ¶87).
As per Claim 14, Huang further discloses wherein performing the route search (as per “the apparatus for route planning is disposed in and runs in the server 104” in ¶33; as per “The processor 701 … implements the method for route planning” in ¶146) includes:
computing, by the processor (104; 701), a plurality of candidate routes (as per “The candidate routes obtained by looking up are sorted” in ¶87; as per “obtain at least one candidate route” in ¶94) in response to the route search request (as per “When the user inputs a starting position and a finishing position to perform route planning” in ¶87); and
computing, by the processor (104; 701), an ETA (as per “sorted according to any one of or any combination of a plurality of dimensions such as passage duration” in ¶87) of each candidate route (as per “The candidate routes obtained by looking up are sorted” in ¶87; as per “obtain at least one candidate route” in ¶94) through the ETA prediction model (as per determination of “estimated arrival time” in ¶114-115, 141).
As per Claim 15, Huang further discloses wherein performing the route search (as per “the apparatus for route planning is disposed in and runs in the server 104” in ¶33; as per “The processor 701 … implements the method for route planning” in ¶146) further includes computing, by the processor (104; 701), a cost of each candidate route (as per “The candidate routes obtained by looking up are sorted” in ¶87; as per “obtain at least one candidate route” in ¶94) based on the computed ETA (as per “sorted according to any one of or any combination of a plurality of dimensions such as passage duration” in ¶87) of each candidate route (as per “The candidate routes obtained by looking up are sorted” in ¶87; as per “obtain at least one candidate route” in ¶94).
As per Claim 16, Huang further discloses wherein computing the ETA (as per “sorted according to any one of or any combination of a plurality of dimensions such as passage duration” in ¶87) of each candidate route (as per “The candidate routes obtained by looking up are sorted” in ¶87; as per “obtain at least one candidate route” in ¶94) through the ETA prediction model (as per determination of “estimated arrival time” in ¶114-115, 141) includes:
calculating, by the processor (104; 701), an ETA (as per “sorted according to any one of or any combination of a plurality of dimensions such as passage duration” in ¶87) of each candidate route (as per “The candidate routes obtained by looking up are sorted” in ¶87; as per “obtain at least one candidate route” in ¶94) through the ETA prediction model (as per determination of “estimated arrival time” in ¶114-115, 141) by inputting data related to a global attribute (as per “The obtained traffic flow feature data” in ¶39) of the graph (as per “a mesh-like topological diagram is built from all road segments on the road network” in ¶87), a node attribute (as per “user data trajectory data uploaded by the terminal devices … during use of the map-like application and traffic flow data uploaded by various traffic sensors, and these data my constitute traffic flow feature data of a road network” in ¶33 for each “Nodes in the topological diagram are crossings” in ¶87) of the graph (as per “a mesh-like topological diagram is built from all road segments on the road network” in ¶87), and an edge attribute (as per “user data trajectory data uploaded by the terminal devices … during use of the map-like application and traffic flow data uploaded by various traffic sensors, and these data my constitute traffic flow feature data of a road network” in ¶33 for each “edges are road segments” in ¶87) of the graph (as per “a mesh-like topological diagram is built from all road segments on the road network” in ¶87) as input values (Figs. 2-3, 5; ¶36-51, 86-105, 111-116).
As per Claim 17, Huang further discloses wherein:
the global attribute (as per “The obtained traffic flow feature data” in ¶39) of the graph (as per “a mesh-like topological diagram is built from all road segments on the road network” in ¶87) includes past ETA information (as per historical information of the road segments in the road network” in ¶45) on the route (as per “user trajectory data uploaded by the terminal devices … during use of the map-like application” in ¶33);
the node attribute (as per “user data trajectory data uploaded by the terminal devices … during use of the map-like application and traffic flow data uploaded by various traffic sensors, and these data my constitute traffic flow feature data of a road network” in ¶33 for each “Nodes in the topological diagram are crossings” in ¶87) of the graph (as per “a mesh-like topological diagram is built from all road segments on the road network” in ¶87) includes information (as per “The obtained traffic flow feature data may include one of or any combination of traffic flow statistics data, speed data and times of sudden deceleration on the road segments” in ¶39) on a past speed or a passage time of a link (as per “road segments” in ¶48) corresponding to a node (as per “Nodes in the topological diagram are crossings” in ¶87) of the graph (as per “a mesh-like topological diagram is built from all road segments on the road network” in ¶87); and
the edge attribute (as per “user data trajectory data uploaded by the terminal devices … during use of the map-like application and traffic flow data uploaded by various traffic sensors, and these data my constitute traffic flow feature data of a road network” in ¶33 for each “edges are road segments” in ¶87) of the graph (as per “a mesh-like topological diagram is built from all road segments on the road network” in ¶87) includes information on connectivity (as per “factors for making the road segment impassible” in ¶61) between the nodes (as per “Nodes in the topological diagram are crossings” in ¶87) and information on whether a road type is changed (as per “The road attribute feature data may include information such as a length and a road class of the road segment” in ¶56).
As per Claim 18, Huang further discloses predicting, by a weight (as per “weighting coefficients” in ¶84), a value (as per weighted risk coefficients in ¶82-84) that is greater (as per “manually-set empirical value or experimental value” in ¶84 that is revised upward ) than a predicted value that is smaller (as per “manually-set empirical value or experimental value” in ¶84 before being revised upward) than a correct answer (as per updated weight in ¶90-94); and
applying (as per “route planning is performed using the state change risk information of the route segments” in ¶86 and “if the planned route recommended to the user includes a road segment with a congested state change risk, a second estimated arrival time of the route may be determined using a predicted passage duration of the road segment including the congested state change risk; an interval of the estimated arrival time of the road segment is displayed using a first estimated arrival time determined when the congested state change risk is not considered, and the second estimated arrival time” in ¶114) the weight (as per “weighting coefficients” in ¶84) to the ETA prediction model (as per determination of “estimated arrival time” in ¶114-115, 141).
As per Claim 19, Huang further discloses increasing, by a weight (as per “weighting coefficients” in ¶84), an influence of a preset time zone (as per effect of weight on each risk coefficient of each segment in ¶78-84) on an output value of the ETA prediction model (as per determination of “estimated arrival time” in ¶114-115, 141); and
applying (as per “route planning is performed using the state change risk information of the route segments” in ¶86 and “if the planned route recommended to the user includes a road segment with a congested state change risk, a second estimated arrival time of the route may be determined using a predicted passage duration of the road segment including the congested state change risk; an interval of the estimated arrival time of the road segment is displayed using a first estimated arrival time determined when the congested state change risk is not considered, and the second estimated arrival time” in ¶114) the weight (as per “weighting coefficients” in ¶84) to the ETA prediction model (as per determination of “estimated arrival time” in ¶114-115, 141).
Response to Arguments
Applicant's arguments filed 4 May 2026 have been fully considered as follows.
Applicant argues that the claim interpretation under 35 USC 112(f) should not be maintained because “the term ‘storage module’ strongly implies or directly denotes the structure and components that perform specific functions as recited in the claims” in that “the ‘storage module’ is used in an apparatus for searching for a route using estimated time of arrival (ETA) prediction and configured to store digital map data” and “Thus, a person having ordinary skill in the art would readily recognize the structure of the storage module, which are for performing the above functions” (page 7 of Amendment).
However, “module” is a non-structural generic placeholder, the generic placeholder is modified by the functional language “configured to”, and the claim language is not modified by any structure, material, or acts for performing the function of “to store” (see MPEP § 2181). Applicant’s assertions that the term “strongly implies or directly denotes the structure and components that perform specific functions as recited in the claims” and that “a person having ordinary skill in the art would readily recognize the structure of the storage module, which are for performing the above functions” are not consistent with the claim language at issue and rely on evidence where no evidence has been presented.
Applicant has neither amended the claim limitation to avoid the claim interpretation under 35 USC 112(f) nor presented a sufficient showing. Accordingly, the claim interpretation under 35 USC 112(f) is maintained.
Applicant argues that the claim interpretation under 35 USC 112(f) should not be maintained because “none of these limitations use the term ‘means for’ or ‘step for’” and “Thus, since the term is not used, the rebuttable presumption is that 35 U.S.C. § 112(f) does not apply” (page 7 of Amendment). However, the claim interpretation under 35 USC 112(f) does not involve an assertion that the claim language at issue recites “means for” or “step for”. Accordingly, Applicant’s argument is irrelevant.
Applicant argues regarding the rejections under 35 USC 102 (page 7-9 of Amendment):
The cited reference fails to teach or suggest the apparatus for searching for a route using estimated time of arrival (ETA) prediction based on a graph neural network of independent claim 1. Specifically, amended independent claim 1 now recites, from original claim 2, "wherein the ETA prediction model is generated by converting a link of road information into a node of a graph and converting connectivity between links into edges of the graph."
Huang merely discloses predicting state-change risks of road segments, such as congestion risk, accident risk, passability risk, traffic rule change risk, and road quality deterioration risk, and then reflecting such predicted risk information in route planning. See Huang, paragraph [0041]. Although Huang uses a GCN in certain prediction models, the GCN of Huang is used to predict a state-change risk, and the route planning is then performed by using the predicted risk information. This is different from the subject matter of claim 1.
By contrast, the subject matter of claim 1 is directed to an ETA prediction model itself, which is generated based on a graph neural network by converting road information into a graph in a specific manner. More specifically, the subject matter of claim 1 (i) converts links of road information into nodes of the graph ("the claimed conversion (i)") and (ii) converts connectivity between the links into edges of the graph ("the claimed conversion (ii)"). In the instant application, each road link can serve as a unit for ETA prediction, and attributes of each link, such as past speed, passage time, and other link-related information, may be assigned to a corresponding graph node. The connectivity between links is then modeled as graph edges. This configuration allows the GNN-based ETA prediction model to learn relationships among road links in a manner suitable for predicting ETA.
This "link-as-node" graph representation is a key technical feature of the instant application, because it enables road-link-based attributes, such as past speed or passage time of each link, to be handled as node attributes of the graph, while link-to-link relationships are handled as edge attributes. This graph representation is not merely a conventional road network topology, but rather a particular graph transformation designed for GNN-based ETA prediction.
Huang merely discloses that to fit an association relationship between different road segments, an association relationship may be built using the GCN, and vector representations obtained from the encoding and a road network link relationship are input to the GCN. See Huang, paragraph [0048]. In a route planning product, a mesh-like topological diagram is built from all road segments on the road network according to a mutual communication relationship. See Huang, paragraph [0087]. Nodes in the topological diagram are crossings and edges are road segments. See Huang, paragraph [0087].
Therefore, Huang merely discloses a conventional road-network graph, used for route planning, and in the conventional road-network graph, intersections or crossings are represented as nodes, and road segments are represented as edges.
However, Huang is silent on converting the road segments (alleged as equivalent to the claimed link, See the Office action, page 6) into crossings (alleged as equivalent to the claimed node, See the Office action, page 6) for the generation of the ETA prediction model. Instead, in view of paragraph [0087] of Huang, Huang treats the road segments as edges, and treats the crossing as nodes. Therefore, Huang fails to teach or suggest the claimed conversion (i), i.e., the claimed link-as-node graph representation used to generate the GNN-based ETA prediction model.
In addition, Huang is silent on converting connectivity between the road segments (alleged as equivalent to the claimed link) into edges of the graph for the generation of the ETA prediction model. Instead, in view of paragraph [0087] of Huang, Huang treats the road segments as edges. Therefore, Huang fails to teach or suggest the claimed conversion (ii). Other cited paragraphs [0044], [0048], [0050], [0054], and [0057]-[0059] do not cure the above noted deficiencies. These paragraphs merely describe using a GCN with a road network link relationship matrix to predict passage duration or accident occurrence probability. However, these paragraphs is silent on converting road links into graph nodes and converting connectivity between the links into graph edges. Merely using a GCN in Huang is insufficient to teach or suggest the specific graph-conversion limitations of the present claims.
For the reasons stated above, Huang fails to teach or suggest "wherein the ETA prediction model is generated by converting a link of road information into a node of a graph and converting connectivity between links into edges of the graph," as recited by claim 1.
However, Applicant’s assertion that Huang “fails to teach or suggest … the subject matter of claim 1” involves a description of the claimed invention that does not correspond to the claim language. As examples, no claim recites as per Applicant’s description of the claimed subject matter: “an ETA prediction model itself”, “each road link can serve as a unit for ETA prediction”, “attributes of each link”, “past speed”, “passage time”, “other link-related information”, “assigned to a corresponding graph node”, “learn relationships among road links”, “link-as-node graph”, “road-link-based attributes”, “past speed or passage time of each link”, “node attributes of the graph”, “link-to-link relationships”, or “edge attributes”. Accordingly, Applicant’s assertions regarding the rejections rely on unclaimed embodiments and are not clearly connected to the claim language. As such, Applicant’s arguments involve an improper interpretation of the claim language at issue. Therefore, Applicant’s arguments do not identify a proper basis for finding that any rejection is improper.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Yoshizumi (US Pub. No. 2013/0238242) discloses a route selection system, method and program. Sykora (US Pub. No. 2021/0248460) discloses systems and methods for optimized multi-agent routing between nodes. Kim (US Pub. No. 2021/0302180) discloses an optimal route searching device and operation method thereof. Davies (US Pub. No. 2021/0326699) discloses travel speed prediction.
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to STEPHEN HOLWERDA whose telephone number is (571)270-5747. The examiner can normally be reached M-F 8am - 4:30pm.
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, KHOI TRAN can be reached at (571) 272-6919. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/STEPHEN HOLWERDA/Primary Examiner, Art Unit 3656
Prosecution Insights