DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Continued Examination Under 37 CFR 1.114
2. A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 2/05/2026 has been entered.
Accordingly, claims 1-20 are pending in this application. Claims 1, 14, and 15 are currently amended.
Response to Arguments
Applicant’s arguments with respect to amended pending claims filed on 2/05/2026 have been fully considered. In view of the claim amendment filed, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made.
Further, regarding the new limitations recited in claims 1, 14, and 15, it is submitted that they are properly addressed by the new ground of rejection.
Furthermore, it is also submitted that all limitations in pending claims, including those not specifically argued, are properly addressed. The reason is set forth in the rejections. See claim analysis below for detail.
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.
4. 1-20 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The claims recite a process of generating a user interest representation of the user (e.g. obtaining a historical content item sequence of a user and identifying a topic and a text of each historical content item as recited in claim 1) and for the intention of performing different processes (e.g. generating a comprehensive topic representation and generating a comprehensive text representation as recited in claim 1).
The claimed process is similar to a method of mental processes, particularly concepts performed in the human minds (including an observation, evaluation, judgement, opinion), which is one of the groupings of abstract ideas according to Prong One in Step 2A of the 2019 Patent Subject Matter Eligibility Guidance since the steps of generating data, which allows processes such as sharing information--are directed to a series of thought processes (i.e. mental processes).
Also this judicial exception is not integrated into a practical application because generating data is merely indicating allowing processes (e.g. sharing process) to happen, which does not mean the process of sharing data will actually occur and result in a practical application.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. Additional elements (e.g. a graph, an aggregation of textual contents) are directed to types of information being manipulated. The types of information being manipulated does not impose a meaningful limit on the judicial exception, such that the claims are more than a drafting effort design to monopolize exception, because the claimed steps could be performed in a same manner to achieve the same outcome with other types of information other than the ones being used in the claims.
The additional processes (e.g. determining categories, setting categories into nodes, determining edges, determining a transition direction) are not being integrated into a practical application.
Hence, the claims do not include additional elements or the combination of the elements are sufficient to amount to significantly more than the judicial exception and fail to integrate the judicial exception into practical application according to Prong Two in Step 2A of the 2019 Patent Subject Matter Eligibility Guidance because the claimed elements or the combination do not impose any meaningful limits on practicing the abstract idea.
Further, in view of Step 2B of the 2019 Patent Subject Matter Eligibility Guidance, it is determined that the computing elements (such as an apparatus comprising: at least one processor; and a memory storing computer-executable instructions) in the claim amount to no more than usage of a generic computing system having generic computing components-- such as a processor-of a generic network, which fails to provide an inventive concept or significantly more than an abstract idea because the elements do not necessary improve the functional of a computing system or an improvement to a technical field since network computing is well known.
Thus, for at least the reasoning above, the pending claims are not patent eligible.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Dongho et al. ("News Recommendation with Topic-Enriched Knowledge Graphs", Proceedings of the 7th ACM Conference on Information- Centric Networking, Acmpub27, 19 October 2020 (2020-10-19), pages 695-704) in view of Chatterjee et al. (US 20210097140 A1) and Mao et al. (“Neural News Recommendation with Collaborative News Encoding and Structural User Encoding”, ARXIV.org, (2021-09-02)).
Regarding Claim 1, Dongho discloses a method for hierarchical representation learning of user interest ([Page 695, Introduction]: Thus, it is essential for users to automatically receive personalized recommendations based on their interests;[Page 701]: LSTUR[1]is a neural news recommendation method that can learn both long and short-term user representations through a news encoder and user encode), comprising:
obtaining a historical content item sequence of a user (Fig. 3; [Page 696]: we propose a Topic-Enriched Knowledge Graph Recommendation System (TEKGR)… which takes a piece of candidate news and a user’s click history as input; [Page 701, section 4.2]: we denote user i's clicked history);
identifying a topic and a text of each historical content item in the historical content item sequence, to obtain a topic sequence and a text sequence corresponding to the historical content item sequence (Fig. 3; [Page 699, sections 4.1.1. - 4.1.3]: The knowledge encoder also has three layers to learn topical information on the news title… The goal of Topic Enhanced KG Construction is to consider contextual knowledge information along with topical information for the recommendation system… Word embedding, the first layer, converts a news title from a sequence of words to a sequence of dense semantic vectors);
generating a comprehensive topic representation based on the topic sequence ([Page 700, secti
ons 4.1.2 and 4.1.3, page 701 left-hand column first full paragraph]: In general, short texts are mapped in implicit spaces and are represented as dense vectors… representations from the ... KG-level news encoder; Fig. 4, right-hand side);
generating a comprehensive text representation based on the text sequence ([Page 699, section 4.1.1, page 701 left-hand column first full paragraph]: We concatenate the concept vector with a news representation vector (from Word-level News Encoder) to extract the topic information vector, Fig 4, left-hand side); and
generating a user interest representation of the user based on the comprehensive topic representation and the comprehensive text representation (Fig. 4, left-hand side; [Page 699, section 4.1.1, page 701 left-hand column first full paragraph]: As shown in Figure 4, the KG-based news modeling layer has three encoders to extract the news representation vector… For example, a user with a huge interest…. would click…news titles that have financial terms in them… we can obtain the final representation of a news title in word-level news encoder).
However, Dongho does not explicitly teach “wherein the topic representation is a graph constructed from the topic sequence, the graph includes a plurality of nodes representing topic categories from the topic sequence, the graph includes edges between nodes representing sequential transitions between corresponding topic categories in the topic sequence, and the edges encode transition information derived from an order in which the user accessed content items of different topic categories in the historical content item sequence; wherein the comprehensive text representation is an aggregation of textual contents of historical content items in the historical content item sequence.”
On the other hand, in the same field of endeavor, Chatterjee teaches
wherein the topic representation is a graph constructed from the topic sequence (Fig. 5; [0005]: A system and method for the automated generation of a conversation graph representing a collection of conversations about a particular topic is disclosed. The system and method solve the problems discussed above by assigning various word sequences),
the graph includes a plurality of nodes representing topic categories from the topic sequence ([0005]: A system and method for the automated generation of a conversation graph representing a collection of conversations about a particular topic… resolution to a single conversation node; [0025]: A “node” in the graph can be extracted that represents the collection of word sequences that fall in the same dialogue act category),
the graph includes edges between nodes representing sequential transitions between corresponding topic categories in the topic sequence, ([0025]: In addition, the nodes will be connected to other nodes by an “edge” line, also referred to herein as a transitional path or transitional edge) and
the edges encode transition information derived from an order in which the user accessed content items of different topic categories in the historical content item sequence ([0108]: For example, because the conversation graph embeds utterance patterns for agents as a plurality of nodes and user utterances as a plurality of transitional paths or edges, it can be understood that the conversation graph implicitly encodes an agent's behavior based on user responses; as identified from historical chat log records);
Additionally, Mao teaches wherein the comprehensive text representation is an aggregation of textual contents of historical content items in the historical content item sequence ([Pages 47-50]: overall user representations can be aggregated by leveraging the correlation among interest clusters; [Pages 49-50]: refining specific user interest representations within clusters and aggregating overall user history information among clusters… With intra-cluster and inter-cluster attention, rinter hierarchically aggregates user interest representations within the cluster graph G).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teaching of Dongho to incorporate the teachings of Chatterjee and Mao to include the comprehensive topic representation as a graph, and the comprehensive text representation has an aggregation of textual contents of historical content items.
The motivation for doing so would be to classify the conversational intent of a conversation, as recognized by Chatterjee ([Abstract] of Chetterjee: The labeled clusters may be used to train a virtual agent to classify the conversational intent of a conversation), and to
learn hierarchical user interest representation to improve the performance of recommendations, as recognized by Mao ([Abstract] of Mao: SUE utilizes graph convolutional networks to extract cluster-structural features of user history, followed by intra-cluster and inter-cluster attention modules to learn hierarchical user interest representations. Experiment results on the MIND dataset validate the effectiveness of our model to improve the performance of news recommendation).
Regarding Claim 2, the combined teachings of Dongho, Chatterjee, and Mao disclose the method of claim 1.
Dongho further teaches wherein the comprehensive topic representation and the comprehensive text representation have different information abstraction levels ([Page 696]: Nevertheless, in addition to the title, our model is also feasible to use full article contents or abstracts of news. Note that our method can be simply utilized in any kind of recommendation scenario with short texts).
Regarding Claim 3, the combined teachings of Dongho, Chatterjee, and Mao disclose the method of claim 1.
Dongho further teaches wherein the generating a comprehensive topic representation comprises: generating a topic representation sequence corresponding to the topic sequence; constructing a topic graph corresponding to the topic sequence ([Page 696]: The KG-level news encoder constructs a topic-enriched subgraph from the entities of news titles by adding their 2-hop neighbors with topical relations, which are learned from knowledge encoder); and
generating the comprehensive topic representation based on the topic representation sequence and the topic graph ([Page 696]: After constructing the topic-enriched subgraph, we apply graph neural networks (GNNs) to get a news embedding vector).
Regarding Claim 4, the combined teachings of Dongho, Chatterjee, and Mao disclose the method of claim 3.
Dongho further teaches wherein the constructing a topic graph comprises:
determining a plurality of topic categories included in the topic sequence; setting the plurality of topic categories into a plurality of nodes ([Page 696]: The knowledge encoder uses the relational facts of KGs to extract the topics of a news title… Green nodes (Trump and Madonna) are the recognized entities connected with their 2-hop neighbor nodes);
determining a set of edges among the plurality of nodes; and combining the plurality of nodes and the set of edges into the topic graph ([Page 696]: The topical relation vector from the knowledge encoder is added between the entities… The KG-level news encoder constructs a topic-enriched subgraph from the entities of news titles… After constructing the topic-enriched subgraph, we apply graph neural networks (GNNs) to get a news embedding vector).
Regarding Claim 5, the combined teachings of Dongho, Chatterjee, and Mao disclose the method of claim 4.
Dongho further teaches wherein the determining a set of edges comprises, for every two nodes in the plurality of nodes:
determining whether there is a transition between two topic categories corresponding to the two nodes according to the topic sequence ([Page 696]: Figure 2 concisely illustrates the example subgraph of Figure 1. Green nodes (Trump and Madonna) are the recognized entities connected with their 2-hop neighbor nodes);
in response to determining that there is a transition between the two topic categories, determining a transition direction of the transition and a number of transitions corresponding to the transition direction; and determining a direction and a number of edges existing between the two nodes based on the determined transition direction and the determined number of transitions (Figs. 1-2; [Page 696]: The topical relation vector from the knowledge encoder is added between the entities to imply Politics topic exists between the entities… the topical relation can indicate that the two entities are appearing in the same news title; [Page 699]: Bidirectional GRU (Bi-GRU)[13], the second layer in the word-level news encoder, captures the contextual information of the sequence).
Regarding Claim 6, the combined teachings of Dongho, Chatterjee, and Mao disclose the method of claim 1.
Dongho further teaches wherein the generating a comprehensive text representation comprises:
generating a comprehensive text attention representation through an attention mechanism based on the text sequence ([Pages 695- 696]: After obtaining news representation vectors, an attention network compares clicked news to the candidate news in order to get the user’s final embedding… With extracted news representation, we use an attention layer to compare clicked news to the candidate news in order to get a user’s final embedding), and
the generating a user interest representation comprises: generating the user interest representation based on the comprehensive topic representation and the comprehensive text attention representation (Fig. 3; [Page 696, section 4.1.1]: With extracted news representation, we use an attention layer to compare clicked news to the candidate news in order to get a user’s final embedding).
Regarding Claim 7, the combined teachings of Dongho, Chatterjee, and Mao disclose the method of claim 1.
Dongho further teaches wherein the generating a comprehensive text representation comprises: generating a comprehensive text capsule representation using a capsule network based at least on the text sequence, and the generating a user interest representation comprises: generating the user interest representation based on the comprehensive topic representation and the comprehensive text capsule representation ([Page 696, section 4.1.1 and figure 3]: Since recurrent neural networks(RNN) is proved to be effective for sentence modeling[36], we apply Bi-GRU… Through summing contextual representations of words weighted by the attention weights, we can obtain the final representation of a news title in word-level news encoder; [The broad and undefined claimed terms "capsule network" and "text capsule representation" correspond to the network employed and the semantic vector calculated in section 4.1.1]).
Additionally, Mao teaches wherein the comprehensive text capsule representation is a group of neurons that output vectors, and wherein the capsule network models hierarchical relationships in the text sequence to generate the comprehensive text capsule representation ([Pages 47-48]: Based on this sequential formulation, recurrent neural networks…are proposed to encode user history… In recent years, deep neural models have achieved superior performance in news recommendation. Many studies pinpointed that this improvement came from the fine-grained news and user representations, which were extracted by deep neural networks… Concretely, we utilize the semantic memory vector).
Regarding Claim 8, the combined teachings of Dongho, Chatterjee, and Mao disclose the method of claim 1.
Dongho further teaches wherein the generating a comprehensive text representation comprises: generating a comprehensive text attention representation through an attention mechanism based on the text sequence; and generating a comprehensive text capsule representation using a capsule network based at least on the text sequence, and
the generating a user interest representation comprises: generating the user interest representation based on the comprehensive topic representation, the comprehensive text attention representation, and the comprehensive text capsule representation (Fig. 3; [Page 701]: Now that we obtain news representation vector from multiple encoders, we use an attention layer to compare clicked news to the candidate news in order to get the user’s final embedding).
Additionally, Mao teaches wherein the comprehensive text capsule representation is a group of neurons that output vectors, and wherein the capsule network models hierarchical relationships in the text sequence to generate the comprehensive text capsule representation ([Pages 47-48]: Based on this sequential formulation, recurrent neural networks…are proposed to encode user history… In recent years, deep neural models have achieved superior performance in news recommendation. Many studies pinpointed that this improvement came from the fine-grained news and user representations, which were extracted by deep neural networks… Concretely, we utilize the semantic memory vector).
Regarding Claim 9, the combined teachings of Dongho, Chatterjee, and Mao disclose the method of claim 8.
Dongho further teaches wherein the comprehensive text attention representation and the comprehensive text capsule representation have different information abstraction levels ([Page 696]: Nevertheless, in addition to the title, our model is also feasible to use full article contents or abstracts of news. Note that our method can be simply utilized in any kind of recommendation scenario with short texts).
Regarding Claim 10, the combined teachings of Dongho, Chatterjee, and Mao disclose the method of claim 7.
Dongho further teaches wherein the generating a comprehensive text capsule representation comprises:
generating an interest capsule representation using the capsule network based on the text sequence; generating a target content item representation of a target content item; and generating the comprehensive text capsule representation through an attention mechanism based on the interest capsule representation and the target content item representation (Fig. 3; [Page 701]: Now that we obtain news representation vector from multiple encoders, we use an attention layer to compare clicked news to the candidate news in order to get the user’s final embedding).
Regarding Claim 11, the combined teachings of Dongho, Chatterjee, and Mao disclose the method of claim 1.
Dongho further teaches further comprising: predicting a click probability of the user clicking a target content item based on the user interest representation and a target content item representation of the target content item ([Page 698, section 4.2 second paragraph]: Using users’ click history along with the link between words in the titles and entities in the knowledge graph, we aim to predict whether user 𝑖 has a potential interest in news title 𝑡 , which has not been clicked before).
Regarding Claim 12, the combined teachings of Dongho, Chatterjee, and Mao disclose the method of claim 11.
Dongho further teaches wherein the click probability is output through a click probability predicting model, and a training of the click probability predicting model comprises:
constructing a training dataset, the training dataset including a plurality of positive samples and a plurality of negative sample sets corresponding to the plurality of positive samples ([Page 701]: For experiments, we applied pre-trained GloVe embedding for the initialization of the word embeddings, which has 200 dimensions. Besides, Microsoft Satori was used to construct the subgraph for a given dataset);
generating a plurality of posterior click probabilities corresponding to the plurality of positive samples ([Page 701]: For the click- through rate (CTR) prediction, we employed the trained model to each line of the dataset in the test dataset and obtained the predicted click probability);
generating a prediction loss based on the plurality of posterior click probabilities; and optimizing the click probability predicting model through minimizing the prediction loss ([Page 698]: we employed multitask learning by utilizing the loss function of short-text modules in both the classification task and recommendation task; [Page 701, section 4.2 second paragraph]: To evaluate the K recommended list, we chose the F1 score metric. We ran each experiment 10 times independently and reported the average and maximum deviation as results).
Regarding Claim 13, the combined teachings of Dongho, Chatterjee, and Mao disclose the method of claim 12.
Dongho further teaches wherein the generating a plurality of posterior click probabilities comprises, for each positive sample: predicting a click probability of the positive sample corresponding to the positive sample; for each negative sample in a negative sample set corresponding to the positive sample, predicting a negative sample click probability corresponding to the negative sample, to obtain a negative sample click probability set corresponding to the negative sample set ([Page 701]: For the click- through rate (CTR) prediction, we employed the trained model to each line of the dataset in the test dataset and obtained the predicted click probability); and
calculating a posterior click probability corresponding to the positive sample based on the positive sample click probability and the negative sample click probability set ([Page 701, section 4.2 second paragraph]: For top-K recommendation, we applied the trained model to choose K items with the highest predicted click probability for each user in the test set. To evaluate the K recommended list, we chose the F1 score metric. We ran each experiment 10 times independently and reported the average and maximum deviation as results).
Regarding Claim 14, Dongho discloses an apparatus for hierarchical representation learning of user interest, comprising: at least one processor; and a memory storing computer-executable instructions that ([Page 695]: Online news websites, such as MSN News and Google News, collect news contents from various sources to provide them to users), when executed, cause the at least one processor to:
obtain a historical content item sequence of a user (Fig. 3; [Page 696]: we propose a Topic-Enriched Knowledge Graph Recommendation System (TEKGR)… which takes a piece of candidate news and a user’s click history as input; [Page 701, section 4.2]: we denote user i's clicked history),
identify a topic and a text of each historical content item in the historical content item sequence, to obtain a topic sequence and a text sequence corresponding to the historical content item sequence (Fig. 3; [Page 699, sections 4.1.1. - 4.1.3]: The knowledge encoder also has three layers to learn topical information on the news title… The goal of Topic Enhanced KG Construction is to consider contextual knowledge information along with topical information for the recommendation system… Word embedding, the first layer, converts a news title from a sequence of words to a sequence of dense semantic vectors),
generate a comprehensive topic representation based on the topic sequence ([Page 700, sections 4.1.2 and 4.1.3, page 701 left-hand column first full paragraph]: In general, short texts are mapped in implicit spaces and are represented as dense vectors… representations from the ... KG-level news encoder; Fig. 4, right-hand side),
generate a comprehensive text representation based on the text sequence ([Page 699, section 4.1.1, page 701 left-hand column first full paragraph]: We concatenate the concept vector with a news representation vector (from Word-level News Encoder) to extract the topic information vector, Fig 4, left-hand side), and
generate a user interest representation of the user based on the comprehensive topic representation and the comprehensive text representation (Fig. 4, left-hand side; [Page 699, section 4.1.1, page 701 left-hand column first full paragraph]: As shown in Figure 4, the KG-based news modeling layer has three encoders to extract the news representation vector… For example, a user with a huge interest…. would click…news titles that have financial terms in them… we can obtain the final representation of a news title in word-level news encoder).
However, Dongho does not explicitly teach “wherein the topic representation is a graph constructed from the topic sequence, the graph includes a plurality of nodes representing topic categories from the topic sequence, the graph includes edges between nodes representing sequential transitions between corresponding topic categories in the topic sequence, and the edges encode transition information derived from an order in which the user accessed content items of different topic categories in the historical content item sequence; wherein the comprehensive text representation is an aggregation of textual contents of historical content items in the historical content item sequence.”
On the other hand, in the same field of endeavor, Chatterjee teaches
wherein the topic representation is a graph constructed from the topic sequence (Fig. 5; [0005]: A system and method for the automated generation of a conversation graph representing a collection of conversations about a particular topic is disclosed. The system and method solve the problems discussed above by assigning various word sequences),
the graph includes a plurality of nodes representing topic categories from the topic sequence ([0005]: A system and method for the automated generation of a conversation graph representing a collection of conversations about a particular topic… resolution to a single conversation node; [0025]: A “node” in the graph can be extracted that represents the collection of word sequences that fall in the same dialogue act category),
the graph includes edges between nodes representing sequential transitions between corresponding topic categories in the topic sequence, ([0025]: In addition, the nodes will be connected to other nodes by an “edge” line, also referred to herein as a transitional path or transitional edge) and
the edges encode transition information derived from an order in which the user accessed content items of different topic categories in the historical content item sequence ([0108]: For example, because the conversation graph embeds utterance patterns for agents as a plurality of nodes and user utterances as a plurality of transitional paths or edges, it can be understood that the conversation graph implicitly encodes an agent's behavior based on user responses; as identified from historical chat log records);
Additionally, Mao teaches wherein the comprehensive text representation is an aggregation of textual contents of historical content items in the historical content item sequence ([Pages 47-50]: overall user representations can be aggregated by leveraging the correlation among interest clusters; [Pages 49-50]: refining specific user interest representations within clusters and aggregating overall user history information among clusters… With intra-cluster and inter-cluster attention, rinter hierarchically aggregates user interest representations within the cluster graph G).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teaching of Dongho to incorporate the teachings of Chatterjee and Mao to include the comprehensive topic representation as a graph, and the comprehensive text representation has an aggregation of textual contents of historical content items.
The motivation for doing so would be to classify the conversational intent of a conversation, as recognized by Chatterjee ([Abstract] of Chetterjee: The labeled clusters may be used to train a virtual agent to classify the conversational intent of a conversation), and to
learn hierarchical user interest representation to improve the performance of recommendations, as recognized by Mao ([Abstract] of Mao: SUE utilizes graph convolutional networks to extract cluster-structural features of user history, followed by intra-cluster and inter-cluster attention modules to learn hierarchical user interest representations. Experiment results on the MIND dataset validate the effectiveness of our model to improve the performance of news recommendation).
Regarding Claim 15, Dongho discloses at least one non-transitory machine-readable medium comprising instructions for hierarchical representation learning of user interest ([Page 695]: Online news websites, such as MSN News and Google News, collect news contents from various sources to provide them to users), that, when executed by at least one processor, causes the at least one processor to perform operations to:
obtain a historical content item sequence of a user (Fig. 3; [Page 696]: we propose a Topic-Enriched Knowledge Graph Recommendation System (TEKGR)… which takes a piece of candidate news and a user’s click history as input; [Page 701, section 4.2]: we denote user i's clicked history);
identify a topic and a text of each historical content item in the historical content item sequence, to obtain a topic sequence and a text sequence corresponding to the historical content item sequence (Fig. 3; [Page 699, sections 4.1.1. - 4.1.3]: The knowledge encoder also has three layers to learn topical information on the news title… The goal of Topic Enhanced KG Construction is to consider contextual knowledge information along with topical information for the recommendation system… Word embedding, the first layer, converts a news title from a sequence of words to a sequence of dense semantic vectors);
generate a comprehensive topic representation based on the topic sequence ([Page 700, sections 4.1.2 and 4.1.3, page 701 left-hand column first full paragraph]: In general, short texts are mapped in implicit spaces and are represented as dense vectors… representations from the ... KG-level news encoder; Fig. 4, right-hand side);
generate a comprehensive text representation based on the text sequence ([Page 699, section 4.1.1, page 701 left-hand column first full paragraph]: We concatenate the concept vector with a news representation vector (from Word-level News Encoder) to extract the topic information vector, Fig 4, left-hand side), and
generate a user interest representation of the user based on the comprehensive topic representation and the comprehensive text representation (Fig. 4, left-hand side; [Page 699, section 4.1.1, page 701 left-hand column first full paragraph]: As shown in Figure 4, the KG-based news modeling layer has three encoders to extract the news representation vector… For example, a user with a huge interest…. would click…news titles that have financial terms in them… we can obtain the final representation of a news title in word-level news encoder).
However, Dongho does not explicitly teach “wherein the topic representation is a graph constructed from the topic sequence, the graph includes a plurality of nodes representing topic categories from the topic sequence, the graph includes edges between nodes representing sequential transitions between corresponding topic categories in the topic sequence, and the edges encode transition information derived from an order in which the user accessed content items of different topic categories in the historical content item sequence; wherein the comprehensive text representation is an aggregation of textual contents of historical content items in the historical content item sequence.”
On the other hand, in the same field of endeavor, Chatterjee teaches
wherein the topic representation is a graph constructed from the topic sequence ([0005]: A system and method for the automated generation of a conversation graph representing a collection of conversations about a particular topic is disclosed. The system and method solve the problems discussed above by assigning various word sequences),
the graph includes a plurality of nodes representing topic categories from the topic sequence ([0005]: A system and method for the automated generation of a conversation graph representing a collection of conversations about a particular topic… resolution to a single conversation node; [0025]: A “node” in the graph can be extracted that represents the collection of word sequences that fall in the same dialogue act category),
the graph includes edges between nodes representing sequential transitions between corresponding topic categories in the topic sequence, ([0025]: In addition, the nodes will be connected to other nodes by an “edge” line, also referred to herein as a transitional path or transitional edge) and
the edges encode transition information derived from an order in which the user accessed content items of different topic categories in the historical content item sequence ([0108]: For example, because the conversation graph embeds utterance patterns for agents as a plurality of nodes and user utterances as a plurality of transitional paths or edges, it can be understood that the conversation graph implicitly encodes an agent's behavior based on user responses; as identified from historical chat log records);
Additionally, Mao teaches wherein the comprehensive text representation is an aggregation of textual contents of historical content items in the historical content item sequence ([Pages 47-50]: overall user representations can be aggregated by leveraging the correlation among interest clusters; [Pages 49-50]: refining specific user interest representations within clusters and aggregating overall user history information among clusters… With intra-cluster and inter-cluster attention, rinter hierarchically aggregates user interest representations within the cluster graph G).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teaching of Dongho to incorporate the teachings of Chatterjee and Mao to include the comprehensive topic representation as a graph, and the comprehensive text representation has an aggregation of textual contents of historical content items.
The motivation for doing so would be to classify the conversational intent of a conversation, as recognized by Chatterjee ([Abstract] of Chetterjee: The labeled clusters may be used to train a virtual agent to classify the conversational intent of a conversation), and to
learn hierarchical user interest representation to improve the performance of recommendations, as recognized by Mao ([Abstract] of Mao: SUE utilizes graph convolutional networks to extract cluster-structural features of user history, followed by intra-cluster and inter-cluster attention modules to learn hierarchical user interest representations. Experiment results on the MIND dataset validate the effectiveness of our model to improve the performance of news recommendation).
Regarding Claim 16, the combined teachings of Dongho, Chatterjee, and Mao disclose the apparatus of claim 14.
Mao further teaches wherein the comprehensive topic representation and the comprehensive text representation have different information abstraction levels ([Pages 49-52]: Besides intracluster refinement of user interests, modeling inter cluster correlation is also essential to leverage the overall information of user history… The GCN extracts structural features on graph G, refining specific user interest representations within clusters and aggregating overall user history information among clusters… deep neural models can learn refined representations adaptively, which are more effective than general feature engineering with fixed hancrafted features).
Regarding Claim 17, the combined teachings of Dongho, Chatterjee, and Mao disclose the apparatus of claim 14.
Mao further teaches the instructions to generate a comprehensive topic representation further comprising instructions to: generate a topic representation sequence corresponding to the topic sequence; construct a topic graph corresponding to the topic sequence; and generate the comprehensive topic representation based on the topic representation sequence and the topic graph ([Pages 48-50]: Section 2-Methodolgy; We construct an original cluster graph with the topic category label of news… We build the subgraph by treating the browsed news at nodes and adding bidirectional edges… Figure 2: The overall architecture of our model. The graph construction is based on the user history in Figure 1(a)).
Regarding Claim 18, the combined teachings of Dongho, Chatterjee, and Mao disclose the at least one non-transitory machine-readable medium of claim 15.
Mao further teaches wherein the comprehensive topic representation and the comprehensive text representation have different information abstraction levels ([Pages 49-52]: Besides intracluster refinement of user interests, modeling inter cluster correlation is also essential to leverage the overall information of user history… The GCN extracts structural features on graph G, refining specific user interest representations within clusters and aggregating overall user history information among clusters… deep neural models can learn refined representations adaptively, which are more effective than general feature engineering with fixed hancrafted features).
Regarding Claim 19, the combined teachings of Dongho, Chatterjee, and Mao disclose the at least one non-transitory machine-readable medium of claim 15.
Mao further teaches the instructions to generate a comprehensive topic representation further comprising instructions to: generate a topic representation sequence corresponding to the topic sequence; construct a topic graph corresponding to the topic sequence; and generate the comprehensive topic representation based on the topic representation sequence and the topic graph ([Pages 48-50]: Section 2-Methodolgy; We construct an original cluster graph with the topic category label of news… We build the subgraph by treating the browsed news at nodes and adding bidirectional edges… Figure 2: The overall architecture of our model. The graph construction is based on the user history in Figure 1(a)).
Regarding Claim 20, the combined teachings of Dongho, Chatterjee, and Mao disclose the at least one non-transitory machine-readable medium of claim 19.
Mao further teaches the instructions to construct a topic graph further comprising instructions to: determine a plurality of topic categories included in the topic sequence; set the plurality of topic categories into a plurality of nodes; determine a set of edges among the plurality of nodes; and combine the plurality of nodes and the set of edges into the topic graph ([Pages 48-50]: Section 2-Methodolgy; We construct an original cluster graph with the topic category label of news… We build the subgraph by treating the browsed news at nodes and adding bidirectional edges… Figure 2: The overall architecture of our model. The graph construction is based on the user history in Figure 1(a)).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SHIRLEY D. HICKS whose telephone number is (571)272-3304. The examiner can normally be reached Mon - Fri 7:30 - 4:00.
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, Charles Rones can be reached on (571) 272-4085. 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.
/S.D.H./Examiner, Art Unit 2168
/CHARLES RONES/Supervisory Patent Examiner, Art Unit 2168