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 .
Claim Objections
Claims 2 and 12 recite:
determining, based on the question feature vector, the root node among a plurality of root nodes of the decision tree.
Examiner suggests amending the claim to read:
determining, based on the question feature vector, the root node among a plurality of root nodes of the decision trees.
This is because by definition a decision tree can only contain one root node.
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.
Step 1 analysis for all claims:
In the instant case, claims 1-10 are directed to a system, claims 11-19 are directed to a method and claim 20 is directed to a manufacture. Thus, each of the claims falls within one of the four statutory categories (i.e., process, machine, manufacture, or composition of matter).
Claim 1:
Step 2A, Prong 1 analysis:
The claim(s) recite(s) in part:
• determining, based on a question input by a user …, a root node associated with the question in a decision tree … that is used for generating an answer to the question; As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses using a question that is given by the user to deciding on a root note that is related to the question and will be helpful for answering that question.
• determining, based on the root node, a plurality of candidate child nodes among a plurality of child nodes of the root node, wherein a plurality of similarities between the plurality of candidate child nodes and the question are greater than a threshold; As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses deciding possible child nodes that more related to the question than others than a threshold using the root node decided upon earlier.
• determining, based on a plurality of similarities of a plurality of candidate paths between the root node and the plurality of candidate child nodes, a target path among the plurality of candidate paths; As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses deciding on a path using multiple paths to the earlier child nodes based on how similar they are to the question.
• generating an answer to the question based on the target path; and; As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses analyzing the child nodes on the path and coming up with an answer to the question from the user.
• determining, based on a reply of the user to the answer, a label for the reply from the user, wherein the label comprises a classification of the question and a degree of satisfaction with the answer.; As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses deciding how satisfied the user is with the answer generated for their question and put it into a grouping of similar satisfaction.
Step 2A, Prong 2 analysis:
The judicial exception is not integrated into a practical application. In particular, the claim recites the additional elements of:
• question answering system; The limitation amounts to no more than generally linking the use of a judicial exception to a particular technological environment or field of use (See MPEP 2106.05(h)).
Accordingly, at Step 2A, prong two, the additional elements individually or in combination do not integrate the judicial exception into a practical application.
Step 2B analysis:
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception. As discussed above, the additional elements of:
• question answering system;
The limitation amounts to no more than generally linking the use of a judicial exception to a particular technological environment or field of use (See MPEP 2106.05(h)).
Accordingly, at Step 2B the additional elements individually or in combination do not amount to significantly more than the judicial exception.
Claim 2:
Step 2A, Prong 1 analysis:
The claim(s) recite(s) in part:
• extracting a plurality of keywords of the question; and; As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses identifying words from the words of the question that are representative of the question.
• converting the plurality of keywords into a question feature vector, wherein the question feature vector represents semantics and syntax of the question; and; As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses mapping the keywords into a vector of numbers that represent the meanings of the question.
• determining, based on the question feature vector, the root node among a plurality of root nodes of the decision tree.; As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses using the vector of numbers to choose the root node.
Step 2A, Prong 2 analysis:
The judicial exception is not integrated into a practical application. In particular, the claim recites the additional elements of:
• by using a trained natural language model; which is recited at a high-level of generality such that it amounts to no more than mere instructions to apply the exception using a generic computer component (See MPEP 2106.05(f))
Accordingly, at Step 2A, prong two, the additional elements individually or in combination do not integrate the judicial exception into a practical application.
Step 2B analysis:
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception. As discussed above, the additional elements of:
• by using a trained natural language model;
The machine learning model is recited at a high level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea. The training of the machine learning model is recited at a high-level of generality with no detail of the training process such that it amounts to no more than mere instructions to apply the exception using a generic computer component (See MPEP 2106.05(f)). Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea (See MPEP 2106.05(f))
Accordingly, at Step 2B the additional elements individually or in combination do not amount to significantly more than the judicial exception.
Claim 3:
Step 2A, Prong 1 analysis:
The claim(s) recite(s) in part:
• determining a plurality of child node feature vectors of the plurality of child nodes; As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses mapping the keywords into a vector of numbers that represent the meanings of the child nodes.
• determining the plurality of similarities based on the question feature vector and the plurality of child node feature vectors; and; As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses analyzing the vectors of the question and the child nodes to see what things they have in common.
• determining the plurality of candidate child nodes based on the plurality of similarities.; As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses analyzing the similarities as found above and choose some possible ones as candidates to use.
Step 2A, Prong 2 analysis:
There are no additional elements that individually or in combination integrate the judicial exception into a practical application.
Step 2B analysis:
There are no additional elements individually or in combination that amount to significantly more than the judicial exception.
Claim 4:
Step 2A, Prong 1 analysis:
The claim(s) recite(s) in part:
• for each candidate path of the plurality of candidate paths:
determining a plurality of similarities between adjacent nodes in each candidate path;
determining a total similarity of each candidate path based on a sum of the plurality of similarities between the adjacent nodes; and
determining a candidate path with the highest total similarity as the target path.;
As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses analyzing each of the possible paths by summing the similarity along each of the nodes on the path and choose the one with the highest sum.
Step 2A, Prong 2 analysis:
There are no additional elements that individually or in combination integrate the judicial exception into a practical application.
Step 2B analysis:
There are no additional elements individually or in combination that amount to significantly more than the judicial exception.
Claim 5:
Step 2A, Prong 1 analysis:
The claim(s) recite(s) in part:
• generating the answer based on a plurality of child node feature vectors of a plurality of child nodes on the target path and a root node feature vector of the root node, wherein the answer comprises an answer to the question or a further question to the question.; As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses analyzing the information from the feature vectors in the target path including the root node information and coming up with a response to the question (either being a question or an answer).
Step 2A, Prong 2 analysis:
There are no additional elements that individually or in combination integrate the judicial exception into a practical application.
Step 2B analysis:
There are no additional elements individually or in combination that amount to significantly more than the judicial exception.
Claim 6:
Step 2A, Prong 1 analysis:
The claim(s) recite(s) in part:
• determining, based on the reply, a reply feature vector of the reply; and
determining, based on the reply feature vector, the label for the reply from the user.; As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses analyzing the user’s reply and creating a vector of numbers to represent it and then using that to categorize the reply.
Step 2A, Prong 2 analysis:
The judicial exception is not integrated into a practical application. In particular, the claim recites the additional elements of:
• acquiring the reply of the user to the answer; which amounts to extra-solution activity of transmitting data for use in the claimed process. As described in MPEP 2106.05(g), limitations that amount to merely adding insignificant extra-solution activity to a judicial exception do not amount to significantly more than the exception itself, and cannot integrate a judicial exception into a practical application.
Accordingly, at Step 2A, prong two, the additional elements individually or in combination do not integrate the judicial exception into a practical application.
Step 2B analysis:
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception. As discussed above, the additional elements of:
• acquiring the reply of the user to the answer;
This limitation is directed to receiving input at an interface on a computing device, wherein the input comprises a dataset, an analysis for the dataset, and an output medium which amounts to extra-solution activity of transmitting data for use in the claimed process. The courts have found limitations directed to obtaining information electronically, recited at a high level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory").
Accordingly, at Step 2B the additional elements individually or in combination do not amount to significantly more than the judicial exception.
Claim 7:
Step 2A, Prong 1 analysis:
The claim(s) recite(s) in part:
• determining validity of the reply based on the reply feature vector;
determining key information of the reply based on the reply feature vector;
determining a classification of the reply based on the reply feature vector; and
determining a label for the reply from the user based on the validity, the key information, and the classification.
As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses analyzing the response of the user using the feature vector created to see how accurate the reply is, the important parts of the reply, a group to classify it in and to label it based on the accuracy, important parts, and the group.
Step 2A, Prong 2 analysis:
There are no additional elements that individually or in combination integrate the judicial exception into a practical application.
Step 2B analysis:
There are no additional elements individually or in combination that amount to significantly more than the judicial exception.
Claim 8:
Step 2A, Prong 1 analysis:
The claim(s) recite(s) in part:
• determining a dialog state based on the label, the question, the answer, a historical label, a historical question, and a historical answer; and
updating a historical dialog state by using the dialog state. As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses deciding a state that the dialogue is at using the current question and answer and the past question and answer along with the past label that it had and then after deciding on the current dialogue state, to change the historical dialogue state.
Step 2A, Prong 2 analysis:
There are no additional elements that individually or in combination integrate the judicial exception into a practical application.
Step 2B analysis:
There are no additional elements individually or in combination that amount to significantly more than the judicial exception.
Claim 9:
Step 2A, Prong 1 analysis:
The claim(s) recite(s) in part:
• determining, based on the retrieved information, a structured representation of a current dialog, wherein the structured representation comprises a plurality of entities and a plurality of corresponding concepts; and
. As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses deciding a state that the dialogue is at using the current question and answer and the past question and answer along with the past label that it had and then after deciding on the current dialogue state, to change the historical dialogue state.
Step 2A, Prong 2 analysis:
The judicial exception is not integrated into a practical application. In particular, the claim recites the additional elements of:
• retrieving, based on the dialog state, information associated with the dialog state; and
which amounts to extra-solution activity of transmitting data for use in the claimed process. As described in MPEP 2106.05(g), limitations that amount to merely adding insignificant extra-solution activity to a judicial exception do not amount to significantly more than the exception itself, and cannot integrate a judicial exception into a practical application.
• storing the structured representation in a memory. which amounts to extra-solution activity of storing data for use in the claimed process. As described in MPEP 2106.05(g), limitations that amount to merely adding insignificant extra-solution activity to a judicial exception do not amount to significantly more than the exception itself, and cannot integrate a judicial exception into a practical application.
Accordingly, at Step 2A, prong two, the additional elements individually or in combination do not integrate the judicial exception into a practical application.
Step 2B analysis:
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception. As discussed above, the additional elements of:
• retrieving, based on the dialog state, information associated with the dialog state; and
This limitation is directed to receiving input at an interface on a computing device, wherein the input comprises a dataset, an analysis for the dataset, and an output medium which amounts to extra-solution activity of gathering data for use in the claimed process. The courts have found limitations directed to obtaining information electronically, recited at a high level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory").
• storing the structured representation in a memory.
As discussed above, the additional element amounts to extra-solution activity of storing data for use in the claimed process. The courts have found limitations directed to obtaining information electronically, recited at a high level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory").
Accordingly, at Step 2B the additional elements individually or in combination do not amount to significantly more than the judicial exception.
Claim 10:
Step 2A, Prong 1 analysis:
The claim(s) recite(s) in part:
• updating the dialog state based on the structured representation; and
replying to a next question of the user based on at least one of the dialog state and the structured representation.; As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses changing the dialog state using a graph representation ( or vector) and then using at least one of those to reply to the next question the user asks.
Step 2A, Prong 2 analysis:
There are no additional elements that individually or in combination integrate the judicial exception into a practical application.
Step 2B analysis:
There are no additional elements individually or in combination that amount to significantly more than the judicial exception.
Claim 11:
Claim 11 recites substantially similar limitations for claim 1 and is therefore rejected on the same basis. However, claim 11 further teaches additional elements.
Step 2A, Prong 2 analysis:
The judicial exception is not integrated into a practical application. In particular, the claim recites the additional elements of:
• a processor; and which are recited at a high-level of generality such that it amounts to no more than mere instructions to apply the exception using a generic computer component (See MPEP 2106.05(f))
• a memory coupled to the processor, wherein the memory has instructions stored therein, and the instructions, when executed by the processor, cause the electronic device to perform actions comprising: which are recited at a high-level of generality such that it amounts to no more than mere instructions to apply the exception using a generic computer component (See MPEP 2106.05(f))
Accordingly, at Step 2A, prong two, the additional elements individually or in combination do not integrate the judicial exception into a practical application.
Step 2B analysis:
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception. As discussed above, the additional elements of:
• a processor; and
Computer elements are recited at a high-level of generality such and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea (See MPEP 2106.05(f))
• a memory coupled to the processor, wherein the memory has instructions stored therein, and the instructions, when executed by the processor, cause the electronic device to perform actions comprising:
Computer elements are recited at a high-level of generality such and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea (See MPEP 2106.05(f))
Accordingly, at Step 2B the additional elements individually or in combination do not amount to significantly more than the judicial exception.
Claim 12:
Claim 12 recites substantially similar limitations as claim 2 and is therefore rejected on the same basis.
Claim 13:
Claim 13 recites substantially similar limitations as claim 3 and is therefore rejected on the same basis.
Claim 14:
Claim 14 recites substantially similar limitations as claim 4 and is therefore rejected on the same basis.
Claim 15:
Claim 15 recites substantially similar limitations as claim 5 and is therefore rejected on the same basis.
Claim 16:
Claim 16 recites substantially similar limitations as claim 6 and is therefore rejected on the same basis.
Claim 17:
Claim 17 recites substantially similar limitations as claim 7 and is therefore rejected on the same basis.
Claim 18:
Claim 18 recites substantially similar limitations as claim 8 and is therefore rejected on the same basis.
Claim 19:
Claim 19 recites substantially similar limitations as the combination of claims 8 and 9 and is therefore rejected on the same basis.
Claim 20:
Claim 20 recites substantially similar limitations for claim 1 and is therefore rejected on the same basis. However, claim 20 further teaches additional elements.
Step 2A, Prong 2 analysis:
The judicial exception is not integrated into a practical application. In particular, the claim recites the additional elements of:
• computer program product, the computer program product being tangibly stored on a non-transitory computer-readable medium and comprising computer-executable instructions, wherein the computer-executable instructions, when executed by a device, cause the device to perform; which is recited at a high-level of generality such that it amounts to no more than mere instructions to apply the exception using a generic computer component (See MPEP 2106.05(f))
Accordingly, at Step 2A, prong two, the additional elements individually or in combination do not integrate the judicial exception into a practical application.
Step 2B analysis:
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception. As discussed above, the additional elements of:
• computer program product, the computer program product being tangibly stored on a non-transitory computer-readable medium and comprising computer-executable instructions, wherein the computer-executable instructions, when executed by a device, cause the device to perform:
Computer elements are recited at a high-level of generality such and amount to no more than adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea (See MPEP 2106.05(f))
Accordingly, at Step 2B the additional elements individually or in combination do not amount to significantly more than the judicial exception.
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 1, 6-10, 16-20 is rejected under 35 U.S.C 103 as being unpatentable over Yuan et al. (US 20230127907 A1, hereinafter Yuan) in view of Deng et al. ("User satisfaction estimation with sequential dialogue act modeling in goal-oriented conversational systems.", hereinafter Deng).
Regarding Claim 1:
Yuan teaches:
A method for a question answering system, comprising:
Yuan [0004] A computer-implemented method for conducting a natural language dialogue between a dialogue system and a user of a client computing device, comprising receiving, by the one or more processing units, a user question from a client computing device.
determining, based on a question input by a user to the question answering system, a root node associated with the question in a decision tree of the question answering system that is used for generating an answer to the question;
Yuan [0052] A user may ask a question in a natural language form through the client computing device to expect an answer to that question from the dialogue system. For example, the user's question may be a speech input in a natural language form or a keyboard input.
Yuan [0060] At block 406, the method 400 may construct a decision tree from the set of entities and the attributes associated with the set of entities. Each node of the decision tree is associated with a respective one of the attributes and represents a respective subset of the plurality of intention candidates. For example, a root node of the decision tree may represent all of the plurality of intention candidates.
Yuan [0063] Returning to FIG. 4 , at block 408, the method 400 may generate a question corresponding to a node of the decision tree to determine the user's intention. For example, a question may be generated corresponding to the root node of the decision tree.
Examiner’s Note (EN): the generated question in 414 is an answer/response to the user’s question in 402 and the generated question is generated using the root node which reads on a root node being determined
determining, based on the root node, a plurality of candidate child nodes among a plurality of child nodes of the root node, wherein a plurality of similarities between the plurality of candidate child nodes and the question are greater than a threshold;
Yuan [0053] At block 402, the method 400 may determine a plurality of intention candidates for the user from the user's question. For example, one or more models may be configured to determine the user's intention candidates from the user's question. Each of the models may be a machine learning model for natural language processing. The machine learning model may be a text classification model, for example, a neural network. Each model may determine one or more intention candidates from the user's question, where the intention candidates may each have a higher probability than a predefined threshold. The probability may be the probability of being determined as true intention.
[0060] At block 406, the method 400 may construct a decision tree from the set of entities and the attributes associated with the set of entities. Each node of the decision tree is associated with a respective one of the attributes and represents a respective subset of the plurality of intention candidates. For example, a root node of the decision tree may represent all of the plurality of intention candidates. The respective subset of the plurality of intention candidates may be split based on the entities associated with the respective one of the attributes.
EN: intentions are predicted using a NN and ranked and are filtered using a threshold; this paragraph reads on the remaining intentions are used to construct the decision tree
determining, based on a plurality of similarities of a plurality of candidate paths between the root node and the plurality of candidate child nodes, a target path among the plurality of candidate paths;
Yuan [0063] Each of the nodes in the decision tree may correspond to a question for interaction with the user. For example, the root node 802 may correspond to a question “which funding?” For example, the nodes 804 may correspond to a question “which city?” The method 400 may determine the user's intention based on the question(s) for interaction with the user, and then determine the answer to the user's question. Returning to FIG. 4 , at block 408, the method 400 may generate a question corresponding to a node of the decision tree to determine the user's intention.
EN: all of the paths along the child nodes in the decision tree created based on the filtered intentions are candidate paths; depth of 0 for the root is also a candidate path
generating an answer to the question based on the target path; and
Yuan [0063] Each of the nodes in the decision tree may correspond to a question for interaction with the user. For example, the root node 802 may correspond to a question “which funding?” For example, the nodes 804 may correspond to a question “which city?” The method 400 may determine the user's intention based on the question(s) for interaction with the user, and then determine the answer to the user's question. Returning to FIG. 4, at block 408, the method 400 may generate a question corresponding to a node of the decision tree to determine the user's intention.
EN: the question from the system to the user reads on generating the answer to the user’s question
determining, based on a reply of the user to the answer, a label for the reply from the user, wherein the label comprises a classification of the question
Yuan [0065] At block 412, the method 400 may determine the user's intention from the decision tree based on the user's answer to the question.
EN: intention classification reads on classification for natural language processing; the intent classification reads on labeling as well
Yuan teaches a label that comprises a classification but does not distinctly disclose labeling the reply with a degree of satisfaction:
degree of satisfaction with the answer.
However, Deng teaches:
degree of satisfaction with the answer.
Deng [page 2, 1. Introduction, col 2] To tackle the aforementioned issues, we propose a novel method, namely USDA, to jointly learn User Satisfaction Estimation and Dialogue Act Recognition tasks. On one hand, DAR serves as an auxiliary task that provides clues about sequential user intents for USE. In return, the dialogue act transitions can also benefit from the prediction of user satisfaction. When the dialogue act labels are available, the joint learning aims at assigning a dialogue act label to each user utterance in the whole conversation session to represent her/his conversational intents, and meanwhile, estimating the degree of user satisfaction towards the conversation. When the dialogue act labels are unavailable, the DAR subtask is expected to be conducted in an unsupervised manner, which could still provide useful sequential patterns for helping estimate the user satisfaction.
EN: estimating the user satisfaction using the dialogue reads on a degree of satisfaction
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art to combine the question answering system of Yuan with method of labeling the dialogue with a degree of satisfaction of Deng in order to fulfill the needs of the user better:
Deng [page 2, 2. Related Work, col 2] User satisfaction, which is related to the fulfillment of a specified desire or goal, is essential in evaluating and improving user-centered interactive IR systems [27].
Regarding Claim 6:
The combination of Yuan and Deng teaches all of the limitations of claim 1 as cited above and Yuan further teaches:
acquiring the reply of the user to the answer;
Yuan [0064] At block 410, the method 400 may receive the user's answer to the generated question from the client computing device. For example, the method 400 may provide the generated question to the user and then the user may answer the question in response.
determining … the label for the reply from the user.
wherein the label comprises … the degree of satisfaction
Yuan [0065] At block 412, the method 400 may determine the user's intention from the decision tree based on the user's answer to the question.
As cited above in claim 1, Yuan teaches labeling the reply of the user by intent classification but does not explicitly teach labeling with a degree of satisfaction or by using a reply feature:
determining, based on the reply, a reply feature vector of the reply; and
determining, based on the reply feature vector, the label for the reply from the user
wherein the label comprises … the degree of satisfaction
However, Deng further teaches labeling the reply with a degree of satisfaction using the reply feature vector:
determining, based on the reply, a reply feature vector of the reply; and
Deng [page 4, section 4.2.2, col 1] Since the user utterances are encoded into high-dimensional contextualized vectors, we employ a deep latent subspace clustering network [23] for the representational learning of latent features in the dialog to capture the DA information.
determining, based on the reply feature vector, the label for the reply from the user
wherein the label comprises … the degree of satisfaction
Deng [page 4, section 4.2.2, col 1] The basic idea is to encourage utterances of the same dialogue act to be clustered into a dense region in the low-dimensional embedding subspace.
[page 3, section 3 Problem Definition] We define the joint learning of user satisfaction estimation (USE) and dialogue act recognition (DAR) tasks. Given the dialogue context D containing 𝑁 utterances {𝑢1,𝑢2,...,𝑢𝑁 } in a conversation session, we split the dialogue into 𝑇 exchanges, and each exchange isa conversation turn between the user and the system, so that D can be represented by {(𝑢𝑞1,𝑢𝑝1), (𝑢𝑞2,𝑢𝑝2), ..., (𝑢𝑞𝑇−1,𝑢𝑝𝑇−1), (𝑢𝑞𝑇 , )},Where 𝑢𝑞𝑡 and 𝑢𝑝𝑡 denote the user utterance and the system utterance at 𝑡-th exchange. Note that the 𝑇-th exchange only contains the final user response. The goal is to simultaneously predict the sequence of dialogue act (DA) labels {𝑦𝑑1 ,𝑦𝑑2..., 𝑦𝑑𝑇} corresponding to the user intent at each turn, and the user satisfaction label 𝑦𝑠 by the end of this conversation session. As for DAR task, it can be accomplished via either supervised learning with annotated DA labels or unsupervised learning as an DA clustering task.
Regarding Claim 7:
The combination of Yuan and Deng teaches all of the limitations of claim 1 as cited above and Yuan further teaches:
determining key information of the reply based on the reply
Yuan [0065] At block 412, the method 400 may determine the user's intention from the decision tree based on the user's answer to the question. For example, if the user's answer is “pension,” the user in effect selects the second subset of the decision tree 800 by answering the question. If the root node 802 is also a leaf node, the user's intention may be determined to be the intention candidate selected by the user's answer.
EN: user’s answer helps narrow down or even determine candidate intention which reads on key information
determining a classification of the reply based on the reply
Yuan [0065] At block 412, the method 400 may determine the user's intention from the decision tree based on the user's answer to the question.
determining a label for the reply from the user based on the … the key information, and the classification.
Yuan [0065] At block 412, the method 400 may determine the user's intention from the decision tree based on the user's answer to the question.
EN: intention classification reads on labeling and in order to label the answer with an intention, the reply has to be classified and key information has to be used
Yuan does not explicitly teach:
reply feature vector
determining validity of the reply based on the reply feature vector;
However, Deng teaches:
reply feature vector
Deng [page 3, 4.1 Hierarchical Transformer Encoder, col 2] To this end, we develop a hierarchical Transformer encoder for the representation learning of dialogue context. Such encoder consists of a shared Exchange-level BERT Encoder for pair wisely encoding the exchange between the system and user in each turn, and a Dialogue-level Transformer Encoder for sequentially encoding the dialogue context in the whole conversation session.
determining validity of the reply based on the reply feature vector;
Deng [page 4, 4.3 User Satisfaction Estimation, col 2] With the content features 𝑐𝑡 learned from the hierarchical transformer encoder and the dialogue act features 𝑎𝑡 learned from the DAR task, we employ a pair of Attentive RNNs to capture both the content based and action-based dialogue transitions within a conversation session:
EN: determining if the reply is on content reads on validity of the reply
Wang [Specifications, page 15, lines 3-5] “A reply validity 512 task for reply verification is to check the validity 514 of the reply 502 of the user and is consistent with the question.”
Regarding Claim 8:
The combination of Yuan and Deng teaches all of the limitations of claim 7 as cited above including a label that comprises a degree of satisfaction and classification:
the label, the question, the answer,
and Yuan teaches ongoing dialogue but Deng further teaches:
a historical question, and a historical answer; and
Deng [page 3, section 3 Problem Definition] We define the joint learning of user satisfaction estimation (USE) and dialogue act recognition (DAR) tasks. Given the dialogue context D containing 𝑁 utterances {𝑢1,𝑢2,...,𝑢𝑁 } in a conversation session, we split the dialogue into 𝑇 exchanges, and each exchange isa conversation turn between the user and the system, so that D can be represented by {(𝑢𝑞1,𝑢𝑝1), (𝑢𝑞2,𝑢𝑝2), ..., (𝑢𝑞𝑇−1,𝑢𝑝𝑇−1), (𝑢𝑞𝑇 , )},Where 𝑢𝑞𝑡 and 𝑢𝑝𝑡 denote the user utterance and the system utterance at 𝑡-th exchange. Note that the 𝑇-th exchange only contains the final user response. The goal is to simultaneously predict the sequence of dialogue act (DA) labels {𝑦𝑑1 ,𝑦𝑑2..., 𝑦𝑑𝑇} corresponding to the user intent at each turn, and the user satisfaction label 𝑦𝑠 by the end of this conversation session. As for DAR task, it can be accomplished via either supervised learning with annotated DA labels or unsupervised learning as an DA clustering task.
determining a dialog state… and updating a historical dialog state by using the dialog state.
Deng [page 3, section 3 Problem Definition] The goal is to simultaneously predict the sequence of dialogue act (DA) labels {𝑦𝑑1 ,𝑦𝑑2..., 𝑦𝑑𝑇} corresponding to the user intent at each turn
EN: each yd is a dialog state and it is updated at each t up until T the end of the conversation; each previous y (ydt-1) that is the historical dialogue and as it moves onto the next part of the conversation the precious dialogue is updated
Regarding Claim 9:
The combination of Yuan and Deng teaches all of the limitations of claim 8 as cited above including a dialog state:
dialog state
Deng [page 3, section 3 Problem Definition] The goal is to simultaneously predict the sequence of dialogue act (DA) labels {𝑦𝑑1 ,𝑦𝑑2..., 𝑦𝑑𝑇} corresponding to the user intent at each turn
EN: DA label reads on dialog state
Yuan teaches:
retrieving, based on the dialog …, information associated with the dialog …; and
Yuan [0067] At block 414, the method 400 may determine a response to the user's question based on the user's intention. For example, if the candidate intention 806-4 may be determined to be the user's intention, it can be determined that the user intends to ask a question “How to withdraw pension in Beijing?”. The method 400 may then query a database for storing question-answer pairs to search for an answer to the disambiguated question.
EN: after the QA system determines the user’s intention from the question then it retrieves the relevant information to answer
determining … a structured representation of a current dialog, wherein the structured representation comprises a plurality of entities and a plurality of corresponding concepts; and
Yuan [0058] Returning to FIG. 4 , at block 404, the method 400 may determine a set of entities and attributes associated with the set of entities from the plurality of intention candidates. An entity is an object in the real world with an independent existence that can be differentiated from other objects. For example, an entity may be a named entity. A named entity is a real-world object that can be denoted with a proper name. For example, the intention candidates may be segmented to obtain a lexicon or vocabulary of the user's intention. The lexicon or vocabulary may include the entities and associated attributes. The entities associated with an attribute may be the values of the attribute. The attributes may also be referred to as tags of the entities.
[0065] At block 412, the method 400 may determine the user's intention from the decision tree based on the user's answer to the question. For example, if the user's answer is “pension,” the user in effect selects the second subset of the decision tree 800 by answering the question. If the root node 802 is also a leaf node, the user's intention may be determined to be the intention candidate selected by the user's answer.
EN: following Fig 4, the decision tree is created at block 404 and then after additional dialogue with the user at block 412, the tree is traversed which reads on structured representation of current dialogue;
storing the structured representation in a memory.
Yuan [0039] As shown in FIG. 1 , computer system/server 12 in cloud computing node 10 is shown in the form of a general-purpose computing device. The components of computer system/server 12 may include, but are not limited to, one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including system memory 28 to processor 16.
Yuan [Fig 4]
EN: as noted above, the tree is accessed during the dialogue which reads on being stored in memory
Regarding Claim 10:
The combination of Yuan and Deng teaches all of the limitations of claim 9 as cited above including a dialog state and a structured representation, but Yuan does not explicitly teach:
replying to a next question of the user
updating the dialog state
However, Deng teaches as cited above:
replying to a next question of the user
Deng [page 3, section 3 Problem Definition] We define the joint learning of user satisfaction estimation (USE) and dialogue act recognition (DAR) tasks. Given the dialogue context D containing 𝑁 utterances {𝑢1,𝑢2,...,𝑢𝑁 } in a conversation session, we split the dialogue into 𝑇 exchanges, and each exchange isa conversation turn between the user and the system, so that D can be represented by {(𝑢𝑞1,𝑢𝑝1), (𝑢𝑞2,𝑢𝑝2), ..., (𝑢𝑞𝑇−1,𝑢𝑝𝑇−1), (𝑢𝑞𝑇 , )},Where 𝑢𝑞𝑡 and 𝑢𝑝𝑡 denote the user utterance and the system utterance at 𝑡-th exchange. Note that the 𝑇-th exchange only contains the final user response.
[page 2, Figure 1]
EN: as shown in figure 1, utterances from the user can be answers or questions; the continuation of the conversation reads on the system replying to the next question of the user
updating the dialog state
Deng [page 3, section 3 Problem Definition] The goal is to simultaneously predict the sequence of dialogue act (DA) labels {𝑦𝑑1 ,𝑦𝑑2..., 𝑦𝑑𝑇} corresponding to the user intent at each turn
EN: each yd is a dialog state and it is updated at each t up until T the end of the conversation
Regarding Claim 11:
Claim 11 recites substantially similar limitations for claim 1 and is therefore rejected on the same basis, and Yuan further teaches:
An electronic device, comprising:
a processor; and a memory coupled to the processor, wherein the memory has instructions stored therein, and the instructions, when executed by the processor, cause the electronic device to perform actions comprising:
Yuan [0005] According to another embodiment of the present disclosure, there is provided a device. The device comprises a processor; and a memory having instructions stored thereon for execution by the processor, the instructions, when executed by the processor, cause the device to perform acts for conducting a natural language dialogue between a dialogue system and a user of a client computing device, the acts comprising.
Regarding Claim 16:
Claim 16 recites substantially similar limitations for claim 6 and is therefore rejected on the same basis.
Regarding Claim 17:
Claim 17 recites substantially similar limitations for claim 7 and is therefore rejected on the same basis.
Regarding Claim 18:
Claim 18 recites substantially similar limitations for claim 8 and is therefore rejected on the same basis.
Regarding Claim 19:
Claim 19 recites substantially similar limitations for the combination of claim 8 and 9 and is therefore rejected on the same basis.
Regarding Claim 20:
Claim 20 recites substantially similar limitations for claim 1 and is therefore rejected on the same basis.
However, in Claim 20, Yuan further teaches:
computer program product, the computer program product being tangibly stored on a non-transitory computer-readable medium and comprising computer-executable instructions, wherein the computer-executable instructions, when executed by a device, cause the device to perform:
Yuan [0069] The present disclosure may be a system, a method, and/or a computer program product at any possible technical detail level of integration. The computer program product may include a computer readable storage medium (or media) having computer readable program instructions thereon for causing a processor to carry out aspects of the present disclosure.
[0070] The computer readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing.
Claim 2-5 are rejected under 35 U.S.C 103 as being unpatentable over Yuan in view of Deng in further view of Malon et al. (US20140236578A1, hereinafter Malon).
Regarding Claim 2:
The combination of Yuan and Deng teaches all of the limitations of claim 1 as cited above and Yuan further teaches:
wherein determining, based on the question input by the user to the question answering system, the root node associated with the question comprises performing the following by using a trained natural language model:
Yuan [0053] At block 402, the method 400 may determine a plurality of intention candidates for the user from the user's question. For example, one or more models may be configured to determine the user's intention candidates from the user's question. Each of the models may be a machine learning model for natural language processing. The machine learning model may be a text classification model, for example, a neural network. Each model may determine one or more intention candidates from the user's question, where the intention candidates may each have a higher probability than a predefined threshold.
[0060] For example, a root node of the decision tree may represent all of the plurality of intention candidates.
EN: root node reads on plurality of predicted intentions as explained above; these intentions are outputted using the neural network model; this paragraph reads on using natural language modeling to determine the root node
determining, based on the question …, the root node among a plurality of root nodes of the decision tree[s].
Yuan [0055] As shown in FIG. 5 , the intention candidates 506 may be merged or aggregated to obtain a group of intention candidates. The group of intention candidates may be deduplicated to obtain an intention set 508. The intention set 508 may include only one instance for each intention candidate. In this way, the number of intention candidates in the intention set 508 may be different from the total number of the intention candidates 506.
[0060] For example, a root node of the decision tree may represent all of the plurality of intention candidates.
EN: the different combinations for the intention candidates reads on different root nodes; one root node is determined
Yuan does not explicitly teach a question feature vector. However, Deng teaches the representation of all dialogue of user and system in vector notation:
question feature vector
Deng [page 3, 4,1 Hierarchical Transformer Encoder, col 2] To this end, we develop a hierarchical Transformer encoder for the representation learning of dialogue context. Such encoder consists of a shared Exchange-level BERT Encoder for pair wisely encoding the exchange between the system and user in each turn, and a Dialogue-level Transformer Encoder for sequentially encoding the dialogue context in the whole conversation session.
EN: encoding the conversation in ML content reads on converting each part to a vector form
converting the plurality of keywords into a question feature vector, wherein the question feature vector represents semantics and syntax of the question; and
Deng [page 4, section 4.2.2, col 1] Under the circumstance where the dialogue act labels are unavailable, previous works [14, 22, 39] induce dialog intents by clustering user utterances to learn discriminative utterance representations in the user intent semantic space. Since the user utterances are encoded into high-dimensional contextualized vectors, we employ a deep latent subspace clustering network [23] for the representational learning of latent features in the dialog to capture the DA information.
EN: the encoded vectors of the conversation include information about both the semantics and syntax
The combination of Yuan and Deng does not explicitly teach NN model to do the following:
extracting a plurality of keywords of the question; and
However, Malon teaches using a neural network that uses question and its support sentence pair that is derived using a NN model in order to answer a question:
using a trained natural language model:
Malon [0021] A recursive neural network (RNN) is discussed next that can extract answers to arbitrary natural language questions from supporting sentences, by training on a crowd sourced data set. The RNN defines feature representations at every node of the parse trees of questions and supporting sentences, when applied recursively, starting with token vectors from a neural probabilistic language model.
extracting a plurality of keywords of the question; and
Malon [0009] Implementation of the above aspects can include one or more of the following. The system takes a (question, support sentence) pair, parses both question and support, and selects a substring of the support sentence as the answer. The recursive neural network, co-trained on recognizing descendants, establishes are presentation for each node in both parse trees. A convolutional neural network classifies each node, starting from the root, based upon the representations of the node, its siblings, its parent, and the question. Following the positive classifications, the system selects a substring of the support as the answer. The system provides a top-down supervised method using continuous word features in parse trees to find the answer; and a co-training task for training a recursive neural network that preserves deep structural information.
EN: this paragraph reads on extracting keywords using the support sentence
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art to combine the question answering system of Yuan and Deng with method the extraction of keywords for a dialogue modeling system in order to have more generality for syntactic/semantic tasks.
Malon [0011] Advantages of the system may include one or more of the following. Using meaning representations of the question and supporting sentences, our approach buys us freedom from explicit rules, question and answer types, and exact string matching. The system fixes neither the types of the questions nor the forms of the answers; and the system classifies tokens to match a substring chosen by the question's author.
Regarding Claim 3:
The combination of Yuan and Deng teaches all of the limitations of claim 2 as cited above and Yuan further teaches:
determining the plurality of candidate child nodes based on the plurality of similarities.
Yuan [0053] At block 402, the method 400 may determine a plurality of intention candidates for the user from the user's question. For example, one or more models may be configured to determine the user's intention candidates from the user's question. Each of the models may be a machine learning model for natural language processing. The machine learning model may be a text classification model, for example, a neural network. Each model may determine one or more intention candidates from the user's question, where the intention candidates may each have a higher probability than a predefined threshold. The probability may be the probability of being determined as true intention.
[0060] At block 406, the method 400 may construct a decision tree from the set of entities and the attributes associated with the set of entities. Each node of the decision tree is associated with a respective one of the attributes and represents a respective subset of the plurality of intention candidates. For example, a root node of the decision tree may represent all of the plurality of intention candidates. The respective subset of the plurality of intention candidates may be split based on the entities associated with the respective one of the attributes.
EN: intentions are predicted using a NN and ranked and are filtered using a threshold which reads on a similarity; this paragraph reads on the remaining intentions are used to construct the decision tree
While Yuan teaches the determination of a plurality of child nodes using a root node and Deng teaches encoding conversation in vectors, neither explicitly teach feature vectors for child nodes. The combination of Yuan and Deng does not explicitly teach the child node feature vectors, but Malon teaches:
determining a plurality of child node feature vectors of the plurality of child nodes;
Malon [0030] FIG. 4 shows an exemplary rooted tree structure. The structure of FIG. 4 is a rooted tree structure with feature vectors attached to terminal nodes. For the rooted tree structure, the system produces a feature vector at every internal node, including the root.
determining the plurality of similarities based on the question feature vector and the plurality of child node feature vectors; and
Malon [0025] However, new applications, such as question-answering, force a neural information processing system to do matching based on the values of features in the language model. For these applications, it is essential to have a model that is useful for modeling the language (through the first part of the feature vector) but can also be used to match words (through the second part).
EN: matching based on features read on finding similarities
Regarding Claim 4:
The combination of Yuan and Deng teaches all of the limitations of claim 2 as cited above and Yuan further teaches:
for each candidate path of the plurality of candidate paths:
determining a plurality of similarities between adjacent nodes in each candidate path;
Yuan [0060] At block 406, the method 400 may construct a decision tree from the set of entities and the attributes associated with the set of entities. Each node of the decision tree is associated with a respective one of the attributes and represents a respective subset of the plurality of intention candidates. For example, a root node of the decision tree may represent all of the plurality of intention candidates. The respective subset of the plurality of intention candidates may be split based on the entities associated with the respective one of the attributes.
EN: this reads on adjacent nodes having similarity as each node is a subset of the overall plurality of intention candidates; each path in the created tree is a candidate path
Although the combination of Yuan and Deng teaches the plurality of candidate paths and a plurality of similarities between adjacent nodes, the combination of Yuan and Deng does not explicitly teach the method of total similarity to the target path for the response from the system. However, Malon teaches:
determining a total similarity of each candidate path based on a sum of the plurality of similarities between the adjacent nodes; and
Malon [0022] Our classifier decides to follow each parse tree node of a support sentence or not, by classifying its RNN embedding together with those of its siblings and the root node of the question, until reaching the tokens it selects as the answer.
[0023] The classifier recursively classifies nodes of the parse tree of a supporting sentence. The positively classified nodes are followed down the tree, and any positively classified terminal nodes become the tokens in the answer. Feature representations are dense vectors in a continuous feature space; for the terminal nodes, they are the word vectors in a neural probabilistic language model, and for interior nodes, they are derived from children by recursive application of an autoencoder.
EN: the combination of all the positive nodes in the path as it traverses the tree reads on a total similarity for each path
determining a candidate path with the highest total similarity as the target path.
Malon [0023] The classifier recursively classifies nodes of the parse tree of a supporting sentence. The positively classified nodes are followed down the tree, and any positively classified terminal nodes become the tokens in the answer. Feature representations are dense vectors in a continuous feature space; for the terminal nodes, they are the word vectors in a neural probabilistic language model, and for interior nodes, they are derived from children by recursive application of an autoencoder.
EN: the path through the positive classified nodes that become tokens in the answer reads on the target path the highest similarity
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art to combine the question answering system of Yuan and Deng with method the extraction of keywords for a dialogue modeling system in order to have more generality for syntactic/semantic tasks.
Malon [0011] Advantages of the system may include one or more of the following. Using meaning representations of the question and supporting sentences, our approach buys us freedom from explicit rules, question and answer types, and exact string matching. The system fixes neither the types of the questions nor the forms of the answers; and the system classifies tokens to match a substring chosen by the question's author.
Regarding Claim 5:
The combination of Yuan and Deng teaches all of the limitations of claim 1 as cited above and Yuan further teaches:
generating the answer based on … target path and a …root node, wherein the answer comprises an answer to the question or a further question to the question.
Yuan [0063] Each of the nodes in the decision tree may correspond to a question for interaction with the user. For example, the root node 802 may correspond to a question “which funding?” For example, the nodes 804 may correspond to a question “which city?” The method 400 may determine the user's intention based on the question(s) for interaction with the user, and then determine the answer to the user's question. Returning to FIG. 4 , at block 408, the method 400 may generate a question corresponding to a node of the decision tree to determine the user's intention.
EN: the target path is the root node as the initial question as a plausible response to the user’s question
The combination of Yuan and Deng does not explicitly teach generating the answer based on the child note feature vectors and a root node feature vector, however, Malon teaches:
generating the answer based on a plurality of child node feature vectors of a plurality of child nodes on the target path and a root node feature vector of the root node
Malon [0030] For the rooted tree structure, the system produces a feature vector at every internal node, including the root.
[0023] The classifier recursively classifies nodes of the parse tree of a supporting sentence. The positively classified nodes are followed down the tree, and any positively classified terminal nodes become the tokens in the answer.
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art to combine the question answering system of Yuan and Deng with method the extraction of keywords for a dialogue modeling system in order to have more generality for syntactic/semantic tasks.
Malon [0011] Advantages of the system may include one or more of the following. Using meaning representations of the question and supporting sentences, our approach buys us freedom from explicit rules, question and answer types, and exact string matching. The system fixes neither the types of the questions nor the forms of the answers; and the system classifies tokens to match a substring chosen by the question's author.
Claim 12:
Claim 12 recites substantially similar limitations for claim 2 and is therefore rejected on the same basis.
Claim 13:
Claim 13 recites substantially similar limitations for claim 3 and is therefore rejected on the same basis.
Claim 14:
Claim 14 recites substantially similar limitations for claim 4 and is therefore rejected on the same basis.
Claim 15:
Claim 15 recites substantially similar limitations for claim 5 and is therefore rejected on the same basis.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JIAHE NIU whose telephone number is (571)270-0152. The examiner can normally be reached 8am-5pm.
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, Omar Fernandez Rivas, can be reached at (571) 272-2589. 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.
/JIAHE NIU/Examiner, Art Unit 2128
/RYAN C VAUGHN/Primary Examiner, Art Unit 2125
Prosecution Insights