Intelligent question answering method, device and system based on cognitive reasoning

Abstract

The invention relates to the field of artificial intelligence, and discloses an intelligent question and answer method, device and system based on cognitive reasoning, and the method comprises the steps: a cloud model call server obtains the answer efficiency of a large language model in a corresponding field according to the answer speed and correct rate of different large language models in different fields; obtaining a large language model sequence of the corresponding field according to the answering efficiency of the large language model in the corresponding field, calling a server by the cloud model to obtain to-be-answered question information sent by the question answering equipment, and generating a question answering container; the question-answering container obtains the field of a to-be-answered question according to the to-be-answered question information sent by the question-answering device, the question-answering container sends the to-be-answered question to the large language question-answering model sequence corresponding to the to-be-answered question, and question-answering content is generated; the question-answering container returns question-answering content to the question-answering device, and intelligent question-answering is completed. According to the method, the multi-field cross problem can be automatically identified and processed, and it is ensured that the problem can be comprehensively and accurately solved according to the optimal sequence and mode.

Description

Technical Field

[0001] The present invention relates to artificial intelligence, and in particular to an intelligent question-answering method, device and system based on cognitive reasoning. Background Art

[0002] With the rapid development of information technology, intelligent question-answering systems have become an important bridge connecting people with information and services. Traditional question-answering systems often rely on methods such as keyword matching, preset rules or templates. These methods perform well when dealing with simple, well-structured questions, but their limitations and shortcomings are fully exposed when faced with complex, multi-domain cross-cutting questions that require deep understanding. In recent years, with the continuous advancement of artificial intelligence technology, especially the rise of large language models, new hope has been brought to intelligent question-answering systems. With its powerful natural language processing capabilities and extensive knowledge coverage, large language models can more accurately understand user intentions and provide more accurate and comprehensive answers.

[0003] However, large language models are not omnipotent. Their performance in different fields varies, and problems such as high resource consumption and long response time also limit their widespread application. How to efficiently and reasonably utilize large language model resources to achieve fast and accurate question and answer has become a major challenge facing the current intelligent question and answer system. In addition, with the increasing diversification of user needs, single-field question and answer can no longer meet actual needs, and multi-field cross-question and answer has become a new trend. This requires the intelligent question and answer system to automatically identify the problem domain and dynamically adjust the question and answer strategy to ensure that each question can get the most appropriate answer.

[0004] Although existing technologies have proposed some solutions to the above problems, such as using domain classifiers to identify the problem domain and then calling a large language model in the corresponding domain to answer the problem, these solutions often ignore the differences in resource usage and communication delays of different large language models, resulting in low overall system efficiency. At the same time, existing technologies lack effective processing mechanisms for multi-domain cross-problems, and can often only simply split the problems and handle them separately, ignoring the correlation and integrity between the problems. Summary of the invention

[0005] The purpose of the present invention is to overcome the deficiencies of the prior art and provide an intelligent question answering method based on cognitive reasoning, comprising the following steps: Step 1: The cloud model calls the server to obtain the answer efficiency of the large language model in the corresponding field according to the answer speed and accuracy of different large language models in different fields, and obtains the large language model sequence in the corresponding field according to the answer efficiency of the large language model in the corresponding field. The cloud model calls the server to obtain the question information to be answered sent by the question-answering device and generate a question-answering container; Step 2: The question-answering container obtains the domain of the question to be answered according to the question information to be answered sent by the question-answering device. If the domain of the question to be answered is a single-domain question, the process proceeds to step 3; otherwise, the process proceeds to step 4. Step 3: According to the field of the question to be answered, a sequence of large language models in the corresponding field is obtained. According to the answer efficiency of each large language model, the question-answering container sends the question information to be answered to the large prediction model with the highest answer efficiency to generate question-answering content, and then proceeds to step 6. Step 4: According to the fields included in the questions to be answered, a large language model sequence for each corresponding field is obtained, and according to the resource occupation of the large language model in the large language model sequence for the corresponding field, the calling priority of each large language model in the large language model sequence for the corresponding field is obtained respectively, and according to the communication delay between the question-answering device and each large language model in the large language model sequence for the corresponding field and the large language model calling priority, the large language model question-answering priority is obtained, and the large language model question-answering sequence for the corresponding field is obtained according to the question-answering priority; Step 5: According to the large language model with the highest question-answering priority in the large language model question-answering sequence of each corresponding field and the order of the fields of the questions to be answered, a large language question-answering model sequence corresponding to the questions to be answered is obtained, and the question-answering container sends the questions to be answered to the large language question-answering model sequence corresponding to the questions to be answered to generate question-answering content; Step 6: The question-and-answer container returns the question-and-answer content to the question-and-answer device to complete the intelligent question-and-answer process.

[0006] Furthermore, the cloud model calling server obtains the answer efficiency of the large language model in the corresponding field according to the answer speed and accuracy of different large language models in different fields, including: Answer efficiency = c ×Answer speed+ d ×Accuracy Among them c represents the weight coefficient of answer speed, d The weight coefficient representing the accuracy rate.

[0007] Further, the calling priority of each large language model in the large language model sequence of the corresponding field is obtained according to the resource occupation of the large language model in the large language model sequence of the corresponding field, and the large language model question-answering priority is obtained according to the communication delay between the question-answering device and each large language model in the large language model sequence of the corresponding field and the large language model calling priority, including: The resource usage of the large language model includes computing power usage, answer load and answer efficiency. The calling priority of the large language model is obtained according to the resource usage, using the following formula: Call Priority = α ×Hashrate usage+ β× Answer Load + Answer Efficiency in, α Indicates the weight coefficient of computing power, β represents the answer load weight coefficient; According to the communication delay between the question-answering device and the large language model sequence in the corresponding field and the large language model call priority, the large language model question-answering priority is obtained: Large language model question answering priority = α ×Hashrate usage+ β × answer load + answer efficiency + communication delay between the question-answering device and the large language model.

[0008] Furthermore, the communication delay between the question-answering device and each language model in the large language model sequence of the corresponding field includes: The question-and-answer device sends a test request with a timestamp to the large language model, records the timestamps of the responses from each language model, and determines the communication delay by calculating the time difference between sending the request and receiving the response.

[0009] Furthermore, the question-and-answer container sends the question to be answered to the large language question-and-answer model sequence corresponding to the question to be answered, and generates question-and-answer content, including: The question-and-answer container decomposes the question to be answered into sub-questions in the corresponding fields, and obtains a sequence of sub-questions in the corresponding fields according to the order of the fields in which the questions are answered. According to the sequence of sub-questions in the corresponding fields, the sub-questions in the corresponding fields are sent to the large language question-and-answer model sequence of the corresponding questions to be answered. According to the question-and-answer results returned by the large language question-and-answer model and the next sub-question in the corresponding field, they are sent to the next large language question-and-answer model until the question-and-answer of all sub-questions in the corresponding fields is completed and the question-and-answer content is obtained.

[0010] An intelligent question-answering device based on cognitive reasoning applies the intelligent question-answering method based on cognitive reasoning, including a communication device, a delay test module, a data processing module and an information input module; the communication device, the delay test module and the information input module are respectively connected to the data processing module.

[0011] An intelligent question-answering system based on cognitive reasoning, using the intelligent question-answering device based on cognitive reasoning, including a cloud model calling server and communication equipment; The intelligent question-answering device based on cognitive reasoning is connected to the cloud model calling server through a communication device.

[0012] The beneficial effects of the present invention are: improving the efficiency and accuracy of question answering: by comprehensively considering the answering efficiency and resource occupancy of the large language model in different fields, the present invention can dynamically select the optimal large language model for question answering, thereby significantly improving the efficiency and accuracy of question answering.

[0013] Reduce resource consumption: The present invention avoids unnecessary resource waste through refined resource management and scheduling. In particular, when dealing with multi-domain cross-problems, the overall resource consumption of the system is effectively reduced by optimizing the calling sequence and method of the large language model.

[0014] Reducing communication delay: By measuring and considering communication delay in real time, the present invention can select a large language model with minimal communication delay for question answering, thereby reducing user waiting time and improving user experience.

[0015] Support multi-domain cross-question answering: The present invention can automatically identify and process multi-domain cross-questions. By constructing a large language question-answering model sequence, it ensures that questions can be answered comprehensively and accurately in the optimal order and manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flowchart of the intelligent question-answering method based on cognitive reasoning; Figure 2 It is a schematic diagram of the principle of an intelligent question-answering device based on cognitive reasoning; Figure 3 Schematic diagram of the principle of an intelligent question-answering system based on cognitive reasoning. DETAILED DESCRIPTION

[0017] The technical solution of the present invention is further described in detail below in conjunction with the accompanying drawings, but the protection scope of the present invention is not limited to the following.

[0018] The features and performance of the present invention are further described in detail below in conjunction with the embodiments.

[0019] like Figure 1 As shown, the intelligent question answering method based on cognitive reasoning includes the following steps: Step 1: The cloud model calls the server to obtain the answer efficiency of the large language model in the corresponding field according to the answer speed and accuracy of different large language models in different fields, and obtains the large language model sequence in the corresponding field according to the answer efficiency of the large language model in the corresponding field. The cloud model calls the server to obtain the question information to be answered sent by the question-answering device and generate a question-answering container; Step 2: The question-answering container obtains the domain of the question to be answered according to the question information to be answered sent by the question-answering device. If the domain of the question to be answered is a single-domain question, the process proceeds to step 3; otherwise, the process proceeds to step 4. Step 3: According to the field of the question to be answered, a sequence of large language models in the corresponding field is obtained. According to the answer efficiency of each large language model, the question-answering container sends the question information to be answered to the large prediction model with the highest answer efficiency to generate question-answering content, and then proceeds to step 6. Step 4: According to the fields included in the questions to be answered, a large language model sequence for each corresponding field is obtained, and according to the resource occupation of the large language model in the large language model sequence for the corresponding field, the calling priority of each large language model in the large language model sequence for the corresponding field is obtained respectively, and according to the communication delay between the question-answering device and each large language model in the large language model sequence for the corresponding field and the large language model calling priority, the large language model question-answering priority is obtained, and the large language model question-answering sequence for the corresponding field is obtained according to the question-answering priority; Step 5: According to the large language model with the highest question-answering priority in the large language model question-answering sequence of each corresponding field and the order of the fields of the questions to be answered, a large language question-answering model sequence corresponding to the questions to be answered is obtained, and the question-answering container sends the questions to be answered to the large language question-answering model sequence corresponding to the questions to be answered to generate question-answering content; Step 6: The question-and-answer container returns the question-and-answer content to the question-and-answer device to complete the intelligent question-and-answer process.

[0020] The cloud model calling server obtains the answer efficiency of the large language model in the corresponding field according to the answer speed and accuracy of different large language models in different fields, including: Answer efficiency = c ×Answer speed+ d ×Accuracy Among them c represents the weight coefficient of answer speed, d The weight coefficient representing the accuracy rate.

[0021] The method of obtaining the calling priority of each large language model in the large language model sequence of the corresponding field according to the resource occupation of the large language model in the large language model sequence of the corresponding field, and obtaining the large language model question-answering priority according to the communication delay between the question-answering device and each large language model in the large language model sequence of the corresponding field and the large language model calling priority, includes: The resource usage of the large language model includes computing power usage, answer load and answer efficiency. The calling priority of the large language model is obtained according to the resource usage, using the following formula: Call Priority = α ×Hashrate usage+ β × Answer Load + Answer Efficiency in, α Indicates the weight coefficient of computing power, β represents the answer load weight coefficient; According to the communication delay between the question-answering device and the large language model sequence in the corresponding field and the large language model call priority, the large language model question-answering priority is obtained: Large language model question answering priority = α ×Hashrate usage+ β× answer load + answer efficiency + communication delay between the question-answering device and the large language model.

[0022] The communication delay between the question-answering device and each language model in the large language model sequence of the corresponding field includes: The question-and-answer device sends a test request with a timestamp to the large language model, records the timestamps of the responses from each language model, and determines the communication delay by calculating the time difference between sending the request and receiving the response.

[0023] The question-and-answer container sends the question to be answered to the large language question-and-answer model sequence corresponding to the question to be answered, and generates question-and-answer content, including: The question-and-answer container decomposes the question to be answered into sub-questions in the corresponding fields, and obtains a sequence of sub-questions in the corresponding fields according to the order of the fields in which the questions are answered. According to the sequence of sub-questions in the corresponding fields, the sub-questions in the corresponding fields are sent to the large language question-and-answer model sequence of the corresponding questions to be answered. According to the question-and-answer results returned by the large language question-and-answer model and the next sub-question in the corresponding field, they are sent to the next large language question-and-answer model until the question-and-answer of all sub-questions in the corresponding fields is completed and the question-and-answer content is obtained.

[0024] like Figure 2 As shown, an intelligent question-answering device based on cognitive reasoning applies the intelligent question-answering method based on cognitive reasoning, including a communication device, a delay testing module, a data processing module and an information input module; the communication device, the delay testing module and the information input module are respectively connected to the data processing module.

[0025] like Figure 3 As shown, the intelligent question-answering system based on cognitive reasoning is characterized in that the intelligent question-answering device based on cognitive reasoning is applied, including a cloud model calling server and a communication device; The intelligent question-answering device based on cognitive reasoning is connected to the cloud model calling server through a communication device.

[0026] Specifically, the present invention proposes an intelligent question-answering method based on cognitive reasoning, which realizes the rapid and accurate answers to questions in different fields through the collaborative work of cloud model calling server, question-answering container and other components, while effectively reducing resource consumption and communication delay. The specific steps are as follows: Step 1: Build a large language model sequence The cloud model call server first calculates the answer efficiency of the large language model in the corresponding field based on the answer speed and accuracy of different large language models in different fields. The calculation formula for answer efficiency is: answer efficiency = γ × answer speed + δ × accuracy, where γ and δ are the weight coefficients of answer speed and accuracy, respectively, which can be adjusted according to actual conditions. Based on the answer efficiency, the server generates a large language model sequence for the corresponding field for subsequent calls.

[0027] When the question-and-answer device sends information about questions to be answered, the cloud model calls the server to receive and generate a question-and-answer container for subsequent question processing.

[0028] Step 2: Problem Area Identification The question-answering container uses natural language processing technology to identify the domain of the question based on the information of the question to be answered. If the question belongs to a single domain, it will directly proceed to step 3; if the question involves multiple domains, it will proceed to step 4 for special processing.

[0029] Step 3: Single field problem handling For single-domain questions, the question-answering container selects the large language model with the highest answer efficiency to answer the question based on the large language model sequence generated in step 1. This ensures the accuracy of the answer and improves the response speed.

[0030] Step 4: Handling cross-cutting issues in multiple fields For multi-domain cross-questions, the question-answering container first obtains the large language model sequence of the corresponding field according to the field involved in the question. Then, considering the resource usage of the large language model (including computing power usage, answer load and answer efficiency), communication delay and other factors, the question-answering priority of each large language model is calculated. The specific calculation method is: call priority = α×computing power usage + β×answer load + answer efficiency, where α and β are the weight coefficients of computing power usage and answer load respectively; combined with communication delay, the large language model question-answering priority is obtained: large language model question-answering priority = α×computing power usage + β×answer load + answer efficiency + communication delay between the question-answering device and the large language model.

[0031] The communication delay is measured by sending a test request with a timestamp to the large language model through the question-and-answer device, recording the timestamps of the responses from each language model, and calculating the time difference between sending the request and receiving the response.

[0032] Step 5: Generate large language question answering model sequence Based on the big language model question-answering priority calculated in step 4 and the order of various fields in the questions to be answered, the question-answering container generates a big language question-answering model sequence corresponding to the questions to be answered. This sequence ensures that the questions can be answered in the optimal order and manner.

[0033] Step 6: Question Answering and Return The question-answering container decomposes the question to be answered into sub-questions in the corresponding fields, and sends the sub-questions to the corresponding large language models for answering in sequence according to the large language question-answering model sequence. The question-answering results returned by each large language model will be used as input for the next large language model to process until all sub-questions are answered. Finally, the question-answering container returns the complete question-answering content to the question-answering device, completing the intelligent question-answering process.

[0034] Example 1: Single domain problem handling example Assume that a user submits a question about "quantum computing principles" through a question-answering device, and the question belongs to a single field (i.e., the field of quantum computing in physics). According to the intelligent question-answering method based on cognitive reasoning proposed by the present invention, the processing flow is as follows: Building a large language model sequence: The cloud model call server has pre-evaluated the answer speed and accuracy of multiple large language models in the field of physics and calculated their answer efficiency. Assume that there are three large language models A, B, and C, and their answer efficiency in the field of physics is 0.85, 0.90, and 0.75 respectively (according to the formula: answer efficiency = γ × answer speed + δ × accuracy, where γ and δ have been set according to actual needs).

[0035] Based on these answer efficiencies, the server generates a large language model sequence in the field of physics: B (highest efficiency)>A>C.

[0036] Problem Area Identification: After the question-and-answer container receives the "quantum computing principles" question submitted by the user, it uses natural language processing technology to identify that the question belongs to the field of physics, especially the subfield of quantum computing.

[0037] Single field problem solving: The question-answer container directly selects the large language model B with the highest answer efficiency to handle the question based on the sequence of large language models in the physics field generated in step 1.

[0038] After receiving the question, the large language model B conducts deep understanding and reasoning, and then generates a detailed answer on the "principles of quantum computing."

[0039] Questions and Answers and Returns: The large language model B returns the answer content to the question and answer container.

[0040] The Q&A container returns the complete Q&A content to the Q&A device, and the user can see the accurate answer to the "Principles of Quantum Computing".

[0041] In this embodiment, by selecting the large language model B with the highest answer efficiency to process single-domain questions, not only the accuracy of the answer is guaranteed, but also the response speed is improved, and resource consumption and communication delay are reduced.

[0042] Example 2: Multi-domain cross-problem processing example Assume that a user submits a question about "the application of artificial intelligence in the medical field and its impact on ethics" through the question-answering device. This question involves three fields: artificial intelligence, medicine, and ethics. According to the intelligent question-answering method based on cognitive reasoning proposed by the present invention, the processing flow is as follows: Building a large language model sequence: The cloud-based model calling server has pre-evaluated the answering speed and accuracy of multiple large language models in the fields of artificial intelligence, medicine, and ethics, and has calculated their answering efficiency in their respective fields.

[0043] Based on these answer efficiencies, the server generates a large language model sequence for the corresponding fields, assuming that A1>A2>A3 in the field of artificial intelligence, M1>M2 in the medical field, and E1>E2 in the field of ethics.

[0044] Problem Area Identification: After receiving the questions submitted by users, the question-answering container uses natural language processing technology to identify that the questions involve three fields: artificial intelligence, medicine, and ethics.

[0045] Handling of multi-domain cross-cutting issues: The question-answer container obtains large language model sequences of corresponding fields according to the fields involved in the questions.

[0046] Taking into account the resource usage of the large language model (including computing power usage, answer load and answer efficiency), communication delay and other factors, the question and answer priority of each large language model is calculated. Assume that after calculation, the obtained large language model question and answer priority order is: M1 (medical field) > A1 (artificial intelligence field) > E1 (ethics field).

[0047] Generate large language question answering model sequence: Based on the calculated large language model question-answering priority and the order of various fields in the question to be answered (assuming that the user wants to first understand the application in the medical field, then understand artificial intelligence technology, and finally discuss the ethical impact), the question-answering container generates a large language question-answering model sequence corresponding to the question to be answered: M1 ->A1 ->E1.

[0048] Questions and Answers and Returns: The question-answering container decomposes the question to be answered into sub-questions in the corresponding field, and sends the sub-questions to the corresponding large language model for answering in sequence according to the large language question-answering model sequence.

[0049] First, the M1 large language model answers the sub-question about "the application of artificial intelligence in the medical field" and returns the result to the question-answering container.

[0050] Next, the question-and-answer container sends M1's answer and the sub-question about "artificial intelligence technology" to the A1 large language model for answering.

[0051] After the A1 large language model answers, it returns the result to the question-answering container, which then sends the answer to A1 and the sub-question about "ethical impact" to the E1 large language model for answering.

[0052] After the E1 large language model answers, the final result is returned to the question-answering container.

[0053] The Q&A container returns the complete Q&A content (including medical applications, introduction to AI technology, and ethical impact analysis) to the Q&A device, so that users can see comprehensive and accurate answers to "the application of AI in the medical field and its impact on ethics."

[0054] In this embodiment, by comprehensively considering factors such as the resource usage and communication delay of the large language model, the large language model question and answer priority is calculated, and a large language question and answer model sequence corresponding to the questions to be answered is generated, ensuring that multi-domain cross-cutting questions can be answered comprehensively and accurately in the optimal order and manner.

Claims

1. An intelligent question-answering method based on cognitive reasoning, characterized in that: The steps include: Step 1: The cloud model calls the server to obtain the answer efficiency of the large language model in the corresponding field according to the answer speed and accuracy of different large language models in different fields, and obtains the large language model sequence in the corresponding field according to the answer efficiency of the large language model in the corresponding field. The cloud model calls the server to obtain the question information to be answered sent by the question-answering device and generate a question-answering container; Step 2: The question-answering container obtains the domain of the question to be answered according to the question information to be answered sent by the question-answering device. If the domain of the question to be answered is a single-domain question, the process proceeds to step 3; otherwise, the process proceeds to step 4. Step 3: According to the field of the question to be answered, a sequence of large language models in the corresponding field is obtained. According to the answer efficiency of each large language model, the question-answering container sends the question information to be answered to the large prediction model with the highest answer efficiency to generate question-answering content, and then proceeds to step 6. Step 4: According to the fields included in the questions to be answered, a large language model sequence for each corresponding field is obtained, and according to the resource occupation of the large language model in the large language model sequence for the corresponding field, the calling priority of each large language model in the large language model sequence for the corresponding field is obtained respectively, and according to the communication delay between the question-answering device and each large language model in the large language model sequence for the corresponding field and the large language model calling priority, the large language model question-answering priority is obtained, and the large language model question-answering sequence for the corresponding field is obtained according to the question-answering priority; Step 5: According to the large language model with the highest question-answering priority in the large language model question-answering sequence of each corresponding field and the order of the fields of the questions to be answered, a large language question-answering model sequence corresponding to the questions to be answered is obtained, and the question-answering container sends the questions to be answered to the large language question-answering model sequence corresponding to the questions to be answered to generate question-answering content; Step 6: The question-and-answer container returns the question-and-answer content to the question-and-answer device to complete the intelligent question-and-answer process.

2. The intelligent question-answering method based on cognitive reasoning according to claim 1, characterized in that: The cloud model calling server obtains the answer efficiency of the large language model in the corresponding field according to the answer speed and accuracy of different large language models in different fields, including: Answer efficiency = γ ×Answer speed+ δ ×Accuracy Among them γ represents the weight coefficient of answer speed, δ The weight coefficient representing the accuracy rate.

3. The intelligent question-answering method based on cognitive reasoning according to claim 2, characterized in that: The method of obtaining the calling priority of each large language model in the large language model sequence of the corresponding field according to the resource occupation of the large language model in the large language model sequence of the corresponding field, and obtaining the large language model question-answering priority according to the communication delay between the question-answering device and each large language model in the large language model sequence of the corresponding field and the large language model calling priority, includes: The resource usage of the large language model includes computing power usage, answer load and answer efficiency. The calling priority of the large language model is obtained according to the resource usage, using the following formula: Call Priority = α ×Hashrate usage+ β × Answer Load + Answer Efficiency in, α Indicates the weight coefficient of computing power, β represents the answer load weight coefficient; According to the communication delay between the question-answering device and the large language model sequence in the corresponding field and the large language model call priority, the large language model question-answering priority is obtained: Large language model question answering priority = α ×Hashrate usage+ β × answer load + answer efficiency + communication delay between the question-answering device and the large language model.

4. The intelligent question-answering method based on cognitive reasoning according to claim 3 is characterized in that: The communication delay between the question-answering device and each language model in the large language model sequence of the corresponding field includes: The question-and-answer device sends a test request with a timestamp to the large language model, records the timestamps of the responses from each language model, and determines the communication delay by calculating the time difference between sending the request and receiving the response.

5. The intelligent question-answering method based on cognitive reasoning according to claim 4 is characterized in that: The question-and-answer container sends the question to be answered to the large language question-and-answer model sequence corresponding to the question to be answered, and generates question-and-answer content, including: The question-and-answer container decomposes the question to be answered into sub-questions in the corresponding fields, and obtains a sequence of sub-questions in the corresponding fields according to the order of the fields in which the questions are answered. According to the sequence of sub-questions in the corresponding fields, the sub-questions in the corresponding fields are sent to the large language question-and-answer model sequence of the corresponding questions to be answered. According to the question-and-answer results returned by the large language question-and-answer model and the next sub-question in the corresponding field, they are sent to the next large language question-and-answer model until the question-and-answer of all sub-questions in the corresponding fields is completed and the question-and-answer content is obtained.

6. An intelligent question-answering device based on cognitive reasoning, characterized in that: The intelligent question-answering method based on cognitive reasoning described in any one of claims 1-5 includes a communication device, a delay test module, a data processing module and an information input module; the communication device, delay test module and information input module are respectively connected to the data processing module.

7. Intelligent question-answering system based on cognitive reasoning, characterized by: The intelligent question-answering device based on cognitive reasoning as claimed in claim 6 includes a cloud model calling server and a communication device; The intelligent question-answering device based on cognitive reasoning is connected to the cloud model calling server through a communication device.

Images