Scientific and technological consultation artificial intelligence communication equipment and heat dissipation auxiliary assembly

Abstract

The invention relates to the technical field of artificial intelligence equipment, and discloses science and technology consultation artificial intelligence communication equipment, which comprises a user interaction module used for receiving information input by a user and outputting a consultation result at the same time, and the input information comprises a problem of the user and background information of the user. According to the method, word segmentation, part-of-speech tagging and named entity recognition are carried out through the background information analysis unit by applying a natural language processing technology, the information understanding accuracy is improved, a foundation is laid for subsequent analysis, the preference modeling unit adopts a K-means clustering algorithm, and a clustering target function is iteratively optimized through historical behavior data collection, feature extraction, dimension reduction processing and iterative optimization. The demand prediction unit is used for constructing a user preference model, accurately identifying a user preference type and providing personalized consultation service, and the demand prediction unit is used for collecting consultation behavior data by using an autoregression integral moving average model, determining parameters, calculating predicted values, predicting potential demands and providing comprehensive consultation service.

Description

Technical Field

[0001] The present invention relates to the technical field of artificial intelligence equipment, and in particular to a technology consulting artificial intelligence communication device and a heat dissipation auxiliary component. Background Art

[0002] In the current field of scientific and technological consulting, existing systems generally rely on pre-set question-and-answer templates and databases for information retrieval and feedback. While this model can meet basic user needs to a certain extent, due to a lack of in-depth understanding of users' specific backgrounds and needs, the advice and solutions provided are often overly generalized and fail to truly solve users' real problems. When using these systems, users often need to spend a considerable amount of time sifting and discerning through vast amounts of information, which not only increases users' time costs but also reduces the overall efficiency of consultations.

[0003] In addition to the lack of personalized service, existing technology consulting and exchange equipment also suffers from hardware design flaws, particularly in heat dissipation. As processing power and functionality increase, equipment generates significant heat during extended operation. If heat dissipation is inadequate, rising internal temperatures can lead to performance degradation and even hardware failure, impacting device stability and lifespan. Summary of the Invention

[0004] (1) Technical problems solved

[0005] In response to the shortcomings of the existing technology, the present invention provides a scientific and technological consulting artificial intelligence communication device and a heat dissipation auxiliary component, which has the advantages of being able to provide customized scientific and technological consulting services according to the specific needs of users, thereby solving the above-mentioned technical problems.

[0006] (2) Technical solution

[0007] To achieve the above-mentioned purpose of providing customized scientific and technological consulting services according to the specific needs of users and having good heat dissipation performance, the present invention provides the following technical solutions: a scientific and technological consulting artificial intelligence communication device, including a user interaction module for receiving information input by a user and outputting a consulting result, wherein the input information includes the user's question and the user's background information;

[0008] Personalized Analysis Module: This module is connected to the User Interaction Module and includes a Background Information Parsing Unit, a Question Relevance Analysis Unit, a Preference Modeling Unit, and a Demand Forecasting Unit. The Background Information Parsing Unit is used to conduct in-depth analysis of the background information provided by the user. The Question Relevance Analysis Unit uses an association rule mining algorithm to analyze the potential connection between the user's question and the background information. The Preference Modeling Unit uses a clustering algorithm in machine learning to construct a user preference model. The Demand Forecasting Unit is used to predict other potential related needs of the user to provide more comprehensive consulting services.

[0009] Knowledge base module: It is connected to the personalized analysis module and is used to store rich scientific and technological knowledge data;

[0010] Intelligent reasoning module: It is connected to the personalized analysis module and the knowledge base module respectively. The intelligent reasoning module uses logical reasoning algorithms and expert system reasoning rules to perform intelligent reasoning and generate preliminary consulting suggestions;

[0011] Feedback optimization module: It is connected to the intelligent reasoning module and is used to optimize and adjust the preliminary consulting suggestions using a gradient descent algorithm, generate final consulting suggestions, and output the final consulting suggestions to the user interaction module.

[0012] Preferably, the background information parsing unit uses natural language processing technology to perform word segmentation, part-of-speech tagging and named entity recognition on the background information provided by the user.

[0013] Preferably, the clustering algorithm used by the preference modeling unit is the K-means clustering algorithm, which is expressed as follows:

[0014]

[0015] Among them, J is the clustering objective function, k is the number of clusters, n is the number of data points, represents the i-th data point in the j-th cluster, c j is the centroid of the jth cluster, and the clustering objective function J is iteratively optimized to build the user preference model.

[0016] Preferably, the demand forecasting unit uses an autoregressive integral moving average model in time series analysis to forecast user potential demand. The expression of the autoregressive integral moving average model is as follows:

[0017] Y t =c+φ1Y t-1 +φ1Y t-2 +...+φ p Y t-p +θ1∈ t-1 +θ1∈t-2 +...+θ q ∈ t-q +∈ t

[0018] Among them, Y t is the value of the time series at time t, c is the constant term, and p is the order of the autoregressive term, that is, the number of lagged observations or lagged predictors included in the model, φ1, φ2, ...φ p is the autoregressive coefficient, q is the order of the moving average term, that is, the number of lagged error terms included in the model, θ1, θ2, ... θ q is the moving average coefficient, ∈ t is the error term, representing the random shock or white noise at time t.

[0019] Preferably, the knowledge base module uses an inverted index structure to store scientific and technological knowledge data, and the knowledge base module has an automatic update program.

[0020] Preferably, the feedback optimization module is further provided with a user feedback classification submodule, and the submodule is capable of classifying user feedback information.

[0021] The present invention also provides a heat dissipation auxiliary component, including a heat dissipation fan installed inside the shell of the artificial intelligence AC device, the end face of the heat dissipation fan is tightly attached to the auxiliary plate, and a plurality of conical cylinders are fixedly connected to the end face of the auxiliary plate.

[0022] Preferably, a conical vent is opened inside the conical cylinder, buckles are fixedly connected to both sides of the auxiliary plate, a clamping plate is fixedly connected to the outer surface of the cooling fan, and the buckle and the clamping plate are clamped to each other.

[0023] Compared with the prior art, the present invention provides a scientific and technological consulting artificial intelligence communication device and a heat dissipation auxiliary component, which has the following beneficial effects:

[0024] 1. The present invention provides a technology consulting artificial intelligence communication device and heat dissipation auxiliary component. The background information analysis unit uses natural language processing technology to perform word segmentation, part-of-speech tagging and named entity recognition, thereby improving the accuracy of information understanding and laying the foundation for subsequent analysis. The preference modeling unit adopts the K-means clustering algorithm to build a user preference model by collecting historical behavior data, feature extraction, dimensionality reduction processing and iterative optimization of the clustering objective function, accurately identifying user preference types and providing personalized consulting services. The demand forecasting unit uses the autoregressive integral sliding average model to collect consulting behavior data, determine parameters and calculate predicted values, predict potential demand, and provide comprehensive consulting services; the feedback optimization module uses the gradient descent algorithm to optimize consulting suggestions, and the user feedback classification submodule classifies feedback information, which helps to understand user evaluation expectations, clarify improvement directions, and enhance user experience.

[0025] 2. The present invention provides a scientific and technological consulting artificial intelligence communication device and a heat dissipation auxiliary component. The heat dissipation auxiliary component cooperates with a heat dissipation fan, an auxiliary plate and a conical vent to accelerate the air flow speed based on the principle of fluid continuity to remove heat and improve heat dissipation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a logic block diagram between the various modules of the present invention;

[0027] Figure 2 This is a logic block diagram of the personalized analysis module in the present invention;

[0028] Figure 3 Schematic diagram of the exploded view of the heat dissipation auxiliary component in the present invention.

[0029] Among them: 1. Cooling fan; 2. Auxiliary plate; 3. Conical cylinder; 4. Conical vent; 5. Buckle; 6. Clamping plate. DETAILED DESCRIPTION

[0030] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0031] See also Figure 1-Figure 3 , a technology consulting artificial intelligence communication device, including a user interaction module, for receiving information input by a user and outputting a consulting result at the same time, the input information including the user's question and the user's background information;

[0032] Personalized Analysis Module: This module is connected to the User Interaction Module and includes a Background Information Parsing Unit, a Question Relevance Analysis Unit, a Preference Modeling Unit, and a Demand Forecasting Unit. The Background Information Parsing Unit is used to conduct in-depth analysis of the background information provided by the user. The Question Relevance Analysis Unit uses an association rule mining algorithm to analyze the potential connection between the user's question and the background information. The Preference Modeling Unit uses a clustering algorithm in machine learning to build a user preference model. The Demand Forecasting Unit is used to predict other potential related needs of the user to provide more comprehensive consulting services.

[0033] Knowledge base module: It is connected to the personalized analysis module and is used to store rich scientific and technological knowledge data;

[0034] Intelligent reasoning module: It is connected to the personalized analysis module and the knowledge base module respectively. The intelligent reasoning module uses logical reasoning algorithms and expert system reasoning rules to perform intelligent reasoning and generate preliminary consulting suggestions;

[0035] Feedback optimization module: It is connected to the intelligent reasoning module and is used to optimize and adjust the preliminary consulting suggestions using algorithms such as gradient descent, generate final consulting suggestions, and output the final consulting suggestions to the user interaction module.

[0036] Specifically, the background information parsing unit uses natural language processing technology to perform word segmentation, part-of-speech tagging, and named entity recognition on the background information provided by the user.

[0037] The advantage is that in the science and technology consulting artificial intelligence communication equipment, background information analysis is implemented through natural language processing technology. When the user enters the background information, word segmentation is performed first, such as splitting the relevant sentences into multiple words, and then part-of-speech tagging is performed to clarify the grammatical function of the words, and then named entity recognition is performed to highlight important information such as professional terms; this can improve the accuracy of information understanding, avoid ignoring key details, accurately grasp the semantics, and thus provide a reliable basis for subsequent analysis; it can also enhance personalized service capabilities, and after accurately understanding the user's background, it can provide consulting advice that meets the needs; at the same time, it can optimize the equipment processing efficiency, and structured data facilitates subsequent correlation analysis and other operations, reducing the calculation process, making the equipment run more efficiently, and improving the overall consulting service quality of the equipment.

[0038] Specifically, the clustering algorithm used by the preference modeling unit is the K-means clustering algorithm, which is expressed as follows:

[0039]

[0040] Among them, J is the clustering objective function, k is the number of clusters, n is the number of data points, represents the i-th data point in the j-th cluster, c j is the centroid of the jth cluster, and the clustering objective function J is iteratively optimized to build the user preference model.

[0041] The advantage is that the preference modeling unit first collects the user's historical behavior data, such as browsing history, search history, and consultation history, and performs feature extraction and dimensionality reduction on these data. Subsequently, the K-means clustering algorithm is applied to divide the users into different clusters. Each cluster represents a user preference type. The algorithm iteratively optimizes the clustering objective function J; the clustering objective function aims to minimize the distance between each data point and the centroid of the cluster to which it belongs. Through continuous iterative calculation, the algorithm finally determines the centroid position of each cluster, thereby constructing a user preference model. The advantage of using the K-means clustering algorithm is that it is computationally efficient and easy to implement. It can effectively cluster users with similar characteristics together, helping the device to more accurately identify user preference types, and thus provide personalized consulting services that are more in line with user needs.

[0042] Specifically, the demand forecasting unit uses the autoregressive integral moving average model in time series analysis to predict user potential demand. The expression of the autoregressive integral moving average model is as follows:

[0043] Y t =c+φ1Y t-1 +φ1Y t-2 +...+φ p Y t-p +θ1∈ t-1 +θ1∈ t-2 +...+θ q ∈ t-q +∈ t

[0044] Among them, Y t is the value of the time series at time t, c is the constant term, and p is the order of the autoregressive term, that is, the number of lagged observations or lagged predictors included in the model, φ1, φ2, ...φ p is the autoregressive coefficient, q is the order of the moving average term, that is, the number of lagged error terms included in the model, θ1, θ2, ... θ q is the moving average coefficient, ∈ t is the error term, representing the random shock or white noise at time t.

[0045] The advantage is that the demand forecasting unit adopts the autoregressive integrated moving average model and is implemented as follows: first, collect the user's consultation behavior data over a period of time, such as the time of consultation, the subject category of consultation, etc., and use these data as a time series. Then, determine the constant term, the order of the autoregressive term, and the order of the moving average term in the model. This can be determined through data analysis or experience. Then, estimate the autoregressive coefficients φ1, φ2, ...φ based on historical data. p and moving average coefficients θ1, θ2, ...θ q ; Afterwards, the model is used to calculate the predicted value.

[0046] Specifically, the knowledge base module uses an inverted index structure to store scientific and technological knowledge data, and the knowledge base module has an automatic update program.

[0047] The advantage is that, for the inverted index structure, the text content in the scientific and technological knowledge data is first segmented, and each word or keyword is used as an index item, and then the document number or knowledge item identifier containing the index item is recorded to form an index table; in terms of the automatic update program, by setting a regular scanning mechanism, such as scanning authoritative scientific and technological data sources once a day or a week, such as professional databases, academic journal websites, etc., the latest scientific and technological knowledge content is obtained; at the same time, text comparison technology is used to identify new or updated knowledge parts, integrate them into the knowledge base, and update the inverted index accordingly; the advantage of this is that the inverted index structure can greatly improve the speed of knowledge retrieval, and when users ask questions, they can quickly locate relevant knowledge and improve the efficiency of consultation response; the automatic update program ensures that the knowledge base keeps pace with the times and always contains the latest scientific and technological achievements, technology trends and other information, providing users with accurate and cutting-edge consulting services, enhancing the authority and practicality of equipment in the field of scientific and technological consulting, and better meeting users' growing demand for scientific and technological knowledge.

[0048] Specifically, the feedback optimization module is further provided with a user feedback classification submodule, which is capable of classifying user feedback information.

[0049] The advantage is that the feedback optimization module optimizes and adjusts the preliminary consulting suggestions generated by the intelligent reasoning module by using the gradient descent algorithm, so that the final output consulting suggestions are more accurate and meet user needs; secondly, the user feedback classification submodule in the feedback optimization module can classify user feedback information, such as distinguishing between positive feedback, negative feedback, suggestion feedback and problem feedback; this classification process helps the device to fully understand the user's evaluation and expectations of the consulting service, identify the links where the user is dissatisfied or has problems, and provide a clear direction for subsequent improvements.

[0050] The usage process of the device is as follows: the user inputs content including questions and background information through the user interaction module; the background information parsing unit in the personalized analysis module uses natural language processing technology to perform word segmentation, part-of-speech tagging and named entity recognition on the background information; the problem association analysis unit uses the association rule mining algorithm to analyze the potential connection between the question and the background information; the preference modeling unit uses the K-means clustering algorithm to build a user preference model; the demand forecasting unit uses the autoregressive integral moving average model to predict potential demand; the knowledge base module uses an inverted index structure to store scientific and technological knowledge data and keeps the knowledge updated through an automatic update program; the intelligent reasoning module uses logical reasoning algorithms and expert system reasoning rules to generate preliminary consulting suggestions; the feedback optimization module uses the gradient descent algorithm to optimize the preliminary consulting suggestions, and its user feedback classification submodule classifies the user feedback information, and finally outputs the optimized final consulting suggestions to the user through the user interaction module.

[0051] The present invention also provides a heat dissipation auxiliary component, including a cooling fan 1 installed inside the shell of the artificial intelligence AC device, the end face of the cooling fan 1 is tightly attached to the auxiliary plate 2, a plurality of conical cylinders 3 are fixedly connected to the end face of the auxiliary plate 2, a conical vent 4 is opened inside the conical cylinder 3, buckles 5 are fixedly connected on both sides of the auxiliary plate 2, a clamping plate 6 is fixedly connected to the outer surface of the cooling fan 1, and the buckle 5 and the clamping plate 6 are clamped to each other.

[0052] By installing the cooling fan 1 inside the device casing, cooling holes are also opened on the outer surface of the device casing. When the cooling fan 1 is started, air can be supplied to the inside of the device casing 1. The wind will pass through the multiple conical cylinders 3 of the auxiliary plate 2. Since the conical vents 4 have a conical structure, the inlet is larger and the outlet is smaller. According to the principle of fluid continuity, when air enters from the larger inlet and flows to the smaller outlet, the flow rate will accelerate, which increases the air flow speed through the conical vents 4, can take away heat more quickly, and improve the heat dissipation efficiency.

[0053] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A technology consulting artificial intelligence communication device, characterized by: include, A user interaction module is used to receive information input by the user and output consultation results at the same time, wherein the input information includes the user's question and the user's background information; Personalized Analysis Module: This module is connected to the User Interaction Module and includes a Background Information Parsing Unit, a Question Relevance Analysis Unit, a Preference Modeling Unit, and a Demand Forecasting Unit. The Background Information Parsing Unit is used to conduct in-depth analysis of the background information provided by the user. The Question Relevance Analysis Unit uses an association rule mining algorithm to analyze the potential connection between the user's question and the background information. The Preference Modeling Unit uses a clustering algorithm in machine learning to construct a user preference model. The Demand Forecasting Unit is used to predict other potential related needs of the user to provide more comprehensive consulting services. Knowledge base module: It is connected to the personalized analysis module and is used to store rich scientific and technological knowledge data; Intelligent reasoning module: It is connected to the personalized analysis module and the knowledge base module respectively. The intelligent reasoning module uses logical reasoning algorithms and expert system reasoning rules to perform intelligent reasoning and generate preliminary consulting suggestions; Feedback optimization module: It is connected to the intelligent reasoning module and is used to optimize and adjust the preliminary consulting suggestions using a gradient descent algorithm, generate final consulting suggestions, and output the final consulting suggestions to the user interaction module.

2. The technology consulting artificial intelligence communication device according to claim 1, characterized in that: The background information parsing unit uses natural language processing technology to perform word segmentation, part-of-speech tagging and named entity recognition on the background information provided by the user.

3. The technology consulting artificial intelligence communication device according to claim 1, characterized in that: The clustering algorithm used by the preference modeling unit is the K-means clustering algorithm, which is expressed as follows: Among them, J is the clustering objective function, k is the number of clusters, n is the number of data points, represents the i-th data point in the j-th cluster, c j is the centroid of the jth cluster, and the clustering objective function J is iteratively optimized to build the user preference model.

4. The technology consulting artificial intelligence communication device according to claim 1, characterized in that: The demand forecasting unit uses the autoregressive integral moving average model in time series analysis to predict user potential demand. The expression of the autoregressive integral moving average model is as follows: Y t =c+φ1Y t-1 +φ1Y t-2 +...+φ p Y t-p +θ1∈ t-1 +θ1∈ t-2 +...+θ q ∈ t-q +∈ t Among them, Y t is the value of the time series at time t, c is the constant term, and p is the order of the autoregressive term, that is, the number of lagged observations or lagged predictors included in the model, φ1, φ2, ...φ p is the autoregressive coefficient, q is the order of the moving average term, that is, the number of lagged error terms included in the model, θ1, θ2, ... θ q is the moving average coefficient, ∈ t is the error term, representing the random shock or white noise at time t.

5. The technology consulting artificial intelligence communication device according to claim 1, characterized in that: The knowledge base module adopts an inverted index structure to store scientific and technological knowledge data, and the knowledge base module has an automatic updating program.

6. The technology consulting artificial intelligence communication device according to claim 1, characterized in that: The feedback optimization module is further provided with a user feedback classification submodule, which is capable of classifying user feedback information.

7. A heat dissipation auxiliary component, suitable for use in a scientific and technological consulting artificial intelligence communication device according to any one of claims 1 to 6, characterized in that: The invention comprises a cooling fan (1) installed inside a housing of an artificial intelligence AC device, wherein the end surface of the cooling fan (1) is in close contact with an auxiliary plate (2), and a plurality of conical cylinders (3) are fixedly connected to the end surface of the auxiliary plate (2).

8. The heat dissipation auxiliary component according to claim 7, characterized in that: A conical vent (4) is provided inside the conical cylinder (3), buckles (5) are fixedly connected to both sides of the auxiliary plate (2), and a clamping plate (6) is fixedly connected to the outer surface of the heat dissipation fan (1), and the buckle (5) and the clamping plate (6) are clamped to each other.

Images