Method, device and equipment for evaluating hotspot technology based on generative artificial intelligence

Abstract

The present application relates to the technical field of hotspot technology evaluation, and particularly relates to a hotspot technology evaluation method, device and equipment based on generative artificial intelligence, which responds to a hotspot technology keyword, queries technical literature corresponding to the hotspot technology keyword and metric data corresponding to the technical literature through a target search engine; analyzes an importance centrality index of the hotspot technology keyword compared to the technical literature through a preset importance evaluation model; calculates hotness data of the technical literature according to the importance centrality index and the metric data; generates a hotspot technology hotness data change curve based on the hotness data; performs hotspot technology prediction evaluation based on the hotspot technology hotness data change curve, and generates a hotspot technology evaluation report, which analyzes a hotspot technology keyword input by a user through a generative artificial intelligence model, and provides efficient hotspot technology analysis results.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of hotspot technology evaluation, in particular to a hotspot technology evaluation method, device and equipment based on generative artificial intelligence. BACKGROUND

[0002] In order to improve the speed of technology development and innovation, research will be conducted on existing hotspot technologies at the initial stage of research, so as to select and dispatch R&D resources and speed up the R&D progress. The hotspot technology refers to the technology topic with a high number of browsing times or comments in a certain period of time. The popularity index of the technology topic is usually used to evaluate and analyze the popularity of news topics in a certain period of time.

[0003] However, the determination of the hotspot technology requires a large amount of data support and analysis process, and has high timeliness, which usually occurs in a short period of time. The traditional hotspot technology analysis process has low efficiency and poor timeliness, which cannot meet the needs of users.

[0004] The above content is only used to assist in understanding the technical solutions of the present application and does not represent the acknowledgement of the above content as prior art. SUMMARY

[0005] The main purpose of the present application is to provide a hotspot technology evaluation method, device and equipment based on generative artificial intelligence, which aims to solve the technical problems of low analysis and identification efficiency and low timeliness of the existing hotspot technology.

[0006] To achieve the above purpose, the present application provides a hotspot technology evaluation method based on generative artificial intelligence, which comprises the following steps:

[0007] In response to the hotspot technology keyword, the technical literature corresponding to the hotspot technology keyword and the measurement data corresponding to the technical literature are queried through a target search engine;

[0008] The importance centrality index of the hotspot technology keyword compared with the technical literature is analyzed by a preset importance evaluation model;

[0009] The popularity data of the technical literature is calculated according to the importance centrality index and the measurement data;

[0010] The hotspot technology popularity data change curve is generated based on the popularity data;

[0011] The hotspot technology prediction evaluation is carried out based on the hotspot technology popularity data change curve, and the hotspot technology evaluation report is generated.

[0012] Optionally, the importance centrality index of the hotspot technology keyword compared with the technical literature is analyzed by a preset importance evaluation model, which comprises:

[0013] perform hierarchical clustering on the technical literature by a hierarchical clustering model to obtain a plurality of clustering clusters;

[0014] determine an attribution keyword of each clustering cluster;

[0015] calculate an importance centrality index according to the attribution keyword and the hot technology keyword by a preset importance evaluation model.

[0016] Optionally, before the calculating the importance centrality index according to the attribution keyword and the hot technology keyword by the preset importance evaluation model, the method further comprises:

[0017] generating a hot technology extended keyword corresponding to the hot technology keyword by a Word2Vector model;

[0018] taking the hot technology extended keyword and the hot technology keyword as a target hot technology keyword;

[0019] calculating the importance centrality index according to the target hot technology keyword and the hot technology keyword by the preset importance evaluation model.

[0020] Optionally, the importance centrality index at least comprises a degree centrality, a betweenness centrality, a closeness centrality and a eigenvector centrality;

[0021] The calculating the importance centrality index according to the target hot technology keyword and the hot technology keyword by the preset importance evaluation model comprises:

[0022] counting a cluster data amount of each clustering cluster and a total amount of clustering clusters;

[0023] performing relevance sorting on the attribution keyword according to the cluster data amount to obtain a relevance sorting result of each attribution keyword, the relevance sorting result representing a relevance degree of the attribution keyword compared with the technical literature;

[0024] Correspondingly, a calculation formula of the degree centrality is:

[0025]

[0026] wherein, vi is the target hot technology keyword, ki is an ordering rank coefficient of the target hot technology keyword in the relevance sorting result, and N is a total number of clustering clusters;

[0027] A calculation formula of the betweenness centrality is:

[0028]

[0029]

[0030] in, is the betweenness factor of the target hot technology keyword before normalization, gij represents the difference in cluster data volume between two keywords in the correlation ranking result, gij(vi) is the difference between the first cluster data volume of the i-th keyword to the cluster corresponding to the target hot technology keyword and the second cluster data volume of the j-th keyword to the cluster corresponding to the target hot technology keyword in the correlation ranking result, and N is the total number of clusters.

[0031] The formula for calculating proximity centrality is:

[0032]

[0033] Where, dij is the cluster data size of the cluster closest to the target hot technology keyword in the correlation ranking results, and N is the total number of clusters;

[0034] The formula for calculating the eigenvector centrality is:

[0035]

[0036] in, Let aij be a constant, aij be the feature vector constructed from the target hot technical keywords and the technical documents, and xj be the centrality score of each attributed keyword.

[0037] Optionally, the metrics data include at least: citation metrics, download metrics, and read metrics;

[0038] The calculation of the popularity data of the technical documents based on the importance centrality index and the metric data includes:

[0039]

[0040] in, This serves as a reading indicator for the technical literature. This serves as a download metric for the technical document. The citation metrics for this technical document are as follows: N1 is the total number of reads of all technical documents in the database associated with the target search engine; N2 is the total number of downloads of all technical documents in the database associated with the target search engine; and N3 is the total number of citations of all technical documents in the database associated with the target search engine.

[0041] Optionally, the step of predicting and evaluating hot technologies based on the trend curve of the hot technology popularity data, and generating a hot technology evaluation report, includes:

[0042] Based on a preset time scale, the heat data change curves of the hot technologies are divided to obtain multiple data change curves.

[0043] Filter the data change curves of each segment to obtain the corresponding multi-segment target data change curves;

[0044] Calculate the mean of the target data change curve for each segment, and the rate of change of data within adjacent time periods;

[0045] When the rate of change of data exceeds a preset threshold in two consecutive time periods, the hot technology keywords corresponding to the hot technology popularity data change curve are determined to be future hot technologies, and a hot technology evaluation report is generated based on the rate of change of data and the hot technology keywords.

[0046] Furthermore, to achieve the above objectives, the present invention also proposes a hotspot technology evaluation device based on generative artificial intelligence, the hotspot technology evaluation device based on generative artificial intelligence comprising:

[0047] The search module is used to respond to hot technical keywords and search for technical documents and measurement data corresponding to the hot technical keywords through the target search engine.

[0048] The analysis module is used to analyze the importance centrality index of the hot technical keywords relative to the technical documents through a preset importance assessment model;

[0049] The calculation module is used to calculate the popularity data of the technical documents based on the importance centrality index and the measurement data;

[0050] The generation module is used to generate a hotspot technology popularity data change curve based on the popularity data;

[0051] The evaluation module is used to predict and evaluate hot technologies based on the trend curve of the hot technology popularity data, and generate a hot technology evaluation report.

[0052] Furthermore, to achieve the above objectives, the present invention also proposes a hotspot technology evaluation device based on generative artificial intelligence. The hotspot technology evaluation device based on generative artificial intelligence includes: a memory, a processor, and a hotspot technology evaluation program based on generative artificial intelligence stored in the memory and executable on the processor. The hotspot technology evaluation program based on generative artificial intelligence is configured to implement the steps of the hotspot technology evaluation method based on generative artificial intelligence as described above.

[0053] Furthermore, to achieve the above objectives, the present invention also proposes a storage medium storing a hotspot technology evaluation program based on generative artificial intelligence, wherein when the hotspot technology evaluation program based on generative artificial intelligence is executed by a processor, it implements the steps of the hotspot technology evaluation method based on generative artificial intelligence as described above.

[0054] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the hotspot technology evaluation method based on generative artificial intelligence as described above.

[0055] This invention responds to trending technical keywords by querying the corresponding technical documents and their corresponding metrics using a target search engine; it analyzes the importance centrality index of the trending technical keywords relative to the technical documents using a preset importance assessment model; it calculates the popularity data of the technical documents based on the importance centrality index and the metrics data; it generates a trending technical popularity data change curve based on the popularity data; it performs trending technical prediction and assessment based on the trending technical popularity data change curve, and generates a trending technical assessment report. By using a generative artificial intelligence model to analyze the trending technical keywords input by the user, it provides efficient trending technical analysis results, avoiding the technical problems of low efficiency and timeliness in the analysis and identification of trending technologies in existing technologies. Attached Figure Description

[0056] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0057] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0058] Figure 1 This is a flowchart illustrating the first embodiment of the hotspot technology evaluation method based on generative artificial intelligence of the present invention.

[0059] Figure 2 This is a flowchart illustrating the second embodiment of the hotspot technology evaluation method based on generative artificial intelligence of the present invention.

[0060] Figure 3 This is a structural block diagram of the first embodiment of the hotspot technology evaluation device based on generative artificial intelligence of the present invention;

[0061] Figure 4 This is a schematic diagram of the structure of a hot technology evaluation device based on generative artificial intelligence in the hardware operating environment involved in the embodiments of the present invention.

[0062] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0063] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0064] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0065] Based on this, embodiments of the present invention provide a method for evaluating hot technologies based on generative artificial intelligence, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of a hotspot technology evaluation method based on generative artificial intelligence according to the present invention.

[0066] In this embodiment, the hotspot technology evaluation method based on generative artificial intelligence includes:

[0067] Step S10: In response to hot technical keywords, query the technical documents corresponding to the hot technical keywords and the measurement data corresponding to the technical documents through the target search engine.

[0068] Step S20: Analyze the importance centrality index of the hot technical keywords relative to the technical documents using a preset importance assessment model.

[0069] Step S30: Calculate the popularity data of the technical documents based on the importance centrality index and the measurement data.

[0070] Step S40: Generate a hotspot technology hotspot data change curve based on the hotspot data.

[0071] Step S50: Based on the hot technology popularity data change curve, perform hot technology prediction and evaluation, and generate a hot technology evaluation report.

[0072] It should be noted that the executing entity of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, personal computer, mobile phone, etc., or an electronic device or control computer that can realize the above functions. The following uses a control computer as an example to describe this embodiment and the following embodiments.

[0073] It should be understood that hot technical keywords refer to high-frequency technical terms entered by users, such as technical terms from different fields like intelligent robots, security sandboxes, and deep synthesis detection. The target search engine is used to search for technical literature related to hot technical keywords. Through citation analysis technology, it mines representative literature in a specific field and arranges the representative literature in chronological order to form the main outline of the field. Through this literature sequence, the research progress in the field can be summarized, thereby clarifying the technical development roadmap and progress of the field.

[0074] The measurement data includes, but is not limited to, the number of technical documents published, the year of publication, and the download, reading, and citation metrics of each document. This embodiment does not impose specific limitations on these metrics.

[0075] In the specific implementation process, since a technical document may use more than one specific solution, for example, multiple models may be used as references for horizontal comparison of effects to highlight the effect of a certain algorithm model. Therefore, in order to evaluate the importance of hot technical keywords in technical documents, this embodiment calculates the importance centrality index of hot technical keywords in each technical document through an importance evaluation model. The importance centrality index includes degree centrality, betweenness centrality, proximity centrality, and eigenvector centrality, which are used to characterize the importance and relevance of hot technical keywords in technical documents.

[0076] Furthermore, the metrics data include at least: citation metrics, download metrics, and read metrics;

[0077] The calculation of the popularity data of the technical documents based on the importance centrality index and the metric data includes:

[0078]

[0079] in, This serves as a reading indicator for the technical literature. This serves as a download metric for the technical document. The citation metrics for this technical document are as follows: N1 is the total number of reads of all technical documents in the database associated with the target search engine; N2 is the total number of downloads of all technical documents in the database associated with the target search engine; N3 is the total number of citations of all technical documents in the database associated with the target search engine; and K is the number of databases linked to by the target search engine. These are the weighting coefficients of the importance centrality index.

[0080] Specifically, to determine whether a technology is a hot technology, one can analyze the changes in the popularity of the literature within a fixed period of time. Popularity data is used to characterize the attention given to technical literature within a unit of time. Generally, the higher the attention given within a unit of time, the higher the popularity, and the more likely it is to be determined as a hot technology. Therefore, in this embodiment, the popularity data of technical literature is calculated by combining the number of citations, downloads, and reads of the literature. Then, the popularity data is weighted by the importance centrality index assigned by hot keywords to calculate the final popularity data.

[0081] Because trending technologies have a short lifespan and can generate a lot of attention in a short period of time, but the development of any technology follows its own path, this embodiment will statistically analyze the trending data of technical documents associated with each keyword to form a continuous trending data curve. The slope of the curve will be used to predict and evaluate trending technologies, so as to determine the documents and technical content with high attention in each field, reduce the user analysis process, and shorten the R&D process.

[0082] Furthermore, the process of predicting and evaluating hot technologies based on the trend curves of the hot technology popularity data, and generating a hot technology evaluation report, includes:

[0083] Based on a preset time scale, the heat data change curves of the hot technologies are divided to obtain multiple data change curves.

[0084] Filter the data change curves of each segment to obtain the corresponding multi-segment target data change curves;

[0085] Calculate the mean of the target data change curve for each segment, and the rate of change of data within adjacent time periods;

[0086] When the rate of change of data exceeds a preset threshold in two consecutive time periods, the hot technology keywords corresponding to the hot technology popularity data change curve are determined to be future hot technologies, and a hot technology evaluation report is generated based on the rate of change of data and the hot technology keywords.

[0087] It should be noted that, considering the high degree of short-term variation in literature within certain fixed periods, such as the sharp increase in citation and download metrics for some literatures due to the publication of a large number of papers each year during graduation season, this embodiment can filter the popularity data change curve to reduce the impact of data volatility on the evaluation process. For the filtered data change curve, the mean of each segment of the curve is calculated as the count of data change. When the data change rate is greater than a preset threshold in two consecutive periods, it is determined that the hot technology keywords corresponding to the hot technology popularity data change curve are likely to be future hot technologies.

[0088] This embodiment responds to trending technical keywords by querying the corresponding technical documents and their corresponding metrics using a target search engine; it analyzes the importance centrality index of the trending technical keywords relative to the technical documents using a preset importance assessment model; it calculates the popularity data of the technical documents based on the importance centrality index and the metrics data; it generates a trending technical popularity data change curve based on the popularity data; it performs trending technical prediction and assessment based on the trending technical popularity data change curve, and generates a trending technical assessment report; and it provides efficient trending technical analysis results by analyzing the user-input trending technical keywords using a generative artificial intelligence model.

[0089] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 Step S20 includes:

[0090] Step S201: Perform hierarchical clustering on the technical documents using a hierarchical clustering model to obtain multiple clusters.

[0091] Step S202: Determine the keywords to which each cluster belongs.

[0092] Step S203: Calculate the importance centrality index based on the attribution keywords and the hot technical keywords using a preset importance assessment model.

[0093] It should be noted that since the searched technical documents are only related to the input search terms, the specific solutions may differ significantly, and there are differences in the application technologies in subdivided fields. In order to reflect the characteristics of specific technologies, it is generally necessary to arrange experimental data of multiple similar technologies in a single document for horizontal comparison. As such, it can be seen that each technical document involves a large number of fields and related keywords. In order to improve the accuracy and reliability of the calculation of the importance centrality index of hot technical keywords relative to technical documents, this embodiment first performs hierarchical clustering on each technical document to obtain the associated clusters of each technical document, and determines the keywords belonging to each cluster. The importance centrality index is then calculated based on the keywords of each cluster and the input hot technical keywords.

[0094] Furthermore, before calculating the importance centrality index based on the attribution keywords and the hot technical keywords using a preset importance assessment model, the method further includes:

[0095] The hot technology extended keywords corresponding to the hot technology keywords are generated using the Word2Vector model;

[0096] The target hot technology keywords are derived from the expanded keywords of the hot technology and the hot technology keywords themselves.

[0097] The importance centrality index is calculated based on the target hot technology keywords and the hot technology keywords using a preset importance assessment model.

[0098] Importance centrality metrics include at least: degree centrality, betweenness centrality, proximity centrality, and eigenvector centrality.

[0099] Accordingly, the step of calculating the importance centrality index based on the target hot technology keywords and the hot technology keywords using a preset importance assessment model includes:

[0100] Calculate the cluster data volume and total number of clusters for each cluster;

[0101] The association keywords are sorted according to the cluster data volume to obtain the association ranking results of each association keyword. The association ranking results represent the degree of relevance of the association keywords to the technical documents.

[0102] In the specific implementation, considering that the input hot technical keywords may have multiple names due to differences in language, expression, or professional level, for example, in the field of biological cultivation, "tomato" and "tomato" are actually the same variety, but they are different in name, which may cause interference in the subsequent index calculation process. In order to improve the accuracy of the subsequent calculation of the centrality index, this embodiment first generates hot technical extended keywords corresponding to the hot technical keywords through the Word2Vector model, improves the correlation between technical documents and keywords, and thus improves the reliability of the importance centrality index calculation.

[0103] In addition, generally speaking, the larger the cluster data of a cluster, the stronger the correlation with the input keywords. This is an inevitable result of the search engine's retrieval of the database.

[0104] The formula for calculating degree centrality is:

[0105]

[0106] in, Targeting hot technology keywords, The ranking coefficient of the target hot technology keywords in the relevance ranking results, where N is the total number of clusters;

[0107] The formula for calculating betweenness centrality is:

[0108]

[0109]

[0110] in, The betweenness number of the target hot technology keywords before normalization. This represents the difference in cluster size between the clusters corresponding to two keywords in the association ranking results. N is the difference between the first cluster data volume of the cluster corresponding to the i-th keyword and the second cluster data volume of the cluster corresponding to the j-th keyword and the target hot technology keyword in the correlation ranking result, where N is the total number of clusters.

[0111] The formula for calculating proximity centrality is:

[0112]

[0113] in, N represents the cluster data size of the cluster closest to the target hot technology keyword in the correlation ranking results, where N is the total number of clusters.

[0114] The formula for calculating the eigenvector centrality is:

[0115]

[0116] in, It is a constant. Feature vectors are constructed by combining the target hot technology keywords with the aforementioned technical literature. The centrality score is the score for each keyword.

[0117] This embodiment performs hierarchical clustering of the technical documents using a hierarchical clustering model to obtain multiple clusters; determines the keywords belonging to each cluster; and calculates the importance centrality index based on the belonging keywords and the hot technical keywords using a preset importance assessment model, thereby reducing the interference of irrelevant documents on the subsequent calculation process and improving the reliability of the importance centrality index calculation.

[0118] This application also provides a hotspot technology evaluation device based on generative artificial intelligence, please refer to... Figure 3 The hotspot technology evaluation device based on generative artificial intelligence includes:

[0119] Search module 10 is used to respond to hot technical keywords and query the technical documents and measurement data corresponding to the hot technical keywords through the target search engine.

[0120] Analysis module 20 is used to analyze the importance centrality index of the hot technical keywords relative to the technical documents through a preset importance assessment model.

[0121] The calculation module 30 is used to calculate the popularity data of the technical documents based on the importance centrality index and the measurement data.

[0122] The generation module 40 is used to generate a hotspot technology hotspot data change curve based on the hotspot data.

[0123] The evaluation module 50 is used to predict and evaluate hot technologies based on the hot technology popularity data change curve, and generate a hot technology evaluation report.

[0124] In one embodiment, the analysis module 20 is further configured to perform hierarchical clustering on the technical documents using a hierarchical clustering model to obtain multiple clusters; determine the associated keywords of each cluster; and calculate the importance centrality index based on the associated keywords and the hot technical keywords using a preset importance assessment model.

[0125] In one embodiment, the analysis module 20 is further configured to generate hot technology extended keywords corresponding to the hot technology keywords through the Word2Vector model; use the hot technology extended keywords and the hot technology keywords as target hot technology keywords; and calculate the importance centrality index based on the target hot technology keywords and the hot technology keywords through a preset importance evaluation model.

[0126] In one embodiment, the analysis module 20 is further configured to count the cluster data volume and the total number of clusters for each cluster; and to perform a correlation ranking of the attribution keywords based on the cluster data volume to obtain a correlation ranking result for each attribution keyword, wherein the correlation ranking result characterizes the degree of correlation between the attribution keyword and the technical literature.

[0127] Accordingly, the formula for calculating degree centrality is:

[0128]

[0129] in, Targeting hot technology keywords, The ranking coefficient of the target hot technology keywords in the relevance ranking results, where N is the total number of clusters;

[0130] The formula for calculating betweenness centrality is:

[0131]

[0132]

[0133] in, The betweenness number of the target hot technology keywords before normalization. This represents the difference in cluster size between the clusters corresponding to two keywords in the association ranking results. N is the difference between the first cluster data volume of the cluster corresponding to the i-th keyword and the second cluster data volume of the cluster corresponding to the j-th keyword and the target hot technology keyword in the correlation ranking result, where N is the total number of clusters.

[0134] The formula for calculating proximity centrality is:

[0135]

[0136] in, N represents the cluster data size of the cluster closest to the target hot technology keyword in the correlation ranking results, where N is the total number of clusters.

[0137] The formula for calculating the eigenvector centrality is:

[0138]

[0139] in, It is a constant. Feature vectors are constructed by combining the target hot technology keywords with the aforementioned technical literature. The centrality score is the score for each keyword.

[0140] In one embodiment, the calculation module 30 is further configured to calculate the popularity data of the technical documents based on the importance centrality index and the metric data, including:

[0141]

[0142] in, This serves as a reading indicator for the technical literature. This serves as a download metric for the technical document. This serves as a citation indicator for the technical literature. The total number of reads of all technical documents in the database associated with the target search engine. This refers to the total number of downloads of all technical documents in the database associated with the target search engine. This refers to the total number of citations in all technical documents within the database associated with the target search engine. These are the weighting coefficients of the importance centrality index.

[0143] In one embodiment, the evaluation module 50 is further configured to divide the hot technology popularity data change curves based on a preset time scale to obtain multiple data change curve segments; filter each data change curve segment to obtain corresponding multiple target data change curve segments; calculate the mean of each target data change curve segment and the data change rate within adjacent time periods; when the data change rate is greater than a preset threshold in two consecutive time periods, determine that the hot technology keywords corresponding to the hot technology popularity data change curves are future hot technologies, and generate a hot technology evaluation report based on the data change rate and the hot technology keywords.

[0144] This application provides a hotspot technology evaluation device based on generative artificial intelligence. The hotspot technology evaluation device based on generative artificial intelligence includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the hotspot technology evaluation method based on generative artificial intelligence in the above embodiment 1.

[0145] The following is for reference. Figure 4 This document illustrates a structural schematic diagram of a hotspot technology evaluation device based on generative artificial intelligence suitable for implementing embodiments of this application. The hotspot technology evaluation device based on generative artificial intelligence in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 4 The illustrated hotspot technology evaluation device based on generative artificial intelligence is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0146] like Figure 4As shown, the hotspot technology evaluation device based on generative artificial intelligence may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 1002 or a program loaded from storage device 1003 into random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the hotspot technology evaluation device based on generative artificial intelligence. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the generative artificial intelligence-based hotspot technology evaluation device to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows a generative artificial intelligence-based hotspot technology evaluation device with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented alternatively.

[0147] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0148] The hot topic technology evaluation device based on generative artificial intelligence provided in this application, employing the hot topic technology evaluation method based on generative artificial intelligence in the above embodiments, can solve the technical problems of hot topic technology evaluation based on generative artificial intelligence. Compared with the prior art, the beneficial effects of the hot topic technology evaluation device based on generative artificial intelligence provided in this application are the same as the beneficial effects of the hot topic technology evaluation method based on generative artificial intelligence provided in the above embodiments, and other technical features in the hot topic technology evaluation device based on generative artificial intelligence are the same as the features disclosed in the method of the previous embodiment, and will not be repeated here.

[0149] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0150] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0151] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the hotspot technology evaluation method based on generative artificial intelligence in the above embodiments.

[0152] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0153] The aforementioned computer-readable storage medium may be included in a hot technology evaluation device based on generative artificial intelligence; or it may exist independently and not assembled into a hot technology evaluation device based on generative artificial intelligence.

[0154] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the aforementioned one or more programs, enable the generative artificial intelligence-based hot technology evaluation device to perform generative artificial intelligence-based hot technology evaluation.

[0155] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0156] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0157] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0158] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described hotspot technology evaluation method based on generative artificial intelligence, thereby solving the technical problem of hotspot technology evaluation based on generative artificial intelligence. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the hotspot technology evaluation method based on generative artificial intelligence provided in the above embodiments, and will not be repeated here.

[0159] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the hotspot technology evaluation method based on generative artificial intelligence as described above.

[0160] The computer program product provided in this application can solve the technical problem of hotspot technology evaluation based on generative artificial intelligence. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the hotspot technology evaluation method based on generative artificial intelligence provided in the above embodiments, and will not be repeated here.

[0161] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for evaluating hot technologies based on generative artificial intelligence, characterized in that, The hot technology evaluation method based on generative artificial intelligence includes: In response to trending technical keywords, the system searches for the technical documents corresponding to the trending technical keywords and the corresponding measurement data of the technical documents through the target search engine. The importance centrality index of the hot technical keywords relative to the technical literature was analyzed using a preset importance assessment model. The popularity data of the technical literature is calculated based on the importance centrality index and the metric data. Based on the aforementioned heat data, a heat data change curve for hotspot technology is generated; Based on the trend curve of the popularity data of the aforementioned hot technologies, a prediction and evaluation of hot technologies is performed, and a hot technology evaluation report is generated. The metrics include at least: citation metrics, download metrics, and read metrics, and the importance centrality metrics include at least: degree centrality, betweenness centrality, proximity centrality, and eigenvector centrality. The calculation of the popularity data of the technical documents based on the importance centrality index and the metric data includes: in, This serves as a reading indicator for the technical literature. This serves as a download metric for the technical document. This serves as a citation indicator for the technical literature. The total number of reads of all technical documents in the database associated with the target search engine. This refers to the total number of downloads of all technical documents in the database associated with the target search engine. This refers to the total number of citations in all technical documents within the database associated with the target search engine. These are the weighting coefficients of the importance centrality index. For degree centrality, For betweenness centrality, To approximate centrality, This refers to the eigenvector centrality.

2. The hot technology evaluation method based on generative artificial intelligence as described in claim 1, characterized in that, The analysis of the importance centrality index of the hot technical keywords relative to the technical literature using a preset importance assessment model includes: The technical documents were hierarchically clustered using a hierarchical clustering model to obtain multiple clusters. Determine the keywords to which each cluster belongs; The importance centrality index is calculated based on the attributed keywords and the hot technical keywords using a preset importance assessment model.

3. The hot technology evaluation method based on generative artificial intelligence as described in claim 2, characterized in that, Before calculating the importance centrality index based on the attribution keywords and the hot technical keywords using a preset importance assessment model, the method further includes: The hot technology extended keywords corresponding to the hot technology keywords are generated using the Word2Vector model; The target hot technology keywords are derived from the expanded keywords of the hot technology and the hot technology keywords themselves. The importance centrality index is calculated based on the target hot technical keywords using a preset importance assessment model.

4. The hot technology evaluation method based on generative artificial intelligence as described in claim 3, characterized in that, The importance centrality indices include at least: degree centrality, betweenness centrality, proximity centrality, and eigenvector centrality; The step of calculating the importance centrality index based on the target hot technical keywords using a preset importance assessment model includes: Calculate the cluster data volume and total number of clusters for each cluster; The association keywords are sorted according to the cluster data volume to obtain the association ranking results of each association keyword. The association ranking results represent the degree of relevance of the association keywords to the technical documents. Accordingly, the formula for calculating degree centrality is: in, Targeting hot technology keywords, The ranking coefficient of the target hot technology keywords in the relevance ranking results, where N is the total number of clusters; The formula for calculating betweenness centrality is: in, The betweenness number of the target hot technology keywords before normalization. This represents the difference in cluster size between the clusters corresponding to two keywords in the association ranking results. N is the difference between the first cluster data volume of the cluster corresponding to the i-th keyword and the second cluster data volume of the cluster corresponding to the j-th keyword and the target hot technology keyword in the correlation ranking result, where N is the total number of clusters. The formula for calculating proximity centrality is: in, N represents the cluster data size of the cluster closest to the target hot technology keyword in the correlation ranking results, where N is the total number of clusters. The formula for calculating the eigenvector centrality is: in, It is a constant. Feature vectors are constructed by combining the target hot technology keywords with the aforementioned technical literature. The centrality score is the score for each keyword.

5. The hot technology evaluation method based on generative artificial intelligence as described in claim 1, characterized in that, The process of predicting and evaluating hot technologies based on the trend curves of the hot technology popularity data, and generating a hot technology evaluation report, includes: Based on a preset time scale, the heat data change curves of the hot technologies are divided to obtain multiple data change curves. Filter the data change curves of each segment to obtain the corresponding multi-segment target data change curves; Calculate the mean of the target data change curve for each segment, and the rate of change of data within adjacent time periods; When the rate of change of data exceeds a preset threshold in two consecutive time periods, the hot technology keywords corresponding to the hot technology popularity data change curve are determined to be future hot technologies, and a hot technology evaluation report is generated based on the rate of change of data and the hot technology keywords.

6. A hot technology evaluation device based on generative artificial intelligence, characterized in that, The hotspot technology evaluation device based on generative artificial intelligence is applied to the hotspot technology evaluation method based on generative artificial intelligence as described in any one of claims 1 to 5, and the device comprises: The search module is used to respond to hot technical keywords and search for technical documents and measurement data corresponding to the hot technical keywords through the target search engine. The analysis module is used to analyze the importance centrality index of the hot technical keywords relative to the technical documents through a preset importance assessment model; The calculation module is used to calculate the popularity data of the technical documents based on the importance centrality index and the measurement data; The generation module is used to generate a hotspot technology popularity data change curve based on the popularity data; The evaluation module is used to predict and evaluate hot technologies based on the trend curve of the hot technology popularity data, and generate a hot technology evaluation report.

7. A hot technology evaluation device based on generative artificial intelligence, characterized in that, The hotspot technology evaluation device based on generative artificial intelligence includes: a memory, a processor, and a hotspot technology evaluation program based on generative artificial intelligence stored on the memory and executable on the processor. The hotspot technology evaluation program based on generative artificial intelligence is configured to implement the hotspot technology evaluation method based on generative artificial intelligence as described in any one of claims 1 to 5.

8. A storage medium, characterized in that, The storage medium stores a hotspot technology evaluation program based on generative artificial intelligence, which, when executed by a processor, implements the hotspot technology evaluation method based on generative artificial intelligence as described in any one of claims 1 to 5.

9. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps of the hotspot technology evaluation method based on generative artificial intelligence as described in any one of claims 1 to 5.

Images