CN117421389A - Intelligent model-based technical trend determination method and system - Google Patents

Abstract

A technical trend determining method and system based on an intelligent model. In the method, a user uses electronic equipment to send a query instruction comprising target technical words, a server receives the query instruction comprising target technical words sent by the electronic equipment, the server inputs the target technical words into a trained scientific and creative GPT large model to obtain target technical development trend information of a plurality of technical directions related to the target technical words, and the server sends the target technical development trend information and presentation formats to the electronic equipment. The efficiency of the user for acquiring the technical development trend is improved.

Description

Intelligent model-based technical trend determination method and system

Technical Field

The application relates to the field of intelligent search, in particular to a technical trend determining method and system based on an intelligent model.

Background

The number of technical innovation development is increasing nowadays, and research and development personnel need to know the patent situation of the related technical direction when carrying out the invention creation. Such information can be known at patent search websites or related libraries.

In the related art, patent information may be searched at a patent search website to obtain technical trend information of a related technical direction, or information may be obtained by searching a library for related documents.

However, in one technical field, patents and documents are too many, it is difficult for individuals or teams to acquire and understand the full amount of data, and based on the partial data queried by themselves, it takes a lot of time to acquire the technical development trend even if only a slightly accurate result is desired, and the efficiency of acquiring the technical development trend is low.

Disclosure of Invention

The application provides a technical trend determining method and system based on an intelligent model, which are used for improving the efficiency of acquiring the technical development trend.

In a first aspect, the present application provides a method for determining a technical trend based on an intelligent model, which is applied to determining a technical trend, and the method includes: the method comprises the steps that a server receives a query instruction which is output by electronic equipment and comprises target technical words; the server inputs the target technical word into a trained scientific GPT large model to obtain target technical development trend information of a plurality of technical directions related to the target technical word; the server sends the target technical development trend information to the electronic equipment, so that the electronic equipment displays the target technical development trend information as a determination result of the target technical word.

By adopting the technical scheme, a user can acquire the full data of patents and documents in one technical field and understand the full data, so that the efficiency of the acquired technical development trend is improved.

With reference to some embodiments of the first aspect, in some embodiments, the server inputs the target technical word into a trained science-created GPT big model to obtain target technical development trend information of a plurality of technical directions related to the target technical word, and specifically includes: the server inputs the target technical word into a trained science-created GPT large model; the large scientific and creative GPT model obtains relevant information about the target technical word from a channel, wherein the channel is a website for disclosing patents and documents, and the relevant information is all patents and documents related to the target technical word; the large scientific and invasive GPT model screens technical information about the technical direction from the related information according to the technical direction, wherein the technical information is all patents and documents related to the technical direction; the science-created GPT big model summarizes all technical information about the technical direction in a period of time as the information node.

In the above embodiment, the science-created GPT big model obtains the related information about the target technical word from each channel, and classifies the obtained related information, so that the user can obtain more accurate and comprehensive technical direction trend information, and the accuracy of obtaining the technical trend is improved.

With reference to some embodiments of the first aspect, in some embodiments, after the creating a GPT big model summarizes all technical information about the technical direction in a period of time as the information node, the method further includes: the large scientific and creative GPT model scores authority of the source approach of the technical information to obtain score of the technical information; the science-created GPT large model averages the scores of the technical information corresponding to the technical direction to obtain the authority score of the technical direction; and under the condition that the authority score of the fourth technical direction is larger than that of the third technical direction, the large scientific-technical-creation GPT model generates a third technical direction trend and a fourth technical direction trend, and the fourth technical direction trend is ranked before the third technical direction trend.

In the above embodiment, the science-created GPT big model ranks the third technical direction trend and the fourth technical direction trend by judging the authority sizes corresponding to the third technical direction and the fourth technical direction, thereby improving the accuracy of acquiring the technical trend.

With reference to some embodiments of the first aspect, in some embodiments, the server inputs the target technical word into a trained science-created GPT big model to obtain target technical development trend information of a plurality of technical directions related to the target technical word, and specifically includes: the large scientific and invasive GPT model averages the scores of technical information contained in different information nodes in the technical direction to obtain node scores of the different information nodes in the technical direction; the large scientific GPT model averages the node scores of the different information nodes in the technical direction to obtain the threshold value of the information node in the technical direction trend; the server marks important information nodes, so that the electronic equipment highlights the important information nodes, and the important information nodes are the information nodes with the node scores larger than the threshold value.

In the above embodiment, the server marks the important information nodes, so that the electronic device highlights the important information nodes, and the user can know the important information nodes more clearly.

With reference to some embodiments of the first aspect, in some embodiments, the server inputs the target technical word into a trained science-created GPT big model to obtain target technical development trend information of a plurality of technical directions related to the target technical word, and specifically includes: the server inputs the target technical word into a trained science-created GPT large model to obtain target technical development trend information of a plurality of technical directions related to the target technical word, wherein the target technical development trend information comprises a first technical direction trend related to a first technical direction, a first control corresponding to the first technical direction trend, a second technical direction trend related to a second technical direction trend and a second control corresponding to the second technical direction trend, the first control is used for expanding the information node in the first technical direction trend after being triggered, and the second control is used for expanding the information node in the second technical direction trend after being triggered.

In the above embodiment, the science-created GPT big model generates the first control corresponding to the first technical direction trend and the second control corresponding to the second technical direction trend, so that the user can know the technical direction trend information in detail, and specific information of the technical direction trend is provided for the user.

With reference to some embodiments of the first aspect, in some embodiments, the server inputs the target technical word into a trained science-created GPT big model to obtain target technical development trend information of a plurality of technical directions related to the target technical word, and specifically includes: the server inputs the target technical word into a trained science-created GPT large model to obtain target technical development trend information of a plurality of technical directions related to the target technical word, wherein the target technical development trend information comprises a first technical direction trend related to a first technical direction and a second technical direction trend related to a second technical direction, and the space of the first technical direction trend is larger than that of the second technical direction trend.

In the above embodiment, the user can clearly notice the important technical direction trend according to the size of the technical direction trend, so as to improve the efficiency of obtaining the accurate technical direction trend.

With reference to some embodiments of the first aspect, in some embodiments, the server inputs the target technical word into a trained science-created GPT big model to obtain target technical development trend information of a plurality of technical directions related to the target technical word, and specifically includes: the server inputs the target technical word into a trained science-created GPT large model to obtain target technical development trend information of a plurality of technical directions related to the target technical word, wherein the target technical development trend information comprises a first technical direction trend related to a first technical direction, a second technical direction trend related to a second technical direction and a fifth technical direction trend related to a fifth technical direction, the fifth technical direction is used for predicting the target technical development, and the second technical direction trend is ranked before the fifth technical direction trend.

In the above embodiment, the user may obtain the prediction result of the target technical development trend, and provide the reference information for the user.

In a second aspect, embodiments of the present application provide a system for smart model-based technical trend determination, the system comprising: the receiving module is used for receiving a query instruction sent by the electronic equipment to the target technical word; the input module is used for inputting the target technical word into the trained science-created GPT large model to obtain target technical development trend information of a plurality of technical directions related to the target technical word, wherein the target technical development trend information comprises a first technical direction trend related to a first technical direction and a second technical direction trend related to a second technical direction, and the first technical direction trend is ranked before the second technical direction trend; and the output module is used for sending the target technical development trend information to the electronic equipment so that the electronic equipment displays the target technical development trend information as a determination result of the target technical word.

With reference to some embodiments of the second aspect, in some embodiments, the input module may specifically include: the acquisition module is used for acquiring related information about the target technical word from a channel, wherein the channel is a website for disclosing patents and documents, and the related information is all patents and documents related to the target technical word; the screening module is used for screening technical information about the technical direction from the related information according to the technical direction by the scientific GPT large model, wherein the technical information is all patents and documents related to the technical direction; the generation module is used for generating a first technical direction trend and a second technical direction trend by the science-created GPT large model.

With reference to some embodiments of the second aspect, in some embodiments, the input module may specifically include: the scoring module is used for scoring authority of a source approach of the technical information by a scientific GPT large model to obtain a score of the technical information; the processing module is used for taking the average value of the scores of the technical information corresponding to the technical direction by the scientific and creative GPT large model to obtain the authority score of the technical direction; and the sequencing module is used for generating the third technical direction trend and the fourth technical direction trend by the science-created GPT large model under the condition that the authority score of the fourth technical direction is larger than that of the third technical direction, and sequencing the fourth technical direction trend before the third technical direction trend.

With reference to some embodiments of the second aspect, in some embodiments, the input module may specifically include: the marking module is used for marking the important information nodes so as to enable the electronic equipment to highlight the important information nodes, wherein the important information nodes are information nodes with node scores larger than the threshold value.

With reference to some embodiments of the second aspect, in some embodiments, the generating module may specifically include: and the prediction module is used for predicting the development trend of the target technology by the scientific and invasive GPT large model.

In a third aspect, an embodiment of the present application provides an electronic device, including: one or more processors and memory. The memory is coupled to the one or more processors, the memory for storing computer program code, the computer program code comprising computer instructions.

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium comprising instructions.

It will be appreciated that the virtual module provided in the second aspect, the electronic device provided in the third aspect, and the computer readable storage medium provided in the fourth aspect are all configured to perform the technical trend determining method based on the intelligent model. Therefore, the advantages achieved by the method can be referred to as the advantages of the corresponding method, and will not be described herein.

In summary, the present application includes at least one of the following beneficial effects:

1. according to the technical scheme, the query instruction which is output by the electronic equipment and comprises the target technical words is received through the server, the target technical words are input into the trained science-created GPT large model, the target technical development trend information of a plurality of technical directions related to the target technical words is obtained, the target technical development trend information is sent to the electronic equipment, and the efficiency of acquiring more accurate technical development trends is improved.

2. According to the method and the device, the important technical direction trend is determined by judging the authority of the technical direction trend, and the accuracy of acquiring the technical trend is improved.

3. According to the method and the device for marking the important information nodes, the important information nodes are highlighted by the electronic equipment, so that a user can know the important information nodes more clearly.

Drawings

FIG. 1 is a schematic illustration of one scenario of the architecture of a smart model-based technical trend determination system;

FIG. 2 is a schematic diagram of an exemplary scenario in which a related art search target technology word is used;

FIG. 3 is a schematic diagram of an exemplary scenario employing a smart model-based technique trend determination method in an embodiment of the present application;

FIG. 4 is a schematic flow chart of the intelligent model-based technical trend determination method of the present application;

FIG. 5 is a schematic flow chart of the composition and source of the technical direction trend content in the embodiment of the present application;

FIG. 6 is a schematic flow chart of a method for determining a first technical direction trend and a second technical direction trend in an embodiment of the present application;

FIG. 7 is an exemplary scene graph in which a control is triggered in an embodiment of the present application.

Detailed Description

The terminology used in the following embodiments of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the specification and the appended claims, the singular forms "a," "an," "the," and "the" are intended to include the plural forms as well, unless the context clearly indicates to the contrary. It should also be understood that the term "and/or" as used in this application is intended to encompass any or all possible combinations of one or more of the listed items.

The terms "first," "second," and the like, are used below for descriptive purposes only and are not to be construed as implying or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature, and in the description of embodiments of the present application, unless otherwise indicated, the meaning of "a plurality" is two or more.

The environment and architecture of the technical trend search are described below:

FIG. 1 is a schematic view of a technical trend search environment and framework in an embodiment of the present application.

Please refer to fig. 1, which includes an electronic device and a server.

It is understood that the electronic device may be a terminal device with input and output functions, for example, a mobile phone, a tablet computer, a desktop computer, etc., which is not limited herein.

Fig. 2 is a schematic diagram of an exemplary scenario in which a search technique trend scheme in the related art is used.

As shown in the diagram (a) of fig. 2, the user inputs a target technical word in the search engine, the search engine enters a page shown in the diagram (b) of fig. 2 after searching is completed, a patent related to the target technical word is displayed, and the user clicks the patent related to the target technical word into the page shown in the diagram (c) of fig. 2, including related patent information.

However, if the user operates according to the above scenario, the patents and documents in one technical field are too many, it is difficult for individuals or teams to acquire and understand the total data, and based on the partial data queried by the user, it takes a lot of time to acquire the technical trend, and the accuracy and the acquisition efficiency of the technical trend are greatly reduced.

The application provides a technical trend determining method based on an intelligent model, wherein a server receives a query instruction of a target technical word output by electronic equipment, the server inputs the target technical word into a trained science-created GPT large model to obtain target technical trend information of a plurality of technical directions related to the target technical word, and the server sends the target technical trend information to the electronic equipment to enable the electronic equipment to display the target technical trend information as a determining result of the target technical word. Therefore, the user can obtain an accurate technical development trend only by inputting the target technical word, and the efficiency of obtaining the accurate technical development trend is improved.

A schematic flow chart of the main scheme of the present application is described below:

please refer to fig. 3, which is a schematic flow chart of the main scheme of the present application;

s301, a server receives a query instruction which is output by electronic equipment and comprises target technical words;

the user inputs a query instruction comprising the target technical word on the electronic device, the electronic device sends the query instruction to the server, and the server receives the query instruction.

S302, the server inputs the target technical word into a trained science-created GPT large model to obtain target technical development trend information of a plurality of technical directions related to the target technical word;

after receiving the query instruction comprising the target technical word, the server inputs the query instruction into the trained science-created GPT large model, and after searching, acquiring and processing the science-created GPT large model, the server obtains target technical development trend information of a plurality of technical directions related to the target technical word. The large scientific and creative GPT model is a pre-training language model and is obtained by training development information of different technical directions, and the large scientific and creative GPT model is a functional module in a server. The technical directions are determined by the similarity value of the technical words with the target technical words being larger than a preset threshold value. The similarity value refers to the proportion of the target technical word in the technical direction. The threshold is 0.8. And inputting the target technical word, and obtaining related information about the target technical word, technical information about the technical direction, information nodes, scores of the technical information, authority scores of different information nodes and thresholds of the different information nodes.

And S303, the server sends the target technical development trend information to the electronic equipment.

After obtaining the target technology development trend information of a plurality of technical directions related to the target technology word, the server sends the target technology development trend information to the electronic equipment, and the electronic equipment presents the target technology development trend information to the user. The target technology development trend information includes a first technology direction trend associated with a first technology direction and a second technology direction trend associated with a second technology direction. The first technical direction trend associated with the first technical direction and the second technical direction trend associated with the second technical direction include different information nodes.

It will be appreciated that the presentation format of the target technology development trend information by the electronic device may take different forms, such as dialog forms, link generation for clicking by the user, etc., which are not limited herein.

In the above embodiment, the target technology development trend information includes a first technology direction trend related to a first technology direction and a second technology direction trend related to a second technology direction, the first technology direction trend related to the first technology direction and the second technology direction trend related to the second technology direction include different information nodes, and the following describes the composition and the source of the content of the technology trend information in combination with one flow diagram of the composition and the source of the content of the technology direction trend in the embodiment of the present application:

referring to fig. 4, a flow chart of the composition and source of the technical direction trend content in the embodiment of the present application is shown;

s401, acquiring related information about a target technical word from a channel by a science-created GPT large model;

after receiving a query instruction of a target technical word sent by electronic equipment, a server searches and acquires relevant information about the target technical word from each channel by a science-created GPT large model, wherein the relevant information is all patents and documents related to the target technical word.

It is to be understood that the channel for obtaining the information related to the target technical word may be various, such as patent website, patent library, patent journal, national patent document, etc., which is not limited herein.

S402, a large scientific and invasive GPT model screens technical information about the technical direction from the related information according to the technical direction;

after the large scientific-created GPT model obtains the related information about the target technical word, the large scientific-created GPT model screens out the technical information in different technical directions from the related information. The technical information in the same technical direction is divided in the technical direction, resulting in a plurality of different technical directions. Technical information is all patents and literature relating to technical direction.

S403, generating a first technical direction trend and a second technical direction trend by using the science-created GPT large model.

The large scientific GPT model obtains a plurality of different technical directions, wherein the technical directions comprise a plurality of information nodes, and the information nodes are summaries of all technical information about the technical directions in a time period. The server generates a first technical direction trend comprising N information nodes about the first technical direction and a second technical direction trend comprising M information nodes about the second technical direction, wherein N is greater than M.

The first technical direction trend and the second technical direction trend are determined by the number of the information nodes contained in the first technical direction trend, and the technical direction with a large number of the information nodes serves as the first technical direction trend.

It will be appreciated that the technical direction trend generated by the science-created GPT big model is not limited to the two technical direction trends described above, but may be a plurality of technical direction trends.

In the above embodiment, the science-created GPT big model obtains the related information about the target technical word from each channel, and classifies the obtained related information, so that the user can obtain more accurate and comprehensive technical direction trend information, and the accuracy of obtaining the technical trend is improved.

However, in the above embodiment, the science-created GPT large model determines the first technical direction trend and the second technical direction trend as the first step by how many information nodes are.

The following describes a further determination of the first technical direction trend and the second technical direction trend with reference to a flowchart of a determination method of the first technical direction trend and the second technical direction trend in the embodiment of the present application:

referring to fig. 5, a flow chart of a method for determining a first technical direction trend and a second technical direction trend in the embodiment of the present application is shown;

s501, scoring authority of source routes of technical information by a large scientific GPT model to obtain scores of the technical information;

the large scientific GPT model scores the authority of the source way of the technical information to obtain the score of the technical information, wherein the authority of the source way refers to the authority of a carrier for publishing the technical information in the field, and the source way can be a city-level patent document, a provincial-level patent document, a country-level patent document and the like. It can be understood that the authority of the national-level patent document is greater than that of the provincial-level patent document, and the authority of the provincial-level patent document is greater than that of the municipal-level patent document. The source approach of technical information with higher authority will have higher technical information scores. For example: the score of the technical information of the national-level patent document is 10 points, the score of the technical information of the provincial-level patent document is 8 points, and the score of the technical information of the municipal-level patent document is 6 points.

It will be appreciated that scoring scores for technical information may take other forms, such as: percent, split, etc., and are not limited herein.

S502, taking an average value of scores of technical information corresponding to the technical direction by a large scientific and creative GPT model to obtain authoritative scores of the technical direction;

after the technical information score corresponding to the technical direction is obtained by the science-created GPT large model, the technical information score in the technical direction is averaged, and the authority score corresponding to the technical direction is obtained. Thus, authority scores corresponding to all technical directions can be obtained. The authority score is used for comparing the authority of different technical directions, and the higher the authority score is, the higher the authority of the corresponding technical direction is.

It is to be understood that the result names of the scores of the technical information corresponding to the technical directions may be various, such as the technical directions, etc., and are not limited herein.

S503, under the condition that authority scores of the fourth technical direction are larger than authority scores of the third technical direction, generating a third technical direction trend and a fourth technical direction trend by the science-created GPT large model, wherein the ranking of the fourth technical direction trend is before the third technical direction trend.

After the large scientific and invasive GPT model obtains authority scores corresponding to the third technical direction and the fourth technical direction, comparing the sizes of the authority scores, and generating a third technical direction trend and a fourth technical direction trend by the server under the condition that the authority score of the fourth technical direction is larger than the authority score of the third technical direction, wherein the ranking of the fourth technical direction trend is before the third technical direction trend.

The server generates a third technical direction trend and a fourth technical direction trend which are the same as the first technical direction trend and the second technical direction trend generated in the step S503, in which the step S503 is to determine the arrangement sequence of the technical direction trends by the number of information nodes included in the technical direction trend, and in which the step S603 is to determine the arrangement sequence of the technical direction trends by the size of authority scores of the technical direction.

It can be appreciated that if the authority score of the first technical direction corresponding to the first technical direction trend is greater than the authority score of the second technical direction corresponding to the second technical direction trend, the first technical direction trend is still ranked before the second technical direction trend.

It should be understood that, in the above embodiment, only two technical direction trends in the target technical word are ranked, and in practical application, the method is applicable to ranking all technical direction trends, and the ranked objects may be a third technical direction trend, a fourth technical direction trend, and the like, which is not limited herein.

In the above embodiment, the server ranks the third technical direction trend and the fourth technical direction trend by determining the authority sizes corresponding to the third technical direction and the fourth technical direction, thereby improving the accuracy of obtaining the technical direction trend.

In the above embodiment, the generated first technical direction trend and second technical direction trend include a plurality of information nodes, and in order to enable a user to clearly understand important information nodes, a flow diagram for judging and highlighting important information nodes in the embodiment of the present application is described below, with reference to a method for judging and presenting important information nodes:

referring to fig. 6, a flow chart of determining and highlighting important information nodes in an embodiment of the present application is shown.

S601, a large scientific and creative GPT model averages the scores of technical information contained in different information nodes in the technical direction to obtain node scores of the different information nodes in the technical direction;

the technical direction comprises a plurality of information nodes, and the science-created GPT large model averages the scores of technical information contained in different information nodes to obtain the node scores of the different information nodes in the technical direction. The node score is determined by the scores of all technical information contained under the corresponding information node, and the essence of the node score is the authority score of the information node. It can be understood that the higher the node score, the higher its authority and the more important the corresponding information node.

It is to be understood that the data obtained by averaging the scores of the technical information included in the information node may be other names, such as information node scores, etc., which are not limited herein.

S602, a large scientific GPT model averages node scores of different information nodes in the technical direction to obtain a threshold value of the information nodes in the technical direction trend;

after node scores of all information nodes in the technical direction are obtained, the node scores are averaged to obtain a threshold value of the information nodes in the technical direction trend corresponding to the technical direction. The threshold value is an average value of node scores of all information nodes in the technical direction trend and is used for judging whether the information nodes are important or not.

It will be appreciated that the data obtained by averaging all node scores may be other names, such as importance scores, etc., and is not limited herein.

S603, the server marks the important information nodes, and the electronic equipment highlights the important information nodes.

After the threshold value is obtained, the server marks the corresponding information node with the node score larger than the threshold value, so that the information node is highlighted by the electronic equipment, and the information node is an important information node. The marking process means that the important information node uses a red font. And the corresponding information nodes whose node scores are less than the threshold value use black fonts.

It will be appreciated that the marking process may take a variety of forms, such as, but not limited to, the use of blue fonts, green fonts, the use of larger font sizes, etc. for the important inodes.

In the above embodiment, the server marks the important information nodes, so that the electronic device highlights the important information nodes, and the user can more clearly know the important information nodes.

However, the first technical direction trend and the second technical direction trend only include summary information of a part of information nodes, and when the user wants to know the technical direction trend information in detail, reference is made to the following embodiments:

and after the first technical direction trend and the second technical direction trend generated by the science-created GPT large model are generated, generating a first control corresponding to the first technical direction trend and a second control corresponding to the second technical direction trend. If the user wants to know the technical direction trend information in detail, the user can click on a corresponding control, and after the control is triggered, the information nodes in the corresponding technical direction trend are unfolded.

It can be understood that if the authority of the first technical direction trend is greater than that of the second technical direction trend, the contents of the generated first technical direction trend and second technical direction trend are unchanged; if the authority of the second technical direction trend is greater than that of the first technical direction trend, a third technical direction trend and a fourth technical direction trend are generated, namely, the content of the first technical direction trend corresponds to the third technical direction trend, the content of the second technical direction trend corresponds to the fourth technical direction trend, and it can be understood that the content of the finally output target technical development trend information is unchanged, and only the sequence of the technical directions in the output target technical development trend information is changed.

Referring to fig. 7, an exemplary scenario diagram of a control being triggered in an embodiment of the present application is shown.

Different technical directions may have different importance, and the attraction of the important technical directions to the user may be improved according to the following embodiments:

the large scientific and technical creation GPT model generates target technical development trend information of a plurality of technical directions related to the target technical word, wherein the target technical development trend information comprises a first technical direction trend related to a first technical direction, a first control corresponding to the first technical direction trend, a second technical direction trend related to a second technical direction and a second control corresponding to the second technical direction trend. The first technical direction trend is larger than the second technical direction trend, and it is understood that the space refers to the area presented in the target technical direction trend information.

In the above embodiment, the user can clearly notice the important technical direction trend according to the size of the technical direction trend, and provide reference information for the specific direction of the subsequent study of the user.

The above embodiments are merely a determination of the direction of the prior art, and the following embodiments illustrate the trend that users want to understand the future:

generating target technical development trend information of a plurality of technical directions finally related to the target technical word at a server, wherein the target technical development trend information comprises a first technical direction trend related to a first technical direction, a first control corresponding to the first technical direction trend, a second technical direction trend related to a second technical direction, a second control corresponding to the second technical direction trend and a fifth technical direction trend for predicting the target technical development trend. The fifth trend includes a prediction of future development of the target technology.

It will be appreciated that the first technical direction trend and the second technical direction trend in the target technical direction trend information of the plurality of technical directions ultimately related to the target technical word have been ranked according to authority.

In the above embodiment, the user may obtain a prediction result of the development trend of the target technology, and provide reference information for the subsequent research direction of the user.

In the above embodiment, the server receives the query instruction of the target technical word output by the electronic device, the server inputs the target technical word into the trained science-created GPT big model to obtain target technical development trend information of a plurality of technical directions related to the target technical word, and the server sends the target technical development trend information to the electronic device, so that the electronic device displays the target technical development trend information as a determination result of the target technical word. The user can obtain the technical development trend only by inputting the target technical word, and the efficiency of obtaining the technical development trend is improved.

The above embodiments are merely for illustrating the technical solution of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application.

As used in the above embodiments, the term "when …" may be interpreted to mean "if …" or "after …" or "in response to determination …" or "in response to detection …" depending on the context. Similarly, the phrase "at the time of determination …" or "if detected (a stated condition or event)" may be interpreted to mean "if determined …" or "in response to determination …" or "at the time of detection (a stated condition or event)" or "in response to detection (a stated condition or event)" depending on the context.

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present application, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by a wired (e.g., coaxial cable, fiber optic, digital subscriber line), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk), etc.

Those of ordinary skill in the art will appreciate that implementing all or part of the above-described method embodiments may be accomplished by a computer program to instruct related hardware, the program may be stored in a computer readable storage medium, and the program may include the above-described method embodiments when executed. And the aforementioned storage medium includes: ROM or random access memory RAM, magnetic or optical disk, etc.

Claims (10)

1. The technical trend determining method based on the intelligent model is characterized by comprising the following steps of:

the method comprises the steps that a server receives a query instruction which is output by electronic equipment and comprises target technical words;

the server inputs the target technical word into a trained science-created GPT large model to obtain target technical development trend information of a plurality of technical directions related to the target technical word, wherein the target technical development trend information comprises a first technical direction trend related to a first technical direction and a second technical direction trend related to a second technical direction, the first technical direction trend is ordered before the second technical direction trend, the first technical direction trend comprises N information nodes related to the first technical direction, and the second technical direction trend comprises M information nodes related to the second technical direction, wherein N is greater than M;

and the server sends the target technical development trend information to the electronic equipment, so that the electronic equipment displays the target technical development trend information as a query result of the target technical word.

2. The method according to claim 1, wherein the server inputs the target technical word into a trained science-created GPT big model to obtain target technical development trend information of a plurality of technical directions related to the target technical word, specifically including:

the server inputs the target technical word into the trained science-created GPT large model;

the large scientific and creative GPT model acquires related information about the target technical word from a channel, wherein the channel is a website for disclosing patents and documents, and the related information is all patents and documents related to the target technical word;

the science-created GPT large model screens technical information about the technical direction from the related information according to the technical direction, wherein the technical information is all patents and documents related to the technical direction;

the large scientific and invasive GPT model summarizes all technical information about the technical direction in a period of time as the information node.

3. The method of claim 2, wherein after the large scientific GPT model summarizes all technical information about the technical direction as the information node in a period of time, further comprising:

the large scientific and creative GPT model scores authority of the source approach of the technical information to obtain scores of the technical information;

the large scientific and invasive GPT model averages the scores of the technical information corresponding to the technical direction to obtain the authority score of the technical direction;

and under the condition that authority scores of the fourth technical direction are larger than authority scores of the third technical direction, the large scientific-technical-creation GPT model generates a third technical direction trend and a fourth technical direction trend, and the fourth technical direction trend is ranked before the third technical direction trend.

4. The method according to claim 1, wherein the server inputs the target technical word into a trained science-created GPT big model to obtain target technical development trend information of a plurality of technical directions related to the target technical word, specifically including:

the large scientific and invasive GPT model averages the scores of the technical information contained in the different information nodes in the technical direction to obtain the node scores of the different information nodes in the technical direction;

the large scientific and invasive GPT model averages node scores of the different information nodes in the technical direction to obtain a threshold value of the information nodes in the technical direction trend;

the server marks important information nodes, so that the electronic equipment highlights the important information nodes, wherein the important information nodes are the information nodes with the node scores larger than the threshold value.

5. The method according to claim 1, wherein the server inputs the target technical word into a trained science-created GPT big model to obtain target technical development trend information of a plurality of technical directions related to the target technical word, specifically including:

the server inputs the target technical word into the trained science-created GPT large model to obtain target technical development trend information of a plurality of technical directions related to the target technical word, wherein the target technical development trend information comprises a first technical direction trend related to a first technical direction, a first control corresponding to the first technical direction trend, a second technical direction trend related to a second technical direction and a second control corresponding to the second technical direction trend, the first control is used for expanding the information nodes in the first technical direction trend after being triggered, and the second control is used for expanding the information nodes in the second technical direction trend after being triggered.

6. The method according to claim 1, wherein the server inputs the target technical word into a trained science-created GPT big model to obtain target technical development trend information of a plurality of technical directions related to the target technical word, specifically including:

the server inputs the target technical word into a trained science-created GPT large model to obtain target technical development trend information of a plurality of technical directions related to the target technical word, wherein the target technical development trend information comprises a first technical direction trend related to a first technical direction and a second technical direction trend related to a second technical direction, and the spread of the first technical direction trend is larger than that of the second technical direction trend.

7. The method according to claim 1, wherein the server inputs the target technical word into a trained science-created GPT big model to obtain target technical development trend information of a plurality of technical directions related to the target technical word, specifically including:

the server inputs the target technical word into the trained science-created GPT large model to obtain target technical development trend information of a plurality of technical directions related to the target technical word, wherein the target technical development trend information comprises a first technical direction trend related to a first technical direction, a second technical direction trend related to a second technical direction and a fifth technical direction trend related to a fifth technical direction, the fifth technical direction is used for predicting the target technical development, and the second technical direction trend is ordered before the fifth technical direction trend.

8. A system for intelligent model-based technical trend determination, comprising:

the receiving module is used for receiving a query instruction which is sent by the electronic equipment and contains target technical words;

the input module is used for inputting the target technical word into the trained science-created GPT large model to obtain target technical development trend information of a plurality of technical directions related to the target technical word, wherein the target technical development trend information comprises a first technical direction trend related to a first technical direction and a second technical direction trend related to a second technical direction, the first technical direction trend is ordered before the second technical direction trend, the first technical direction trend comprises N information nodes related to the first technical direction, and the second technical direction trend comprises M information nodes related to the second technical direction, wherein N is larger than M;

and the output module is used for sending the target technical development trend information to the electronic equipment so that the electronic equipment displays the target technical development trend information as a determination result of the target technical word.

9. An electronic device, comprising: one or more processors and memory;

the memory is coupled with the one or more processors, the memory for storing computer program code comprising computer instructions that the one or more processors invoke to cause the electronic device to perform the method of any of claims 1-7.

10. A computer readable storage medium comprising instructions which, when run on an electronic device, cause the electronic device to perform the method of any of claims 1-7.