Scientific and technological achievement transformation potential prediction method and system based on multi-source data fusion

Abstract

The invention discloses a scientific and technological achievement transformation potential prediction method and system based on multi-source data fusion, and the method comprises the steps: judging whether the similarity between a certain abstract data of a certain scientific and technological achievement text data and a certain data label of a certain text database is greater than a first threshold value or not; if yes, at least one target keyword is selected from a certain abstract data according to a preset selection strategy, and a first transformation potential value between at least one first target enterprise data and a certain scientific and technological achievement text data and a second transformation potential value between second target enterprise data and the certain scientific and technological achievement text data are calculated, and fusing the first transformation potential value and the second transformation potential value based on a preset fusion strategy to obtain a transformation potential value of certain scientific and technological achievement text data. The problem that the matching result is inaccurate due to the fact that deviation exists between the data label of the scientific and technological achievement data and the actual content of the scientific and technological achievement data is solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of data analysis, and particularly relates to a method and system for predicting the transformation potential of scientific and technological achievements based on multi-source data fusion. Background Art

[0002] Currently, by directly matching the data tags of scientific and technological achievement data with the data tags of enterprise data, the matching result is inaccurate due to the deviation between the data tags of scientific and technological achievement data and the actual content of scientific and technological achievement data, thereby reducing the accuracy of predicting the transformation potential of scientific and technological achievements. Summary of the Invention

[0003] The present invention provides a method and system for predicting the transformation potential of scientific and technological achievements based on multi-source data fusion, which is used to solve the technical problem that the matching result is inaccurate due to the deviation between the data tags of scientific and technological achievement data and the actual content of scientific and technological achievement data.

[0004] In a first aspect, the present invention provides a method for predicting the transformation potential of scientific and technological achievements based on multi-source data fusion, including: Crawling at least one scientific and technological achievement text data, and partitioning the at least one scientific and technological achievement text data based on a preset partitioning rule to obtain at least one text database, wherein the data tags of different text databases are different; Judging whether the similarity between a certain abstract data of a certain scientific and technological achievement text data and a certain data tag of a certain text database is greater than a first threshold, wherein the certain scientific and technological achievement text data is partitioned in the certain text database, and the certain abstract data contains at least one keyword; If it is not greater than the first threshold, then selecting at least one target keyword from the certain abstract data according to a preset selection strategy; Searching for at least one first target enterprise data in a preset enterprise database according to the at least one target keyword, and searching for second target enterprise data in the enterprise database according to a certain data tag of the certain text database; Calculating a first transformation potential value between the at least one first target enterprise data and the certain scientific and technological achievement text data, and a second transformation potential value between the second target enterprise data and the certain scientific and technological achievement text data, and fusing the first transformation potential value and the second transformation potential value based on a preset fusion strategy to obtain the transformation potential value of the certain scientific and technological achievement text data.

[0005] In a second aspect, the present invention provides a system for predicting the transformation potential of scientific and technological achievements based on multi-source data fusion, including: A partitioning module, configured to crawl at least one scientific and technological achievement text data, partition the at least one scientific and technological achievement text data based on a preset partitioning rule, and obtain at least one text database, wherein the data tags of different text databases are different; A judgment module, configured to judge whether the similarity between a certain abstract data of a certain scientific and technological achievement text data and a certain data tag of a certain text database is greater than a first threshold, wherein the certain scientific and technological achievement text data is partitioned in the certain text database, and the certain abstract data contains at least one keyword; A selection module, configured to, if it is not greater than the first threshold, select at least one target keyword from the certain abstract data according to a preset selection strategy; A search module, configured to search for at least one first target enterprise data in a preset enterprise database according to the at least one target keyword, and search for second target enterprise data in the enterprise database according to a certain data tag of the certain text database; A fusion module, configured to calculate a first conversion potential value between the at least one first target enterprise data and the certain scientific and technological achievement text data, and a second conversion potential value between the second target enterprise data and the certain scientific and technological achievement text data, and fuse the first conversion potential value and the second conversion potential value based on a preset fusion strategy to obtain the conversion potential value of the certain scientific and technological achievement text data.

[0006] In a third aspect, an electronic device is provided, which includes: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can execute the steps of the method for predicting the conversion potential of scientific and technological achievements based on multi-source data fusion according to any embodiment of the present invention.

[0007] In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the program instructions are executed by a processor, the processor is enabled to execute the steps of the method for predicting the conversion potential of scientific and technological achievements based on multi-source data fusion according to any embodiment of the present invention.

[0008] The potential prediction method and system for the transformation of scientific and technological achievements based on multi-source data fusion in this application determine whether the similarity between a certain abstract data of a scientific and technological achievement text data and a certain data label in a certain text database is greater than a first threshold. If it is not greater than the first threshold, at least one target keyword is selected from a certain abstract data according to a preset selection strategy. This can select keywords in the abstract data that are as different as possible from the data label, calculate a first transformation potential value between at least one first target enterprise data and a certain scientific and technological achievement text data, and a second transformation potential value between a second target enterprise data and a certain scientific and technological achievement text data, and fuse the first transformation potential value and the second transformation potential value based on a preset fusion strategy to obtain the transformation potential value of a certain scientific and technological achievement text data. The second transformation potential value between the data label and the enterprise label is corrected by the first transformation potential value between these keywords and the enterprise label, thereby improving the accuracy of the transformation potential prediction and solving the problem that the matching result is inaccurate due to the deviation between the data label of the scientific and technological achievement data and the actual content of the scientific and technological achievement data. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0010] Figure 1 It is a flowchart of a method for predicting the transformation potential of scientific and technological achievements based on multi-source data fusion provided by an embodiment of the present invention; Figure 2 It is a structural block diagram of a system for predicting the transformation potential of scientific and technological achievements based on multi-source data fusion provided by an embodiment of the present invention; Figure 3 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0011] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0012] Please refer to Figure 1, which shows a flowchart of a method for predicting the potential of scientific and technological achievement transformation based on multi-source data fusion according to the present application.

[0013] As Figure 1 shown, the method for predicting the potential of scientific and technological achievement transformation based on multi-source data fusion specifically includes the following steps: Step S101, crawl at least one scientific and technological achievement text data, and divide the at least one scientific and technological achievement text data based on a preset division rule to obtain at least one text database, where the data tags of different text databases are different.

[0014] In this step, crawl at least one scientific and technological achievement text data, and obtain the data tags of the at least one scientific and technological achievement text data; divide the scientific and technological achievement text data containing the same data tag into the same text database to obtain at least one text database.

[0015] Step S102, determine whether the similarity between a certain abstract data of a certain scientific and technological achievement text data and a certain data tag of a certain text database is greater than a first threshold, where the certain scientific and technological achievement text data is divided into the certain text database, and the certain abstract data contains at least one keyword.

[0016] In this step, obtain each keyword in a certain abstract data, calculate the similarity between each keyword and a certain data tag, and determine whether each similarity is greater than the first threshold. The expression for calculating the similarity is: , In the formula, is the similarity between a keyword and a certain data tag, is the word vector of the keyword, is the word vector of the data tag, , are both offsets, , are both weight vectors; It should be noted that the acquisition of the word vector of a keyword or the word vector of a data tag includes: selecting a pre-trained deep learning model according to requirements, such as BERT, RoBERTa, GPT, etc.; then using the corresponding library (such as transformers) to load the model and input the text into the model to obtain the corresponding word vector of the word or data tag.

[0017] In a specific embodiment, after determining whether the similarity between a certain abstract data of a scientific and technological achievement text data and a certain data label in a certain text database is greater than a preset threshold, if it is greater than the preset threshold, directly search for second target enterprise data in a preset enterprise database according to the certain data label; calculate a second conversion potential value between the second target enterprise data and the certain scientific and technological achievement text data, and directly use the second conversion potential value as the conversion potential value of the certain scientific and technological achievement text data.

[0018] Step S103, if it is not greater than the first threshold, select at least one target keyword from the certain abstract data according to a preset selection strategy.

[0019] In this step, obtain each keyword in a certain abstract data, and sort each keyword based on the similarity between each keyword and a certain data label to obtain a keyword sequence; take the first similarity value in the keyword sequence as the key similarity value, judge the similarity difference between other similarity values and the key similarity value, and judge whether each similarity difference is greater than a preset second threshold, where the other similarity values are the similarity values excluding the first similarity value in the keyword sequence; if a certain similarity difference is greater than the preset second threshold, take the certain keyword corresponding to the certain similarity difference as the target keyword, that is, obtain at least one target keyword; if all similarity differences are not greater than the preset second threshold, directly take the keyword corresponding to the last similarity value in the keyword sequence as the target keyword. The purpose is to obtain keywords that are as different as possible from the data label of the scientific and technological achievement text data, so that the first conversion potential value obtained subsequently is more valuable for reference.

[0020] Step S104, search for at least one first target enterprise data in a preset enterprise database according to the at least one target keyword, and search for second target enterprise data in the enterprise database according to a certain data label in the certain text database.

[0021] In this step, search for enterprise data containing at least one target keyword in the enterprise database to obtain at least one first target enterprise data; search for enterprise data containing a certain data label in the enterprise database to obtain second target enterprise data; judge whether a certain first target enterprise data and the second target enterprise data are repeated, where a certain first target enterprise data is any one of the at least one first target enterprise data; if they are repeated, directly remove the certain first target enterprise data to obtain the updated at least one first target enterprise data; if they are not repeated, there is no need to update the at least one first target enterprise data.

[0022] It should be noted that enterprise data can be obtained by crawling from the official website of the enterprise. For example, enterprise data can be the introduction of the products developed or produced by the enterprise, or the promotional introduction of the enterprise.

[0023] Step S105: Calculate the first conversion potential value between the at least one first target enterprise data and the certain scientific and technological achievement text data, and the second conversion potential value between the second target enterprise data and the certain scientific and technological achievement text data, and fuse the first conversion potential value and the second conversion potential value based on a preset fusion strategy to obtain the conversion potential value of the certain scientific and technological achievement text data.

[0024] In this step, specifically calculating the first conversion potential value between the at least one first target enterprise data and the certain scientific and technological achievement text data, and the second conversion potential value between the second target enterprise data and the certain scientific and technological achievement text data means: calculating the consistency score between the enterprise label of a certain first target enterprise data and the data label of the certain scientific and technological achievement text data to obtain a certain first conversion potential value, and calculating the consistency score between the enterprise label of a certain second target enterprise data and the data label of the certain scientific and technological achievement text data to obtain a certain second conversion potential value.

[0025] It should be noted that the average of each first conversion potential value is obtained to get the first average conversion potential value; it is judged whether the difference between the first average conversion potential value and the second conversion potential value is greater than a preset potential threshold; if it is not greater than the preset potential threshold, the second conversion potential value is directly used as the conversion potential value of the certain scientific and technological achievement text data; if it is greater than the preset potential threshold, the differences between each first conversion potential value and the second conversion potential value are respectively obtained to get each conversion potential difference, and the average of each conversion potential difference is calculated to get the second average conversion potential value; the second average conversion potential value is added to the second conversion potential value to obtain the second target conversion potential value, that is, the conversion potential value of the certain scientific and technological achievement text data is obtained.

[0026] In summary, in the method of the present application, by determining whether the similarity between a certain abstract data of a scientific and technological achievement text data and a certain data label of a certain text database is greater than a first threshold, if it is not greater than the first threshold, at least one target keyword is selected from a certain abstract data according to a preset selection strategy, which can select keywords as different as possible from the data label in the abstract data, and calculate a first conversion potential value between at least one first target enterprise data and a certain scientific and technological achievement text data and a second conversion potential value between a second target enterprise data and a certain scientific and technological achievement text data, and fuse the first conversion potential value and the second conversion potential value based on a preset fusion strategy to obtain the conversion potential value of a certain scientific and technological achievement text data. The second conversion potential value between the data label and the enterprise label is corrected by the first conversion potential value between the keyword and the enterprise label, so as to improve the accuracy of conversion potential prediction and solve the problem that the matching result is inaccurate due to the deviation between the data label of the scientific and technological achievement data and the actual content of the scientific and technological achievement data.

[0027] Please refer to Figure 2 , which shows a structural block diagram of a scientific and technological achievement conversion potential prediction system based on multi-source data fusion according to the present application.

[0028] As Figure 2 shown, the scientific and technological achievement conversion potential prediction system 200 includes a division module 210, a judgment module 220, a selection module 230, a search module 240, and a fusion module 250.

[0029] Among them, the partitioning module 210 is configured to crawl at least one scientific and technological achievement text data, partition the at least one scientific and technological achievement text data based on a preset partitioning rule to obtain at least one text database, where the data tags of different text databases are different; the judgment module 220 is configured to judge whether the similarity between a certain abstract data of a certain scientific and technological achievement text data and a certain data tag of a certain text database is greater than a first threshold, where the certain scientific and technological achievement text data is partitioned in the certain text database, and the certain abstract data contains at least one keyword; the selection module 230 is configured to, if it is not greater than the first threshold, select at least one target keyword from the certain abstract data according to a preset selection strategy; the search module 240 is configured to search for at least one first target enterprise data in a preset enterprise database according to the at least one target keyword, and search for second target enterprise data in the enterprise database according to a certain data tag of the certain text database; the fusion module 250 is configured to calculate a first conversion potential value between the at least one first target enterprise data and the certain scientific and technological achievement text data and a second conversion potential value between the second target enterprise data and the certain scientific and technological achievement text data, and fuse the first conversion potential value and the second conversion potential value based on a preset fusion strategy to obtain the conversion potential value of a certain scientific and technological achievement text data.

[0030] It should be understood that Figure 2 the modules described in Figure 1 correspond to the respective steps in the method described with reference to Figure 2 Therefore, the operations, features, and corresponding technical effects described above for the method also apply to

[0031] In some other embodiments, the embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the program instructions are executed by a processor, the processor executes the method for predicting the transformation potential of scientific and technological achievements based on multi-source data fusion in any of the above method embodiments; As an implementation manner, the computer-readable storage medium of the present invention stores computer-executable instructions, and the computer-executable instructions are set as: Crawl at least one scientific and technological achievement text data, partition the at least one scientific and technological achievement text data based on a preset partitioning rule to obtain at least one text database, where the data tags of different text databases are different; Judge whether the similarity between a certain abstract data of a certain scientific and technological achievement text data and a certain data tag of a certain text database is greater than a first threshold, where the certain scientific and technological achievement text data is partitioned in the certain text database, and the certain abstract data contains at least one keyword; If it is not greater than the first threshold, at least one target keyword is selected from the certain abstract data according to a preset selection strategy; At least one first target enterprise data is searched in a preset enterprise database according to the at least one target keyword, and second target enterprise data is searched in the enterprise database according to a certain data label of the certain text database; A first conversion potential value between the at least one first target enterprise data and the certain scientific and technological achievement text data and a second conversion potential value between the second target enterprise data and the certain scientific and technological achievement text data are calculated, and the first conversion potential value and the second conversion potential value are fused based on a preset fusion strategy to obtain a conversion potential value of the certain scientific and technological achievement text data.

[0032] A computer-readable storage medium may include a storage program area and a storage data area. Among them, the storage program area may store an operating system and application programs required for at least one function; the storage data area may store data created according to the use of the scientific and technological achievement conversion potential prediction system based on multi-source data fusion, etc. In addition, the computer-readable storage medium may include a high-speed random access memory, and may also include a memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some embodiments, the computer-readable storage medium may optionally include a memory remotely provided with respect to the processor, and these remote memories may be connected to the scientific and technological achievement conversion potential prediction system based on multi-source data fusion through a network. Examples of the above network include, but are not limited to, the Internet, an enterprise internal network, a local area network, a mobile communication network, and combinations thereof.

[0033] Figure 3 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention, as Figure 3 shown, the device includes: a processor 310 and a memory 320. The electronic device may further include: an input device 330 and an output device 340. The processor 310, the memory 320, the input device 330, and the output device 340 may be connected through a bus or other means, Figure 3 taking connection through a bus as an example. The memory 320 is the above-mentioned computer-readable storage medium. The processor 310 executes various functional applications and data processing of the server by running non-volatile software programs, instructions, and modules stored in the memory 320, that is, implements the scientific and technological achievement conversion potential prediction method based on multi-source data fusion in the above method embodiment. The input device 330 may receive input digital or character information, and generate key signal inputs related to user settings and function controls of the scientific and technological achievement conversion potential prediction system based on multi-source data fusion. The output device 340 may include a display device such as a display screen.

[0034] The above electronic device can execute the method provided by the embodiments of the present invention, and has corresponding functional modules and beneficial effects for executing the method. For technical details not described in detail in this embodiment, reference may be made to the method provided by the embodiments of the present invention.

[0035] As an implementation manner, the above electronic device is applied to a scientific and technological achievement transformation potential prediction system based on multi-source data fusion, and is used for a client, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable 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: Crawl at least one scientific and technological achievement text data, and divide the at least one scientific and technological achievement text data based on a preset division rule to obtain at least one text database, wherein the data tags of different text databases are different; Determine whether the similarity between a certain abstract data of a certain scientific and technological achievement text data and a certain data tag of a certain text database is greater than a first threshold, wherein the certain scientific and technological achievement text data is divided into the certain text database, and the certain abstract data contains at least one keyword; If it is not greater than the first threshold, select at least one target keyword from the certain abstract data according to a preset selection strategy; Search for at least one first target enterprise data in a preset enterprise database according to the at least one target keyword, and search for second target enterprise data in the enterprise database according to a certain data tag of the certain text database; Calculate a first transformation potential value between the at least one first target enterprise data and the certain scientific and technological achievement text data and a second transformation potential value between the second target enterprise data and the certain scientific and technological achievement text data, and fuse the first transformation potential value and the second transformation potential value based on a preset fusion strategy to obtain the transformation potential value of the certain scientific and technological achievement text data.

[0036] Through the description of the above implementation manners, those skilled in the art can clearly understand that each implementation manner can be realized by means of software plus a necessary general hardware platform, and of course, it can also be realized by hardware. Based on such an understanding, the above technical solution, in essence, or the part that contributes to the prior art can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiments.

[0037] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than limiting them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for predicting the potential for transformation of scientific and technological achievements based on multi-source data fusion, characterized in that: include: Crawling at least one scientific and technological achievement text data, dividing the at least one scientific and technological achievement text data based on a preset division rule, and obtaining at least one text database, wherein data labels of different text databases are different; Determine whether the similarity between a certain abstract data of a certain scientific and technological achievement text data and a certain data label of a certain text database is greater than a first threshold, wherein the certain scientific and technological achievement text data is divided into the certain text database, and the certain abstract data contains at least one keyword; If it is not greater than the first threshold, selecting at least one target keyword from the summary data according to a preset selection strategy; Searching for at least one first target enterprise data in a preset enterprise database according to the at least one target keyword, and searching for second target enterprise data in the enterprise database according to a data tag in the certain text database; Calculate the first conversion potential value between the at least one first target enterprise data and the certain scientific and technological achievement text data, and the second conversion potential value between the second target enterprise data and the certain scientific and technological achievement text data, and fuse the first conversion potential value and the second conversion potential value based on a preset fusion strategy to obtain the conversion potential value of the certain scientific and technological achievement text data.

2. The method for predicting the potential for transformation of scientific and technological achievements based on multi-source data fusion according to claim 1 is characterized in that: The step of dividing the at least one scientific and technological achievement text data based on a preset division rule to obtain at least one text database comprises: Obtaining a data label of the at least one scientific and technological achievement text data; The scientific and technological achievement text data containing the same data label are divided into the same text database to obtain at least one text database.

3. The method for predicting the potential for transformation of scientific and technological achievements based on multi-source data fusion according to claim 1 is characterized in that: After determining whether the similarity between a certain abstract data of a certain scientific and technological achievement text data and a certain data label of a certain text database is greater than a preset threshold, the method further includes: If it is greater than a preset threshold, directly searching for the second target enterprise data in a preset enterprise database according to the certain data tag; A second conversion potential value between the second target enterprise data and the certain scientific and technological achievement text data is calculated, and the second conversion potential value is directly used as the conversion potential value of the certain scientific and technological achievement text data.

4. The method for predicting the potential for transformation of scientific and technological achievements based on multi-source data fusion according to claim 1 is characterized in that: The selecting at least one target keyword from the summary data according to a preset selection strategy includes: Obtain each keyword in the certain summary data, and sort each keyword based on the similarity between each keyword and the certain data tag to obtain a keyword sequence, wherein the expression for calculating the similarity value between each keyword and the certain data tag is: ， In the formula, is the similarity between a keyword and a data label, is the word vector of the keyword, is the word vector of the data label, , are offsets, , are weight vectors; Taking the first similarity value in the keyword sequence as a key similarity value, determining similarity differences between other similarity values ​​and the key similarity value, and determining whether each similarity difference is greater than a preset second threshold, wherein the other similarity values ​​are similarity values ​​in the keyword sequence excluding the first similarity value; If a certain similarity difference is greater than a preset second threshold, a certain keyword corresponding to the certain similarity difference is used as a target keyword, that is, at least one target keyword is obtained; If all similarity differences are not greater than the preset second threshold, the keyword corresponding to the last similarity value in the keyword sequence is directly used as the target keyword.

5. The method for predicting the potential for transformation of scientific and technological achievements based on multi-source data fusion according to claim 1 is characterized in that: The searching for at least one first target enterprise data in a preset enterprise database according to the at least one target keyword, and searching for at least one second target enterprise data in the enterprise database according to a data tag in the certain text database comprises: Searching the enterprise database for a first enterprise tag containing the at least one target keyword, taking enterprise data corresponding to the first enterprise tag as first target enterprise data, and obtaining at least one first target enterprise data; Searching the enterprise database for a second enterprise tag containing the certain data tag, and taking the enterprise data corresponding to the second enterprise tag as the second target enterprise data; Determining whether a certain first target enterprise data and the second target enterprise data are repeated, wherein the certain first target enterprise data is any one of the at least one first target enterprise data; If there is a duplication, directly remove a first target enterprise data to obtain at least one updated first target enterprise data; If there is no duplication, there is no need to update the at least one first target enterprise data.

6. The method for predicting the potential for transformation of scientific and technological achievements based on multi-source data fusion according to claim 1 is characterized in that: The step of fusing the first conversion potential value and the second conversion potential value based on a preset fusion strategy to obtain a conversion potential value of a certain scientific and technological achievement text data includes: Averaging each first conversion potential value to obtain a first average conversion potential value; Determine whether the difference between the first average conversion potential value and the second conversion potential value is greater than a preset potential threshold; If it is not greater than the preset potential threshold, the second transformation potential value is directly used as the transformation potential value of a certain scientific and technological achievement text data; If it is greater than a preset potential threshold, respectively obtaining the difference between each first conversion potential value and the second conversion potential value to obtain each conversion potential difference value, and averaging each conversion potential difference value to obtain a second average conversion potential value; The second average conversion potential value is added to the second conversion potential value to obtain a second target conversion potential value, that is, to obtain a conversion potential value of a certain scientific and technological achievement text data.

7. A scientific and technological achievement transformation potential prediction system based on multi-source data fusion, characterized in that: include: A partitioning module is configured to crawl at least one scientific and technological achievement text data, and partition the at least one scientific and technological achievement text data based on a preset partitioning rule to obtain at least one text database, wherein different text databases have different data labels; A judgment module is configured to judge whether the similarity between a certain abstract data of a certain scientific and technological achievement text data and a certain data label of a certain text database is greater than a first threshold, wherein the certain scientific and technological achievement text data is divided into the certain text database, and the certain abstract data contains at least one keyword; a selection module configured to select at least one target keyword from the summary data according to a preset selection strategy if the value is not greater than a first threshold; A search module, configured to search for at least one first target enterprise data in a preset enterprise database according to the at least one target keyword, and to search for second target enterprise data in the enterprise database according to a data tag in the certain text database; The fusion module is configured to calculate a first conversion potential value between the at least one first target enterprise data and the certain scientific and technological achievement text data and a second conversion potential value between the second target enterprise data and the certain scientific and technological achievement text data, and to fuse the first conversion potential value and the second conversion potential value based on a preset fusion strategy to obtain a conversion potential value of the certain scientific and technological achievement text data.

8. An electronic device, characterized in that: include: At least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable 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 perform the method described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images