Patent retrieval result sorting method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a patent retrieval result sorting method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining patent retrieval results, and calculating the similarity between each patent in the patent retrieval results and a target text; sorting based on the similarity to obtain a first patent retrieval sorting result; obtaining a data monitoring result of each patent in the first patent retrieval sorting result, and obtaining a second patent retrieval sorting result based on the data monitoring result; obtaining a patent value score of each patent in the second patent retrieval sorting result, and obtaining a third patent retrieval sorting result based on the patent value scores; and displaying the third patent retrieval sorting result to the user.

Description

Technical Field

[0001] This document relates to the field of computer technology, and in particular to a patent search result sorting method, device, electronic device and storage medium. Background Art

[0002] In the era of knowledge economy, patents have become the core competitiveness of current enterprises and even an economy. Enterprises enhance their competitiveness in the international and domestic markets by building intellectual property barriers. With the continuous development and improvement of social systems, the number of patent documents has increased rapidly, making enterprises in various countries pay more and more attention to the protection of patent rights. For enterprises, how to accurately retrieve and analyze information that meets their needs from a large number of patent documents is crucial to the development of the entire enterprise. In the existing technology, the number of patent search results given is often huge, and users need to spend a lot of time to select patents that meet the requirements. Therefore, there is an urgent need for technical solutions for patent search technology and its result sorting. Summary of the invention

[0003] The purpose of the present invention is to provide a patent search result sorting method, device, electronic device and storage medium, aiming to solve the above-mentioned problems in the prior art.

[0004] The present invention provides a patent search result ranking method, comprising:

[0005] Obtain patent search results, and calculate the similarity between each patent in the patent search results and the target text;

[0006] Sorting based on the similarity to obtain a first patent search ranking result;

[0007] Obtaining data monitoring results of each patent in the first patent search and ranking results, and obtaining a second patent search and ranking result based on the data monitoring results;

[0008] Obtaining a patent value score for each patent in the second patent search ranking result, and obtaining a third patent search ranking result based on the patent value score; and

[0009] The third patent search ranking results are displayed to the user.

[0010] The present invention provides a patent search result sorting device, comprising:

[0011] The similarity module is used to obtain patent search results and calculate the similarity between each patent in the patent search results and the target text;

[0012] A first sorting module, used for sorting based on the similarity to obtain a first patent search sorting result;

[0013] A second ranking module is used to obtain data monitoring results of each patent in the first patent search ranking result, and obtain a second patent search ranking result based on the data monitoring results;

[0014] A third ranking module is used to obtain a patent value score of each patent in the second patent search ranking result, and obtain a third patent search ranking result based on the patent value score; and

[0015] A display module is used to display the third patent search ranking results to the user.

[0016] An embodiment of the present invention also provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the steps of the above-mentioned patent search result sorting method when executed by the processor.

[0017] An embodiment of the present invention also provides a computer-readable storage medium, on which a program for implementing information transmission is stored. When the program is executed by a processor, the steps of the above-mentioned patent search result sorting method are implemented.

[0018] By adopting the embodiment of the present invention, patent search results can be sorted according to historical data, which saves the user's time in patent screening and improves the user's patent search efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate one or more embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0020] Figure 1 is a flow chart of a patent search result ranking method according to an embodiment of the present invention;

[0021] Figure 2 is a schematic diagram of a patent search result ranking device according to an embodiment of the present invention;

[0022] Figure 3 is a schematic diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the following will be combined with the drawings in one or more embodiments of this specification to clearly and completely describe the technical solutions in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this document.

[0024] Method Embodiment

[0025] According to an embodiment of the present invention, a method for sorting patent search results is provided. Figure 1 is a flow chart of a method for sorting patent search results according to an embodiment of the present invention. Figure 1 As shown, the patent search result ranking method according to an embodiment of the present invention specifically includes:

[0026] Step S101, obtaining patent search results, and calculating the similarity between each patent in the patent search results and the target text; in an embodiment of the present invention, the target text may be a data set of patent search keywords.

[0027] In one embodiment of the present invention, M text similarity algorithm models based on a neural network can be obtained; model features of each text similarity algorithm model can be extracted; according to the model features, the M text similarity algorithm models are clustered to obtain K model clusters, where K is less than or equal to M; each model cluster is trained by reinforcement learning, and each text similarity algorithm model is weighted by ensemble learning to obtain a comprehensive text similarity algorithm model; similarity calculation is performed on the target text by the comprehensive text similarity algorithm model.

[0028] Specifically, the text similarity algorithm model may be trained or untrained. It should be noted that the M text similarity algorithm models are all constructed based on neural networks.

[0029] The M text similarity algorithm models can be obtained through an open source network community, such as obtaining a certain number (the recommended number is not less than 10, that is, M is greater than 10) of text similarity algorithm models based on neural networks from Internet channels (such as github, etc.). Of course, the M text similarity algorithm models can also be constructed by the staff themselves. In a possible implementation, among the M text similarity algorithm models, M1 text similarity algorithm models are obtained from Internet channels, and M2 text similarity algorithm models can be constructed by the staff themselves, M=M1+M2. In another possible implementation mode, among the M text similarity algorithm models, M3 text similarity algorithm models are trained, and M4 text similarity algorithm models are untrained, M=M3+M4, and the trained M3 text similarity algorithm models can include corresponding training information.

[0030] The above-mentioned text similarity algorithm model needs to meet the conditions of training and testing under the same data set, that is, the M text similarity algorithm models need to meet the conditions of training and testing under the same data set. In this way, during the training process, the differences in text similarity calculation between different text similarity algorithm models can be learned through the same data set.

[0031] Step S102, sorting based on the similarity to obtain the first patent search sorting result; in this step, sorting is performed in descending order of similarity to obtain the first patent search sorting result.

[0032] Step S103, obtaining data monitoring results of each patent in the first patent search ranking result, and obtaining a second patent search ranking result based on the data monitoring results; wherein the data monitoring results specifically include: the historical acquisition times of patents in the patent search results corresponding to the same or similar search keywords. The historical acquisition times specifically include: historical click times, historical download times, and / or historical browsing times.

[0033] In step S103, obtaining the patent value score of each patent in the second patent search ranking result specifically includes:

[0034] A plurality of value parameters of a patent document are obtained, and a patent value evaluation model is adopted to generate a patent value score for each patent based on the respective weights of the plurality of value parameters.

[0035] Step S104, obtaining the patent value score of each patent in the second patent search ranking result, and obtaining a third patent search ranking result based on the patent value score;

[0036] In this step, the patents are sorted in descending order according to their patent value scores to obtain the third patent search ranking result.

[0037] Step S105, displaying the third patent search ranking result to the user.

[0038] In summary, by adopting the embodiments of the present invention, patent search results can be sorted according to historical data, which saves the user's time in patent screening and improves the user's patent search efficiency.

[0039] Device Example 1

[0040] According to an embodiment of the present invention, a patent search result sorting device is provided. Figure 2 is a schematic diagram of a patent search result sorting device according to an embodiment of the present invention. Figure 2 As shown, the patent search result sorting device according to an embodiment of the present invention specifically includes:

[0041] A similarity module 20 is used to obtain patent search results and calculate the similarity between each patent in the patent search results and the target text;

[0042] A first sorting module 22, used for sorting based on the similarity to obtain a first patent search sorting result;

[0043] The second sorting module 24 is used to obtain the data monitoring results of each patent in the first patent search sorting result, and obtain the second patent search sorting result based on the data monitoring results; the data monitoring results specifically include: the historical acquisition times of patents in the patent search results corresponding to the same or similar search keywords. The historical acquisition times specifically include: historical click times, historical download times, and / or historical browsing times.

[0044] The second sorting module 24 is specifically used for:

[0045] A plurality of value parameters of a patent document are obtained, and a patent value evaluation model is adopted to generate a patent value score for each patent based on the respective weights of the plurality of value parameters.

[0046] A third ranking module 26 is used to obtain the patent value score of each patent in the second patent search ranking result, and obtain a third patent search ranking result based on the patent value score;

[0047] The display module 28 is used to display the third patent search ranking result to the user.

[0048] The embodiment of the present invention is a device embodiment corresponding to the above-mentioned method embodiment. The specific operations of each module can be understood by referring to the description of the method embodiment, which will not be repeated here.

[0049] Device Example 2

[0050] An embodiment of the present invention provides an electronic device, such as Figure 3 As shown, it includes: a memory 30, a processor 32, and a computer program stored in the memory 30 and executable on the processor 32. When the computer program is executed by the processor 32, the steps described in the method embodiment are implemented.

[0051] Device Example 3

[0052] An embodiment of the present invention provides a computer-readable storage medium, on which a program for implementing information transmission is stored. When the program is executed by the processor 32, the steps described in the method embodiment are implemented.

[0053] The computer-readable storage medium in this embodiment includes, but is not limited to, ROM, RAM, magnetic disk or optical disk, etc.

[0054] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A patent search result ranking method, characterized in that include: Obtain patent search results, and calculate the similarity between each patent in the patent search results and the target text; Sorting based on the similarity to obtain a first patent search ranking result; Obtaining data monitoring results of each patent in the first patent search and ranking results, and obtaining a second patent search and ranking result based on the data monitoring results; Obtaining a patent value score for each patent in the second patent search ranking result, and obtaining a third patent search ranking result based on the patent value score; and The third patent search ranking results are displayed to the user.

2. The method according to claim 1, characterized in that The data monitoring results specifically include: the historical acquisition times of patents in the patent search results corresponding to the same or similar search keywords.

3. The method according to claim 2, characterized in that The historical acquisition times specifically include: historical click times, historical download times, and / or historical browsing times.

4. The method according to claim 1, characterized in that Obtaining the patent value score of each patent in the second patent search ranking result specifically includes: A plurality of value parameters of a patent document are obtained, and a patent value evaluation model is adopted to generate a patent value score for each patent based on the respective weights of the plurality of value parameters.

5. A patent search result sorting device, characterized in that include: The similarity module is used to obtain patent search results and calculate the similarity between each patent in the patent search results and the target text; A first sorting module, used for sorting based on the similarity to obtain a first patent search sorting result; A second ranking module is used to obtain data monitoring results of each patent in the first patent search ranking result, and obtain a second patent search ranking result based on the data monitoring results; A third ranking module is used to obtain a patent value score of each patent in the second patent search ranking result, and obtain a third patent search ranking result based on the patent value score; and A display module is used to display the third patent search ranking results to the user.

6. The device according to claim 5, characterized in that The data monitoring results specifically include: the historical acquisition times of patents in the patent search results corresponding to the same or similar search keywords.

7. The device according to claim 6, characterized in that The historical acquisition times specifically include: historical click times, historical download times, and / or historical browsing times.

8. The device according to claim 5, characterized in that The second sorting module is specifically used for: A plurality of value parameters of a patent document are obtained, and a patent value evaluation model is adopted to generate a patent value score for each patent based on the respective weights of the plurality of value parameters.

9. An electronic device, characterized in that include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the patent search result ranking method as described in any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an implementation program for information transmission, and when the program is executed by the processor, the steps of the patent search result sorting method as described in any one of claims 1 to 4 are implemented.

Images