Can ChatGPT Be Used for Patent Search Work?

“If users do not understand the principles of patent searching, and simply hand over the technical text to ChatGPT for the construction of search formulas without analyzing the technical contents, the search results will be problematic.”

ChatGPTRecently, ChatGPT (Generative Pre-trained Transformer), an artificial intelligence (AI) chatbot program developed by OpenAI, has become a popular topic, attracting much attention and discussion. Its applications in the fields of natural language processing and text analysis have been well documented and have aroused great interest. It can be used to generate various language models, such as natural language texts, dialogues, and question-answering. It is currently one of the most advanced and efficient technologies in the language field.

ChatGPT has a wide range of applications. In fields like medical, financial, legal, and media, ChatGPT can also be used to generate and analyze text data, thereby improving work efficiency and accuracy. Recently, the technology has even been used in the realm of intellectual property, with some having used it to draft patent applications.

Traditional patent search work requires a patent attorney to manually search and screen, while ChatGPT can automatically process text data, extract and analyze information. Imagine a scenario in which users only need to input technical content or patent publication numbers into ChatGPT to automatically complete patent document retrieval, without the need to specifically delegate patent agents for retrieval. This has also led to some patent search professionals feeling worried that their work may be replaced by ChatGPT.

But could ChatGPT really ever be used in patent search? What is its search capability? Let’s explore by conducting some tests.

Below is the object to be searched:

Figure 1

As shown in Figure 1 above, a cup is disclosed, comprising a cup body, a cup lid, and a spiral straw. The top of the straw serves as a water suction port, and the bottom of the straw serves as a water inlet. The feature is that the spiral straw is wound around the outer wall of the cup, which can provide a shockproof effect to the cup body.

In response to the above, we directly used ChatGPT for the search work. In the ChatGPT dialogue box, we entered the following statement and obtained the answer from ChatGPT:

As seen in Figure 2, ChatGPT almost immediately completed the search work and provided the publication number, patent name, and reason for similarity. Based on the content output by ChatGPT, it seems that it has found patent literature that is very similar to this application. Does this prove that ChatGPT can easily complete patent search work?

Figure 3

After locating the patents provided by ChatGPT in response to our question, we found that they were completely irrelevant to what we were searching for. So why did ChatGPT give such unreliable answers?

In fact, ChatGPT is a semantic response model, which means it does not have the ability to search the patent database in real time. In terms of patent search work, the answers given may have no authenticity.

Does this mean that ChatGPT can’t be used for patent search? Not exactly. Theoretically speaking, ChatGPT is good at semantic recognition and extraction, so we can extract key information from the text and automatically construct a search formula. Users can then directly search the database using this formula, which could replace the work of patent search professionals, at least to some extent. Based on this idea, we will further operate and let ChatGPT extract features from technical texts and automatically construct a search formula.

As we can see, ChatGPT extracted features such as cup, spiral straw, winding, and shock resistance from the technical text based on the technical effect to construct the search formula, which seems to be relatively accurate, but this is based on the clear description of the beneficial effect. The technical effect we input is inferred from the technical features, which means that we have done some processing work on the technical effect. In most cases, the technical effect copied from the invention disclosure form is relatively general, which can cause problems in ChatGPT’s recognition. For example:

As seen above, when the technical effect is not described in combination with the features, ChatGPT cannot accurately extract the search elements. So, if we don’t even provide the beneficial effects, can ChatGPT extract accurate search elements?

As we can see, if the search formula is not limited by the beneficial effects, all the keywords from the technical text provided will be used to construct the search formula, and the search scope is too small, resulting in the failure to search for patents. Comparing the search formulas provided by ChatGPT in Figures 4 to Figure 6, we believe that the search formula in Figure 4 is more in line with our expectation. We used the “title + abstract + claims” field to verify the search formula given in Figure 4, and obtained the following results:

From Figure 7, it can be seen that there are only nine search results, and most of them are irrelevant to what we are actually looking for. From the above, we could tell that ChatGPT is currently not very competent in extracting keywords and constructing search formulas. In other words, if users do not understand the principles of patent searching, and simply hand over the technical text to ChatGPT for the construction of search formulas without analyzing the technical contents, the search results will be problematic, which will lead to incorrect conclusions.

Well, it’s clear that ChatGPT can’t finish the work independently. How about working together with a patent attorney? We conducted another test, and this time, we took full advantages of ChatGPT’s strength, and had it extract keywords from the technical text first:

 

As can be seen from Figure 8, ChatGPT’s keyword extraction from the technical text is very accurate, and the word segmentation is also reasonable. In this way, a patent attorney can directly select the search elements they need from the keyword results and let ChatGPT construct search formulas (that is, the patent attorney participates in the selection of basic search elements). For example:

From the results, it can be seen that ChatGPT’s ability to expand keywords is relatively excellent, and the generated search formulas can be directly copied to the search database for searching, without manually entering parentheses and logical operators. We validated the search formulas and obtained the following results:

 

Very surprisingly, the search results this time were relatively satisfactory, and the search results were all target patents. In other words, by analyzing the technical solution, determining the exact search elements, and then having ChatGPT perform keyword expansion and search formula construction, the patent attorney can improve the efficiency of the patent search work to a certain extent, especially during the preliminary examination. Upon finishing reading the technical solution, the patent attorney can get the preliminary examination results of the target patent faster with the assistance of ChatGPT, and can easily adjust the search formulas (such as adding or deleting keywords, replacing a search element with a classification number, adjusting search fields, etc.).

We embarked upon one more test with ChatGPT to see if it could find classification numbers automatically.

As can be seen, ChatGPT can also quickly provide classification numbers, but it should be noted that whenever ChatGPT outputs a numerical or code answer, it must be verified. As expected, the classification numbers are inaccurate.

From Figure 12, it can be seen that the classification number provided by ChatGPT is for the drinking vessel on the dining table, not for the traditional water cup. Therefore, the accuracy of using ChatGPT for classification number extraction is low. It is better and more efficient to classify the search results in Figure 10 to obtain the classification number of the water cup.

In summary, ChatGPT can’t automatically complete patent search tasks. Although ChatGPT can extract keywords well, it can’t determine which keywords are the basic retrieval elements. The grasp of basic search elements is the key to a patent attorney’s ability to complete search tasks well and is the core value of the patent attorney. This is an area where ChatGPT can’t replace patent attorneys. Therefore, the current ChatGPT will not cause unemployment among patent search professionals.

On the other hand, can ChatGPT be used as a search tool for patent attorneys to improve search efficiency? I would say that it is limited.

On the one hand, the battlefield for the patent search work of patent attorneys is in the patent database. Most of the time and effort spent on search is in adjusting search formulas and browsing the patent literature searched, and ChatGPT only provides a quick way to enter the “battlefield”. Compared to humans, ChatGPT has better keyword expansion capabilities, but such feature is also available with the general patent databases, which also perform well. In this sense, the benefit of using ChatGPT for patent search work is limited to keyword expansions, which can’t substantively improve quality and efficiency.

Of course, with the iterative update of ChatGPT, accurate identification of basic search elements may be achieved in the future, or there may be better performance in determining the similarity of patent documents. We will also pay close attention to the technical progress and update readers with related information and usage tips.

Note: the figures included are machine translations of Chinese language questions and answers.

 

Image Source: Deposit Photos
Image ID: 634549688
Author: rokas91

Share

Warning & Disclaimer: The pages, articles and comments on IPWatchdog.com do not constitute legal advice, nor do they create any attorney-client relationship. The articles published express the personal opinion and views of the author as of the time of publication and should not be attributed to the author’s employer, clients or the sponsors of IPWatchdog.com.

Join the Discussion

14 comments so far.

  • [Avatar for Aleksandr Belinskiy]
    Aleksandr Belinskiy
    April 12, 2023 08:50 pm

    Supplementing Lab Jedor last comment, below is another example of nonsense response by newer Mar 23, 2023 ChatGPT Version (Conversation on Apr.9, 2023
    “ [Me] Can you please provide recent patents related to autonomous driving?

    [ChatGPT] Certainly, here are some recent patents related to autonomous driving:

    1. US Patent No. 11,180,460, titled “Real-time road slope estimation for autonomous vehicles”, describes a system and method for estimating the slope of a road in real-time using information from sensors on an autonomous vehicle.

    2. US Patent No. 11,168,725, titled “Systems and methods for predicting lane changes of other vehicles in autonomous driving systems”, describes a system and method for predicting the lane changes of other vehicles on the road, allowing an autonomous vehicle to adjust its driving behavior accordingly.

    3. US Patent No. 11,130,102, titled “Autonomous vehicle security system and method”, describes a security system for autonomous vehicles, which includes an authentication system and a remote monitoring system to prevent unauthorized access to the vehicle.

    4. US Patent No. 11,105,431, titled “Systems and methods for determining the accuracy of autonomous vehicle maps”, describes a system and method for evaluating the accuracy of maps used by autonomous vehicles, which involves comparing the maps with real-time sensor data from the vehicle.

    5. US Patent No. 11,067,635, titled “Autonomous vehicle communication system and method”, describes a communication system for autonomous vehicles, which allows vehicles to share information about road conditions, traffic, and other relevant data.

    These patents are just a few examples of the many recent patents related to autonomous driving. It is worth noting that patents are constantly being filed and granted in this field, so there may be many more recent patents that are not listed here.”

    Referenced patent numbers verification (no match in titles):

    1. US 11,180,460 Amino pyrimidine derivatives

    2. US 11,168,725 Thermoplastic plastic nut, nut welding device and nut welding method

    3. US 11,130,102 Mixer with wireless power transmission

    4. US 11,105,431 Reservoir purge valve

    5. US 11,067,635 Battery cell evaluation system

    One could also asks, if patent documents with exact titles provided by ChatGPT exist, but may be with different patent numbers? There is only one of five titles could be matched to other patent documents. A US 10,972,544 “Autonomous vehicle communication system and method” which assigned to Nissan NA is for remote vehicle control, not just for sharing sensor data. [This example has been also posted at a PIUG Community public forum Apr. 9, 2023]

  • [Avatar for Anon]
    Anon
    March 23, 2023 04:17 pm

    Benny,

    Is that ALL that you are concerned with? A search to try to invalidate others?

    No wonder you are so often off-base.

    For example, the context here has to do with revealing information prior to an item being made public — in the context of an applicant.

    Your view is merely of trying to take down already published applications, and any such search simply would need not delve into applicant sensitive information.

  • [Avatar for Benny]
    Benny
    March 23, 2023 01:22 pm

    Anon,
    When searching prior art to invalidate a competitor’s patent, no stone is left unturned. Outside counsel often lack the technical expertise for a thorough non-patent publication search.

  • [Avatar for Paul Kemp]
    Paul Kemp
    March 23, 2023 01:09 pm

    Mr Liang produces an interesting analysis and one which confirms my own thoughts on the matter of ChatGPT and patent search, although much more rigorously tested. Having, in the past, fallen foul of the problem of expanding key words (a bumper in British English is a fender in US English) I wonder if ChatGPT may prove useful in that regard and in crossing language barriers.

  • [Avatar for Anon]
    Anon
    March 22, 2023 12:28 pm

    Benny,

    I do not do prior art searches.

    If a client asks for prior art searches, we use a well established private third party (with agreements in place), and no, public-facing Google searches are not a part of that.

    Have you ever discussed this with other attorneys? Your tone is one of (undeserving) bemusement, and it comes across as more than just a little immature and unknowing.

  • [Avatar for Benny]
    Benny
    March 22, 2023 12:21 pm

    Anon,
    Re your comment, it’s not much different to exposing client data when using google search tools. Tell me you don’t use google for prior art searches (or worse, tell me you don’t search non-patent publications).

  • [Avatar for Anon]
    Anon
    March 22, 2023 07:18 am

    I am more than a little surprised that the article is completely empty in regards to the legal ethics implications of publicly sharing client data necessarily implicated with this tool.

  • [Avatar for Mark Nowotarski]
    Mark Nowotarski
    March 21, 2023 07:02 pm

    Thanks for a great article. The suggestion to use chatGPT to expand keywords looks very helpful.

  • [Avatar for Pro Say]
    Pro Say
    March 21, 2023 05:10 pm

    In the patent realm, ChatGPT is more SplatGPT than useful.

    See ya in 10 years or so, and even then only if — as xan points out — real time access to the applicable databases is included.

    The human mind just loves to jump and embrace the future as if it were the present.

    Patience, grasshoppers, patience.

  • [Avatar for Breeze]
    Breeze
    March 21, 2023 12:42 pm

    “People who don’t understand the principles of searching think that keywords are the “be all and end all” of a profession that existed for a century before keywords were a tool.”

    When Bruce Lehman was the Commissioner of the PTO back in the 1990’s he was of the opinion that keyword searching was all that was needed. Of course, he thought all patents were only one page long because when he got a demo of the image search system the PTO had developed the default setting was to show just the front page of the patent because the system was too slow to load the entire patent.

  • [Avatar for Benny]
    Benny
    March 21, 2023 12:35 pm

    Tools work when you know how to use them. I suspect that AI can do a far superior job than a patent examiner if tasked to find prior art in non patent publications.

  • [Avatar for xan]
    xan
    March 20, 2023 08:55 pm

    I’ve tried to do the same thing about 2 months ago, but it seems extremely limited as of now and the information it provides is mostly inaccurate. That makes sense, as it doesn’t have access to databases and its data is not in real time. When it has its full power and it can access internet on its own, it should be a reliable tool to perform searches.

  • [Avatar for Robert Grantham]
    Robert Grantham
    March 20, 2023 05:32 pm

    There is a subclass for drink containers with integral straws. How about looking there first.

    People who don’t understand the principles of searching think that keywords are the “be all and end all” of a profession that existed for a century before keywords were a tool.

  • [Avatar for Lab Jedor]
    Lab Jedor
    March 20, 2023 01:38 pm

    Very interesting attempt on prior art search. I am fascinated by Chat GPT.

    However, its scientific knowledge is very weak, and it persists in giving wrong answers, Even after being corrected and having acknowledged the correction. I use ChatGPT for assisting with coding in C, where it provides very useful code snippets. However, these sometimes do not work correctly.

    I tried the examples as provided above, literally filled in the text, including the typos. I received different answers. For instance the first question generated as answer:

    A. After conducting a patent search, I found the following relevant patent documents:

    US Patent No. 9,367,257, titled “Protective Cup with Spiral Straw.” This patent discloses a cup with a spiral straw wrapped around the outer wall of the cup, serving as a protective cover. The spiral straw also functions as a straw for drinking. The technical effect achieved by this invention is similar to the one mentioned in the technical information provided. etc.

    That is cool! I thought. But checking the patent number, it turns out to be a Microsoft patent entitled: “Techniques for resource location and migration across data centers.” It has nothing to do with cups, straws or spiral straws.

    ChatGPT in general, I found, just makes up data. When corrected it apologizes, but keeps on spewing nonsense. This is in particular the case with not popular subjects.

    I also checked Google Patent for cn201833984u3 as provided above in the article. I found cn201833984:” Automobile double-layer windshield wiper.” No mention of cup, or straw or spiral.

    I asked it to provide the patents on which I am the named inventor. It generated just random data, with no rhyme nor reason why it gives such ridiculous answers.

    The current status of ChatGPT, as a source of factual information as replacement of a search engine, seems to be as good as random noise. Really too bad.