Medical patent information analysis method and device based on large model, equipment and medium

Abstract

The invention discloses a medicine patent information analysis method and device based on a large model, equipment and a medium, and relates to the technical field of artificial intelligence, and the method comprises the steps: inputting a medicine patent uploaded by a current user side into a fine-tuned large model, and employing preset prompt information to analyze key information in the current medicine patent, and obtaining target key information; determining a disease field of the current medical patent according to indications in the target key information, and obtaining the highest research and development state of the current medical patent at home and abroad from a related website according to the disease field and target spots in the target key information; determining the level of a target based on the highest research and development state at home and abroad, and judging whether an application company of a current medical patent belongs to a concerned company or not to obtain a judgment result; and judging whether the target has research and development value or not according to the judgment result and the target level. The efficiency of medicine patent information analysis is greatly improved, the labor cost and time cost of medicine patent analysis are saved, and waste of human resources is avoided.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method, device, equipment and medium for analyzing pharmaceutical patent information based on a large model. Background Art

[0002] At present, when extracting and parsing key information (such as targets, indications, etc.) in pharmaceutical patents to analyze the current situation and provide guidance and suggestions for enterprises to determine the direction of research and development, it is highly dependent on the manual reading and statistical ability of professionals in the professional field. The average number of articles per person per week is 3-5, which not only depends on the technical level of professionals, but also is time-consuming and labor-intensive. In addition, since pharmaceutical patents are highly professional and have a variety of different languages, they require high professional quality of personnel, and manual methods occupy a large amount of human resources, increase the labor cost of patent information analysis, and fail to provide guidance for the direction of research and development in a timely manner. Summary of the invention

[0003] In view of this, the purpose of this application is to provide a method, device, equipment and medium for analyzing pharmaceutical patent information based on a large model, which can automatically extract and organize key information in pharmaceutical patents and analyze the current status, greatly improve the efficiency of patent information analysis, save the manpower cost and time cost of patent analysis, avoid waste of human resources, and at the same time, reduce the requirements for the professional quality of professionals, so as to provide timely and accurate guidance for enterprises to determine the direction of research and development. The specific plan is as follows:

[0004] In the first aspect, the present application discloses a method for analyzing pharmaceutical patent information based on a large model, comprising:

[0005] Get the medical patent uploaded by the current user and get the current medical patent;

[0006] The current pharmaceutical patent is input into the fine-tuned large model, so as to parse the key information in the current pharmaceutical patent using the preset prompt information to obtain the target key information; the fine-tuned large model is a model obtained by fine-tuning the pre-trained model using the pharmaceutical patent data set; the target key information includes the target, indication and the applicant company of the current pharmaceutical patent;

[0007] Determine the disease field of the current pharmaceutical patent according to the indication in the target key information to obtain the target disease field, and obtain the highest domestic and foreign research and development status of the current pharmaceutical patent from relevant websites according to the target disease field and the target in the target key information;

[0008] Determine the level of the target based on the highest R&D status at home and abroad, obtain the target level, and judge whether the applicant company of the current pharmaceutical patent is a company of key concern, and obtain the judgment result;

[0009] Whether the target in the target disease field has research and development value is determined based on the judgment result and the target level.

[0010] Optionally, obtaining the highest domestic and foreign research and development status of the current pharmaceutical patent from relevant websites based on the target disease field and the target in the target key information includes:

[0011] The highest domestic and international research and development status of the current pharmaceutical patent is captured from relevant websites using a web crawler based on the target disease field and the targets in the target key information.

[0012] Optionally, the large model-based pharmaceutical patent information analysis method further includes:

[0013] Collect different types of historical pharmaceutical patents to obtain a pharmaceutical patent dataset;

[0014] Convert all historical pharmaceutical patents in the pharmaceutical patent dataset into a unified data format to obtain a converted dataset;

[0015] Text recognition is performed on each medical patent in the converted data set to obtain historical patent text information, and the historical patent text information is input into a pre-trained model for model fine-tuning to obtain the fine-tuned large model; the pre-trained model is located in the inference server.

[0016] Optionally, performing text recognition on each pharmaceutical patent in the converted data set to obtain historical patent text information includes:

[0017] The text information of each pharmaceutical patent in the converted data set is identified using an optical character recognition tool to obtain historical patent text information.

[0018] Optionally, the current pharmaceutical patent is input into the fine-tuned large model to parse the key information in the current pharmaceutical patent using preset prompt information to obtain target key information, including:

[0019] Convert the current pharmaceutical patent into a picture to obtain a target picture, and cut the target picture to obtain multiple sub-pictures;

[0020] Text recognition is performed on each of the sub-images to obtain multiple current patent text information, and the current patent text information is input into the fine-tuned large model in turn to parse the key information in the current medical patent using preset prompt information to obtain target key information.

[0021] Optionally, determining whether the target in the target disease field has research and development value according to the judgment result and the target level includes:

[0022] Obtaining the appearance positions of the target and the indication in the current pharmaceutical patent to obtain first position information, and counting the number of times the target and the indication appear in the current pharmaceutical patent to obtain number information;

[0023] The position where the applicant company appears in the current pharmaceutical patent is obtained to obtain the second position information, and whether the target in the target disease field has research and development value is determined based on the judgment result, the target level, the first position information, the number information and the second position information.

[0024] Optionally, the large model-based pharmaceutical patent information analysis method further includes:

[0025] The target key information, the target disease field, the highest domestic and international research and development status, the target level, the judgment result and the judgment result of whether it has research and development value are sent to the user terminal for structured display on the human-computer interaction interface of the user terminal.

[0026] In the second aspect, the present application discloses a pharmaceutical patent information analysis device based on a large model, comprising:

[0027] The patent acquisition module is used to obtain the medical patent uploaded by the current user and obtain the current medical patent;

[0028] A parsing module, used for inputting the current pharmaceutical patent into the fine-tuned large model, so as to parse the key information in the current pharmaceutical patent using preset prompt information to obtain target key information; the fine-tuned large model is a model obtained by fine-tuning the pre-trained model using the pharmaceutical patent data set; the target key information includes the target, indication and the applicant company of the current pharmaceutical patent;

[0029] A field determination module, used to determine the disease field of the current pharmaceutical patent according to the indication in the target key information, and obtain the target disease field;

[0030] A status acquisition module, used to acquire the highest domestic and foreign research and development status of the current pharmaceutical patent from relevant websites according to the target disease field and the target in the target key information;

[0031] A level determination module, used to determine the level of the target based on the highest research and development status at home and abroad to obtain the target level;

[0032] A judgment module, used to judge whether the applicant company of the current pharmaceutical patent is a company of key concern, and obtain a judgment result;

[0033] The research and development value determination module is used to determine whether the target in the target disease field has research and development value based on the determination result and the target level.

[0034] In a third aspect, the present application discloses an electronic device, comprising a processor and a memory; wherein, when the processor executes a computer program stored in the memory, the aforementioned large model-based pharmaceutical patent information analysis method is implemented.

[0035] In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the aforementioned large-model-based pharmaceutical patent information analysis method is implemented.

[0036] It can be seen that the present application first obtains the pharmaceutical patent uploaded by the current user end to obtain the current pharmaceutical patent, and then inputs the current pharmaceutical patent into the fine-tuned large model obtained by fine-tuning the pre-trained model using the pharmaceutical patent data set, so as to use the preset prompt information to parse the key information in the current pharmaceutical patent to obtain the target key information; the fine-tuned large model is a model obtained by fine-tuning the pre-trained model using the pharmaceutical patent data set, wherein the target key information includes the target, indications and the applicant company of the current pharmaceutical patent, then, according to the indications in the target key information, the disease field of the current pharmaceutical patent is determined to obtain the target disease field, and according to the target disease field and the target in the target key information, the highest domestic and foreign research and development status of the current pharmaceutical patent is obtained from the relevant website, and then the level of the target is determined based on the highest domestic and foreign research and development status to obtain the target level, and it is judged whether the applicant company of the current pharmaceutical patent belongs to a company of key concern to obtain a judgment result, and finally, according to the judgment result and the target level, it is judged whether the target in the target disease field has research and development value. This application first parses the current pharmaceutical patent input by the user through a fine-tuned large model to obtain the target key information including targets, indications and the applicant company of the current pharmaceutical patent, and then determines the disease field of the current pharmaceutical patent, the highest domestic and foreign research and development status, the target level and whether it belongs to a key company based on the target key information. Finally, based on the determined information, it determines whether the current target has research and development value. This application uses large model technology to deeply understand and analyze pharmaceutical patents, and realizes the extraction, collation and current status analysis of key information in automated pharmaceutical patents. Compared with traditional manual patent information analysis methods, it not only greatly improves the efficiency of patent information analysis, but also saves the manpower and time costs of patent analysis, avoids the waste of human resources, and at the same time, reduces the requirements for the professional quality of professionals, and greatly shortens the time and confirmation cycle of patent key information statistics, thereby providing timely and accurate guidance for enterprises to determine the direction of research and development. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present application 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 embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0038] Figure 1 A flow chart of a method for analyzing pharmaceutical patent information based on a large model disclosed in this application;

[0039] Figure 2A flowchart of a specific method for analyzing pharmaceutical patent information based on a large model disclosed in this application;

[0040] Figure 3 This is a schematic diagram of the structure of a large model-based pharmaceutical patent information analysis device disclosed in this application;

[0041] Figure 4 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0043] The present application embodiment discloses a method for analyzing pharmaceutical patent information based on a large model, see Figure 1 As shown, the method includes:

[0044] Step S11: Acquire the pharmaceutical patent uploaded by the current user terminal to obtain the current pharmaceutical patent.

[0045] In this embodiment, the pharmaceutical patent currently uploaded by the user in the patent upload portal in the human-computer interaction interface at the user end is first obtained to obtain the current pharmaceutical patent. It should be noted that the number of pharmaceutical patents uploaded by the user end can be one or multiple patents uploaded in batches, that is, this solution supports batch analysis of multiple pharmaceutical patent information. In addition, for the pharmaceutical patents uploaded by the user end, a file backup can be made for subsequent call, viewing and manual analysis.

[0046] Step S12: Input the current pharmaceutical patent into the fine-tuned large model to parse the key information in the current pharmaceutical patent using preset prompt information to obtain target key information; the fine-tuned large model is a model obtained by fine-tuning the pre-trained model using the pharmaceutical patent data set; the target key information includes the target, indication and the applicant company of the current pharmaceutical patent.

[0047] In this embodiment, after obtaining the pharmaceutical patent uploaded by the current user end, the current pharmaceutical patent is further input into the large model (i.e., the fine-tuned large model) obtained by fine-tuning the pre-trained model using the pharmaceutical patent data set, so as to use the semantic information provided by the preset prompt information (prompt) in the model to ask questions to the large model, so as to parse the key information in the above-mentioned current pharmaceutical patent, and answer the target key information including the target, indication and the applicant company of the above-mentioned current pharmaceutical patent according to the preset requirements; wherein, the preset prompt information includes but is not limited to semantic information for the target, indication, patent-owning company, etc.; the target includes but is not limited to single target, simultaneous targeting and multiple targets, etc., and the indication can be specifically divided into 18 major disease areas, such as cardiovascular system diseases, infectious diseases, tumors, endocrine and metabolic system diseases, and the indication can be specifically subdivided into nearly 2,000 types such as B-cell leukemia, leukocyte adhesion deficiency, and interleukin receptor 1 antagonist deficiency. Among them, the way of asking questions to the large model can choose the way of asking questions in pre-screening content.

[0048] In a specific implementation, the Prompt may be:

[0049] i. Asking about targets: The inventor title is # XXX #, The inventor content is #XXX #, Please extract the target (English) information. The extracted targets are strictly in the answer format of 'Target:......'. If there are multiple targets, use ';' to separate them. Do not explain. Do not include redundant content in the answer. Please answer in English.

[0050] ii. Ask the applicant: the inventor applicant is # XXX #. Please extract the applicant company (in English). The extracted applicant company should strictly follow the answer format of 'Applicant:......'. If there are multiple applicant companies, separate them with ';'. Do not explain. Do not include redundant content in the answer. Please answer in English. [Example 1]: 'the inventor applicant is # REVOLUTION MEDICINES, INC. [US / US]; 700 Saginaw Drive, Redwood City, California 94063 (US). #', the extracted information is 'Applicant: REVOLUTION MEDICINES, INC' [Example 2]: 'the inventor applicant is # MEMORIALSLOAN KETTERING CANCER CENTER [US.US]; Office Of Technology Development, 1275 York Aenue, New York, NY 10065 (US). MEMORIAL" HOSPITAL FOR CANCER AND ALLIEDDISESES [US / US]; Office Of Technology Development, 1275 York Aenue, New York, NY10065 (US). #', the extracted information is 'Applicant: MEMORIAL SLOAN KETTERING CANCER CENTER; MEMORIAL HOSPITAL FOR CANCER AND ALLIED DISESES'.

[0051] In this embodiment, the process of acquiring the fine-tuned large model may specifically include: collecting different types of historical medical patents to obtain a medical patent data set; converting all historical medical patents in the medical patent data set into a unified data format to obtain a converted data set; performing text recognition on each medical patent in the converted data set to obtain historical patent text information, and inputting the historical patent text information into a pre-trained model to perform model fine-tuning to obtain the fine-tuned large model; the pre-trained model is located in an inference server. In this embodiment, historical medical patents in different fields may be collected to obtain a medical patent data set. Furthermore, considering that the historical medical patents may be downloaded through different channels during the collection process, the multiple historical medical patents in the historical medical patent set may have different text formats, such as PDF (Portable Document Format), word (a text file format), etc. In order to facilitate the subsequent unified model fine-tuning training, all historical medical patents in the historical medical patent set may be converted into data formats. For example, historical medical patents in PDF, word and other formats are uniformly converted into jpg (Joint Photographic Experts Group, an image format with a hybrid compression method) image format. Then, text recognition is performed on each medical patent in the converted data set to obtain historical patent text information including the title, abstract, target, indication, etc. of each patent. The historical patent text information is then input into the pre-trained model for model fine-tuning, thereby obtaining the fine-tuned large model; wherein the pre-trained model may be located in the inference server.

[0052] It is understandable that the large model (Large Language Model, LLM) has the complex ability and characteristics of comprehensive analysis and solving deeper problems, can show human-like thinking and intelligence, and can capture the complex semantic relationship of language and perform human-level language interaction. In a specific embodiment, the pre-trained model can be the L0 Hairuo large model, and the parameter volume of the model is 60B, and the maximum number of tokens supported is 4096. The model has the capabilities of entity extraction, semantic matching, intelligent summary, keyword extraction, knowledge classification, text error correction, etc., and adopts the framework of bert class + Bilstm + CRF, and uses BIO (a commonly used sequence annotation method, Begin Inside Outside) annotation method to annotate the training set.

[0053] It should be pointed out that in the process of fine-tuning the model in the pre-trained model, the appropriate fine-tuning strategy can be selected according to the task requirements and available resources, specifically considering whether to perform full fine-tuning or partial fine-tuning, as well as the level and scope of fine-tuning. Since the low-level features close to the input layer are more general, freezing the weights of these layers can maintain their general feature extraction capabilities learned in pre-training; while the high-level parts close to the output layer need to be fine-tuned according to specific tasks to adapt to new task requirements.

[0054] In addition, before fine-tuning the model, it is also necessary to determine the hyperparameters in the fine-tuning process, such as learning rate, batch size, number of training rounds, etc. For fine-tuning layers, a smaller learning rate can be used to avoid excessive damage to the pre-trained weights; for frozen layers, the learning rate can be zero. The selection of these hyperparameters has an important impact on the performance and convergence speed of fine-tuning. Considering that weights can be used to determine the degree of importance the model attaches to different input features, input features corresponding to larger weight values ​​have a greater impact on the output results, while smaller weight values ​​have a smaller impact. Therefore, weights can be set for pre-trained models to improve the performance of the model. For partial fine-tuning, the parameters of the high-level part close to the output layer will be randomly initialized; for full fine-tuning, all model parameters will be randomly initialized. This solution can use partial fine-tuning to train the model.

[0055] After determining the fine-tuning strategy, the strategy can be used to fine-tune the pre-trained model based on the pharmaceutical patent dataset. In the process of fine-tuning the model, the parameters of the model can be gradually adjusted according to the set hyperparameters and optimization algorithms to minimize the loss function; wherein the loss function is used to calculate the difference between the model's prediction and the true label, which can be maximized by binary cross entropy to correctly judge the probability of the target in the text. The calculation formula is:

[0056] ;

[0057] In the formula, represents the true label (value is 0 or 1), represents the predicted value of the model, and n is the total number of samples.

[0058] Furthermore, the Hinge Loss function is used to calculate the probability distribution difference between the target extracted from the input medical patent text and the correct target. The calculation formula is:

[0059] ;

[0060] In the formula, represents the true label (value is +1 or -1), Represents the predicted value of the model.

[0061] Furthermore, during the process of model fine-tuning, the validation set can be used to regularly evaluate the model and adjust the hyperparameters or fine-tuning strategies based on the evaluation results. In addition, after fine-tuning is completed, the test set can be used to evaluate the final fine-tuned model to obtain the final performance indicators.

[0062] In this embodiment, the performing of text recognition on each pharmaceutical patent in the converted data set to obtain historical patent text information may include: using an optical character recognition tool to recognize the text information of each pharmaceutical patent in the converted data set to obtain historical patent text information. That is, the optical character recognition (OCR) tool may be used to recognize the text information of each pharmaceutical patent in the converted data set.

[0063] Step S13: Determine the disease field of the current pharmaceutical patent according to the indication in the target key information to obtain the target disease field, and obtain the highest domestic and international research and development status of the current pharmaceutical patent from relevant websites according to the target disease field and the target in the target key information.

[0064] In this embodiment, after parsing the key information in the current pharmaceutical patent using the preset prompt information in the fine-tuned large model to obtain the target key information, the disease field to which the current pharmaceutical patent belongs is determined according to the indications in the above target key information to obtain the target disease field, and then the highest foreign research and development status and the highest domestic research and development status of the current pharmaceutical patent are obtained from relevant websites according to the target disease field and the target in the above target key information; wherein, the highest research and development status refers to the latest research and development stage that the target has developed to in the corresponding disease field, including no application, preclinical, non-active clinical application, clinical application in progress, clinical application, clinical approval, clinical progress, clinical phase I, clinical phase I / II, clinical phase II, clinical phase II / III, clinical phase III, non-active application for marketing, marketing in progress, application for marketing, and approval for marketing, a total of 16 stages.

[0065] It should be pointed out that in order to improve the accuracy of the analysis of pharmaceutical patents, after obtaining the target key information, it can be displayed on the manual interaction interface so that the user can modify it in the manual interaction interface, such as deleting, adding, modifying, etc.

[0066] In a specific embodiment, the obtaining the highest domestic and foreign research and development status of the current pharmaceutical patent from relevant websites according to the target disease field and the target in the target key information may specifically include: using a web crawler to crawl the highest domestic and foreign research and development status of the current pharmaceutical patent from relevant websites according to the target disease field and the target in the target key information. That is, crawling the highest domestic and foreign research and development status from relevant websites according to the result returned by the fine-tuned large model.

[0067] Step S14: Determine the level of the target based on the highest R&D status at home and abroad, obtain the target level, and judge whether the applicant company of the current pharmaceutical patent is a company of key concern, and obtain the judgment result.

[0068] In this embodiment, the level of the target in the above-mentioned target key information can be determined based on the highest domestic and foreign R&D status, that is, the patent is rated according to the highest domestic R&D status and the highest foreign R&D status of the target, and then it is judged whether the applicant company of the above-mentioned current pharmaceutical patent is a company of key concern, and the corresponding judgment result is obtained. It can be understood that whether the company to which the comprehensive patent belongs is a major competitor and object of concern, it can be judged whether the research and development of the target is urgent or needs to be abandoned, and the judgment of the company of key concern can be made through a preset database containing competitors and objects of concern.

[0069] It should be pointed out that this application has divided various types of targets into different levels in advance according to the highest R&D status at home and abroad. For example, multiple types of targets are divided into three levels, A, B, and C. When both the highest R&D status at home and abroad have not reached "clinical", the target level is A; when the highest R&D status at home has not reached "clinical", and the highest R&D status abroad has reached "clinical" but has not reached "clinical phase III", the target level is B; when the highest R&D status at home has reached "clinical" but has not reached "clinical phase II", and the highest R&D status abroad has reached "clinical phase III" but has not reached "application for listing", the target level is C. In addition, other situations are not included in the rating and are not worth paying attention to. Among them, the R&D value of level A is the highest, and the R&D value of level C is the lowest.

[0070] Step S15: Determine whether the target in the target disease field has research and development value based on the judgment result and the target level.

[0071] In this embodiment, after obtaining the above judgment result (i.e., whether it is a company of key focus) and the above target level, it can be comprehensively judged whether the target in the above target disease field has research and development value based on these two parts of information.

[0072] In a specific embodiment, determining whether the target in the target disease field has research and development value based on the judgment result and the target level may specifically include: obtaining the appearance positions of the target and the indication in the current pharmaceutical patent to obtain first position information, and counting the number of times the target and the indication appear in the current pharmaceutical patent to obtain number information; obtaining the appearance position of the applicant company in the current pharmaceutical patent to obtain second position information, and determining whether the target in the target disease field has research and development value based on the judgment result, the target level, the first position information, the number information and the second position information.

[0073] In this embodiment, the appearance positions of the target and indication in the current pharmaceutical patent can be obtained respectively to obtain the first position information, and then the number of times the target and indication appear in the current pharmaceutical patent can be counted respectively, and then the appearance position of the applicant company in the current pharmaceutical patent can be obtained to obtain the second position information. Finally, it can be comprehensively judged whether the target in the disease field to which the current pharmaceutical patent belongs has research and development value based on the judgment result of whether it belongs to a key company, the target level, the first position information, the number information, and the second position information.

[0074] Further, after determining whether the target in the target disease field has research and development value according to the judgment result and the target level, it can also include: sending the target key information, the target disease field, the highest research and development status at home and abroad, the target level, the judgment result and the judgment result of whether it has research and development value to the user terminal, so as to perform structured display on the human-computer interaction interface of the user terminal. In this embodiment, in order to facilitate user viewing, the extracted target key information, the disease field of the current pharmaceutical patent, the highest research and development status at home and abroad, the target level, the judgment result and the judgment result of whether it has research and development value can be sent to the human-computer interaction interface of the user terminal for structured display. For example, the extracted key information is marked at the corresponding position of the original text and structured display is performed. In addition, the human-computer interaction interface can also provide the authority to modify, so as to facilitate the user to manually modify and maintain the displayed information. For example, the user modifies and supplements the information such as the target and indication in the human-computer interaction interface, and can also modify the marked position of the key information.

[0075] It can be seen that the embodiment of the present application first obtains the pharmaceutical patent uploaded by the current user end to obtain the current pharmaceutical patent, and then inputs the current pharmaceutical patent into the fine-tuned large model obtained by fine-tuning the pre-trained model using the pharmaceutical patent data set, so as to use the preset prompt information to parse the key information in the current pharmaceutical patent to obtain the target key information; the fine-tuned large model is a model obtained by fine-tuning the pre-trained model using the pharmaceutical patent data set, wherein the target key information includes the target, indications and the applicant company of the current pharmaceutical patent, then, according to the indications in the target key information, the disease field of the current pharmaceutical patent is determined to obtain the target disease field, and according to the target disease field and the target in the target key information, the highest domestic and foreign research and development status of the current pharmaceutical patent is obtained from the relevant website, and then the level of the target is determined based on the highest domestic and foreign research and development status to obtain the target level, and it is judged whether the applicant company of the current pharmaceutical patent belongs to a company of key concern to obtain a judgment result, and finally, according to the judgment result and the target level, it is determined whether the target in the target disease field has research and development value. The embodiment of the present application first parses the current pharmaceutical patent input by the user through the fine-tuned large model to obtain the target key information including the target, indication and the applicant company of the current pharmaceutical patent, and then determines the disease field of the current pharmaceutical patent, the highest research and development status at home and abroad, the target level and whether it belongs to a key company based on the target key information. Finally, it determines whether the current target has research and development value based on the determined information. The embodiment of the present application uses the large model technology to deeply understand and analyze pharmaceutical patents, and realizes the extraction, collation and current status analysis of key information in automated pharmaceutical patents. Compared with the traditional manual patent information analysis method, it not only greatly improves the efficiency of patent information analysis, but also saves the manpower cost and time cost of patent analysis, avoids the waste of human resources, and at the same time, reduces the requirements for the professional quality of professionals, and greatly shortens the time and confirmation cycle of patent key information statistics, so as to provide timely and accurate guidance for enterprises to determine the research and development direction.

[0076] The present application embodiment discloses a specific method for analyzing pharmaceutical patent information based on a large model, see Figure 2 As shown, the method includes:

[0077] Step S21: Acquire the pharmaceutical patent uploaded by the current user terminal to obtain the current pharmaceutical patent.

[0078] Step S22: convert the current medical patent into a picture to obtain a target picture, and cut the target picture to obtain multiple sub-pictures.

[0079] In this embodiment, in order to improve the efficiency of patent information analysis, after obtaining the pharmaceutical patent uploaded by the user, the above current pharmaceutical patent can be converted into a picture format, and then the target picture can be cut into multiple sub-pictures for subsequent parallel processing.

[0080] Step S23: Perform text recognition on each of the sub-images to obtain multiple current patent text information, and input the current patent text information into the fine-tuned large model in turn, so as to parse the key information in the current medical patent using preset prompt information to obtain target key information; the fine-tuned large model is a model obtained by fine-tuning the pre-trained model using the medical patent data set; the target key information includes the target, indication and the applicant company of the current medical patent.

[0081] In this embodiment, after the target image is cut to obtain multiple sub-images, the OCR tool can be used to perform segmented text recognition on each sub-image to obtain multiple current patent text information, and then the current patent text information is sequentially input into the large model obtained by fine-tuning the pre-trained model using the pharmaceutical patent data set, so as to use the preset prompt information (prompt) in different models to ask questions about the above-mentioned current pharmaceutical patents to parse the key information in the current pharmaceutical patents, and answer the target key information including targets, indications and the applicant company of the current pharmaceutical patent according to the preset requirements. Among them, in the segmented text recognition process, it supports the recognition of multiple small languages ​​such as Chinese, English, Japanese, Korean, French and German, and can extract patent titles, patent numbers and other information based on text features. In addition, the large model supports the analysis of pharmaceutical patents in Chinese, English and multiple other languages, and parses out information such as targets, indications and patent companies in the corresponding texts.

[0082] It should be noted that the fixed format refers to the format specified in the prompt, for example:

[0083] i. Question: The inventor title is # XXX #, the inventor content is # XXX#. Please extract the target (English) information. The extracted target is strictly in the answer format of 'Target:......'. If there are multiple targets, use ';' to separate them. Do not explain. Do not include redundant content in the answer. Please answer in English.

[0084] ii.Answer: Target: XXX;XXX.

[0085] Step S24: Determine the disease field of the current pharmaceutical patent according to the indication in the target key information to obtain the target disease field, and obtain the highest domestic and international research and development status of the current pharmaceutical patent from relevant websites according to the target disease field and the target in the target key information.

[0086] Step S25: Determine the level of the target based on the highest R&D status at home and abroad, obtain the target level, and judge whether the applicant company of the current pharmaceutical patent is a company of key concern to obtain the judgment result.

[0087] Step S26: Determine whether the target in the target disease field has research and development value based on the judgment result and the target level.

[0088] For more specific processing procedures of the above steps S21, S24 to S26, reference may be made to the corresponding contents disclosed in the aforementioned embodiments, which will not be described in detail here.

[0089] It can be seen that the embodiment of the present application first converts the current pharmaceutical patent into a picture to obtain a target picture, and cuts the target picture to obtain multiple sub-pictures, and then performs text recognition on each of the sub-pictures to obtain multiple current patent text information, and sequentially inputs the current patent text information into the fine-tuned large model to parse the key information in the current pharmaceutical patent using preset prompt information to obtain target key information, and then determine the disease field of the current pharmaceutical patent according to the indications in the target key information to obtain the target disease field, and obtain the highest domestic and foreign research and development status of the current pharmaceutical patent from relevant websites according to the target disease field and the target in the target key information, and finally determine the level of the target based on the highest domestic and foreign research and development status to obtain the target level, and determine whether the applicant company of the current pharmaceutical patent is a company of focus to obtain a judgment result, so as to determine whether the target in the target disease field has research and development value according to the judgment result and the target level. The embodiment of this application integrates technologies such as text recognition and language big models, and uses pre-trained big models to deeply understand and analyze pharmaceutical patents, realizing the extraction, collation and current status analysis of key information of pharmaceutical patents; moreover, this solution supports batch processing of pharmaceutical patents, taking an average of 2 minutes per 100 patents, which is significantly improved in information processing speed compared to the traditional manual analysis method of 3-5 patents per person per week. At the same time, it liberates human resources in professional fields, reduces professional requirements for human resources, greatly shortens the time and confirmation cycle for statistics of key patent information, and reduces labor costs and time costs. In addition, this solution also promotes the intelligent and automated development of patent management, and provides guidance on timely adjustment of R&D directions and finding scarce R&D directions, laying a solid foundation for the digital transformation and sustainable development of enterprises.

[0090] Correspondingly, the present application also discloses a pharmaceutical patent information analysis device based on a large model, see Figure 3 As shown, the device comprises:

[0091] The patent acquisition module 11 is used to acquire the medical patent uploaded by the current user end and obtain the current medical patent;

[0092] The parsing module 12 is used to input the current pharmaceutical patent into the fine-tuned large model, so as to parse the key information in the current pharmaceutical patent using the preset prompt information to obtain the target key information; the fine-tuned large model is a model obtained by fine-tuning the pre-trained model using the pharmaceutical patent data set; the target key information includes the target, indication and the applicant company of the current pharmaceutical patent;

[0093] A field determination module 13 is used to determine the disease field of the current pharmaceutical patent according to the indication in the target key information to obtain a target disease field;

[0094] A status acquisition module 14 is used to acquire the highest domestic and foreign research and development status of the current pharmaceutical patent from relevant websites according to the target disease field and the target in the target key information;

[0095] A level determination module 15 is used to determine the level of the target based on the highest research and development status at home and abroad to obtain the target level;

[0096] A judgment module 16 is used to judge whether the company applying for the current pharmaceutical patent is a company of key concern, and obtain a judgment result;

[0097] The R&D value determination module 17 is used to determine whether the target in the target disease field has R&D value based on the determination result and the target level.

[0098] Among them, the specific working processes of the above-mentioned modules can refer to the corresponding contents disclosed in the aforementioned embodiments, which will not be repeated here.

[0099] It can be seen that in the embodiment of the present application, the pharmaceutical patent uploaded by the current user end is first obtained to obtain the current pharmaceutical patent, and then the current pharmaceutical patent is input into the fine-tuned large model obtained by fine-tuning the pre-trained model using the pharmaceutical patent data set, so as to use the preset prompt information to parse the key information in the current pharmaceutical patent to obtain the target key information; the fine-tuned large model is a model obtained by fine-tuning the pre-trained model using the pharmaceutical patent data set, wherein the target key information includes the target, indications and the applicant company of the current pharmaceutical patent, then, according to the indications in the target key information, the disease field of the current pharmaceutical patent is determined to obtain the target disease field, and according to the target disease field and the target in the target key information, the highest domestic and foreign research and development status of the current pharmaceutical patent is obtained from the relevant website, and then based on the highest domestic and foreign research and development status, the level of the target is determined to obtain the target level, and it is judged whether the applicant company of the current pharmaceutical patent belongs to a company of key concern to obtain a judgment result, and finally, according to the judgment result and the target level, it is determined whether the target in the target disease field has research and development value. The embodiment of the present application first parses the current pharmaceutical patent input by the user through the fine-tuned large model to obtain the target key information including the target, indication and the applicant company of the current pharmaceutical patent, and then determines the disease field of the current pharmaceutical patent, the highest research and development status at home and abroad, the target level and whether it belongs to a key company based on the target key information. Finally, it determines whether the current target has research and development value based on the determined information. The embodiment of the present application uses the large model technology to deeply understand and analyze pharmaceutical patents, and realizes the extraction, collation and current status analysis of key information in automated pharmaceutical patents. Compared with the traditional manual patent information analysis method, it not only greatly improves the efficiency of patent information analysis, but also saves the manpower cost and time cost of patent analysis, avoids the waste of human resources, and at the same time, reduces the requirements for the professional quality of professionals, and greatly shortens the time and confirmation cycle of patent key information statistics, so as to provide timely and accurate guidance for enterprises to determine the research and development direction.

[0100] In some specific embodiments, the state acquisition module 14 may specifically include:

[0101] The crawling unit is used to crawl the highest domestic and international research and development status of the current pharmaceutical patent from relevant websites using a web crawler based on the target disease field and the targets in the target key information.

[0102] In some specific embodiments, the large model-based pharmaceutical patent information analysis device may further include:

[0103] Patent collection unit, used to collect different types of historical medical patents to obtain medical patent data sets;

[0104] A format conversion unit, used to convert all historical pharmaceutical patents in the pharmaceutical patent dataset into a unified data format to obtain a converted dataset;

[0105] A first text recognition unit, configured to perform text recognition on each pharmaceutical patent in the converted data set to obtain historical patent text information;

[0106] An information input unit is used to input the historical patent text information into a pre-trained model to perform model fine-tuning to obtain the fine-tuned large model; the pre-trained model is located in an inference server.

[0107] In some specific embodiments, the first text recognition unit may specifically include:

[0108] The second text recognition unit is used to recognize the text information of each pharmaceutical patent in the converted data set by using an optical character recognition tool to obtain historical patent text information.

[0109] In some specific embodiments, the analysis module 12 may specifically include:

[0110] A picture conversion unit, used for converting the current pharmaceutical patent into a picture to obtain a target picture;

[0111] A picture cutting unit, used for cutting the target picture to obtain multiple sub-pictures;

[0112] A third text recognition unit is used to perform text recognition on each of the sub-pictures to obtain multiple current patent text information;

[0113] The parsing unit is used to input the current patent text information into the fine-tuned large model in sequence, so as to parse the key information in the current medical patent using preset prompt information to obtain target key information.

[0114] In some specific embodiments, the R&D value determination module 17 may specifically include:

[0115] A first position information acquisition unit, used to acquire the appearance positions of the target and the indication in the current pharmaceutical patent to obtain first position information;

[0116] A frequency counting unit, used to count the number of times the target and the indication appear in the current pharmaceutical patent to obtain frequency information;

[0117] A second position information acquisition unit, used to acquire the position where the applicant company appears in the current pharmaceutical patent to obtain second position information;

[0118] A research and development value determination unit is used to determine whether the target in the target disease field has research and development value based on the judgment result, the target level, the first position information, the number information and the second position information.

[0119] In some specific embodiments, the large model-based pharmaceutical patent information analysis device may further include:

[0120] The information display unit is used to send the target key information, the target disease field, the highest domestic and foreign research and development status, the target level, the judgment result and the judgment result of whether it has research and development value to the user terminal, so as to perform structured display on the human-computer interaction interface of the user terminal.

[0121] Furthermore, the present application also discloses an electronic device. Figure 4 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram cannot be regarded as any limitation on the scope of use of the present application.

[0122] Figure 4 A schematic diagram of the structure of an electronic device 20 provided in an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the large model-based pharmaceutical patent information analysis method disclosed in any of the aforementioned embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0123] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0124] In addition, the memory 22, as a carrier for storing resources, can be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon can include an operating system 221, a computer program 222, etc., and the storage method can be temporary storage or permanent storage.

[0125] The operating system 221 is used to manage and control the hardware devices and computer program 222 on the electronic device 20, which can be Windows Server, Netware, Unix, Linux, etc. In addition to the computer program that can be used to complete the large model-based pharmaceutical patent information analysis method performed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 can further include computer programs that can be used to complete other specific tasks.

[0126] Furthermore, the present application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the aforementioned large model-based pharmaceutical patent information analysis method is implemented. The specific steps of the method can be referred to the corresponding contents disclosed in the aforementioned embodiments, and will not be repeated here.

[0127] Furthermore, an embodiment of the present application also discloses a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of the large model-based pharmaceutical patent information analysis method as disclosed above.

[0128] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0129] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0130] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0131] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0132] The above is a detailed introduction to the large-model-based pharmaceutical patent information analysis method, device, equipment and medium provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for analyzing pharmaceutical patent information based on a large model, characterized in that: include: Get the medical patent uploaded by the current user and get the current medical patent; The current pharmaceutical patent is input into the fine-tuned large model, so as to parse the key information in the current pharmaceutical patent using the preset prompt information to obtain the target key information; the fine-tuned large model is a model obtained by fine-tuning the pre-trained model using the pharmaceutical patent data set; the target key information includes the target, indication and the applicant company of the current pharmaceutical patent; Determine the disease field of the current pharmaceutical patent according to the indication in the target key information to obtain the target disease field, and obtain the highest domestic and foreign research and development status of the current pharmaceutical patent from relevant websites according to the target disease field and the target in the target key information; Determine the level of the target based on the highest R&D status at home and abroad, obtain the target level, and judge whether the applicant company of the current pharmaceutical patent is a company of key concern, and obtain the judgment result; Whether the target in the target disease field has research and development value is determined based on the judgment result and the target level.

2. The method for analyzing pharmaceutical patent information based on a large model according to claim 1, characterized in that: The obtaining of the highest domestic and foreign research and development status of the current pharmaceutical patent from relevant websites based on the target disease field and the target in the target key information includes: The highest domestic and international research and development status of the current pharmaceutical patent is captured from relevant websites using a web crawler based on the target disease field and the targets in the target key information.

3. The method for analyzing pharmaceutical patent information based on a large model according to claim 1, characterized in that: Also includes: Collect different types of historical pharmaceutical patents to obtain a pharmaceutical patent dataset; Convert all historical pharmaceutical patents in the pharmaceutical patent dataset into a unified data format to obtain a converted dataset; Text recognition is performed on each medical patent in the converted data set to obtain historical patent text information, and the historical patent text information is input into a pre-trained model for model fine-tuning to obtain the fine-tuned large model; the pre-trained model is located in the inference server.

4. The method for analyzing pharmaceutical patent information based on a large model according to claim 3, characterized in that: The text recognition is performed on each pharmaceutical patent in the converted data set to obtain historical patent text information, including: The text information of each pharmaceutical patent in the converted data set is identified using an optical character recognition tool to obtain historical patent text information.

5. The method for analyzing pharmaceutical patent information based on a large model according to claim 1, characterized in that: The current pharmaceutical patent is input into the fine-tuned large model to analyze the key information in the current pharmaceutical patent using the preset prompt information to obtain the target key information, including: Convert the current pharmaceutical patent into a picture to obtain a target picture, and cut the target picture to obtain multiple sub-pictures; Text recognition is performed on each of the sub-images to obtain multiple current patent text information, and the current patent text information is input into the fine-tuned large model in turn to parse the key information in the current medical patent using preset prompt information to obtain target key information.

6. The method for analyzing pharmaceutical patent information based on a large model according to claim 1, characterized in that: Determining whether the target in the target disease field has research and development value based on the judgment result and the target level includes: Obtaining the appearance positions of the target and the indication in the current pharmaceutical patent to obtain first position information, and counting the number of times the target and the indication appear in the current pharmaceutical patent to obtain number information; The position where the applicant company appears in the current pharmaceutical patent is obtained to obtain the second position information, and whether the target in the target disease field has research and development value is determined based on the judgment result, the target level, the first position information, the number information and the second position information.

7. The method for analyzing pharmaceutical patent information based on a large model according to any one of claims 1 to 6, characterized in that: Also includes: The target key information, the target disease field, the highest domestic and international research and development status, the target level, the judgment result and the judgment result of whether it has research and development value are sent to the user terminal for structured display on the human-computer interaction interface of the user terminal.

8. A pharmaceutical patent information analysis device based on a large model, characterized in that: include: The patent acquisition module is used to obtain the medical patent uploaded by the current user and obtain the current medical patent; A parsing module, used for inputting the current pharmaceutical patent into the fine-tuned large model, so as to parse the key information in the current pharmaceutical patent using preset prompt information to obtain target key information; the fine-tuned large model is a model obtained by fine-tuning the pre-trained model using the pharmaceutical patent data set; the target key information includes the target, indication and the applicant company of the current pharmaceutical patent; A field determination module, used to determine the disease field of the current pharmaceutical patent according to the indication in the target key information, and obtain the target disease field; A status acquisition module, used to acquire the highest domestic and foreign research and development status of the current pharmaceutical patent from relevant websites according to the target disease field and the target in the target key information; A level determination module, used to determine the level of the target based on the highest research and development status at home and abroad to obtain the target level; A judgment module, used to judge whether the applicant company of the current pharmaceutical patent is a company of key concern, and obtain a judgment result; The research and development value determination module is used to determine whether the target in the target disease field has research and development value based on the determination result and the target level.

9. An electronic device, characterized in that: It comprises a processor and a memory; wherein, when the processor executes the computer program stored in the memory, the large model-based pharmaceutical patent information analysis method as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: Used to store computer programs; wherein, when the computer program is executed by a processor, the large model-based pharmaceutical patent information analysis method as described in any one of claims 1 to 7 is implemented.

Images