Mining Method, Device, Equipment and Storage Medium for Medical Device Sales Data

Abstract

An embodiment of the present invention provides a method and device for mining medical device sales data. Among them, the method includes: obtaining the bidding and procurement information of each hospital; obtaining the medical device bidding and procurement information of each hospital according to the bidding and procurement information of each hospital; and determining the sales data of the target medical device according to the medical device bidding and procurement information of each hospital. By using the method for mining medical device sales data disclosed in this embodiment, it is possible to quickly, accurately, and objectively obtain the medical device market sales data, greatly improving the data analysis efficiency and effectively enhancing the user experience.

Description

Technical Field

[0001] The present invention relates to the field of computer application technologies, and particularly relates to a method and device for mining medical device sales data. Additionally, it also relates to an electronic device and a non-transitory computer-readable storage medium. Background Art

[0002] For a long time, China's medical device industry has maintained a rapid and healthy development trend. It is speculated that the output value of China's medical devices has exceeded 800 billion yuan in 2020. According to online information, China's medical device industry has formed an industrial system with complete product categories and a perfect production chain, and has become an important medical device production base in the world. In the field of various mid- to low-end medical devices, China's output has ranked first in the world.

[0003] Due to problems such as complex circulation links and highly dispersed sales terminals in China's medical device industry, the market sales data of China's medical device products has always been blank. Enterprises can only obtain sample data of a specific regional market through market research and other methods to estimate the market capacity of a certain product, the enterprise competition pattern, etc. How to obtain objective and reliable medical device market sales data to guide R & D, sales, and investment has always been a pain point in the industry. Summary of the Invention

[0004] To this end, embodiments of the present invention provide a method, device, electronic device, and storage medium for mining medical device sales data to solve the problem in the prior art that objective, accurate, and complete sales data of the medical device market cannot be obtained.

[0005] In a first aspect, embodiments of the present invention provide a method for mining medical device sales data, including:

[0006] Obtaining the bidding and procurement information of each hospital;

[0007] Obtaining the medical device bidding and procurement information of each hospital according to the bidding and procurement information of each hospital;

[0008] Determining the sales data of the target medical device according to the medical device bidding and procurement information of each hospital.

[0009] Further, according to the method for mining medical device sales data, obtaining the bidding and procurement information of each hospital specifically includes:

[0010] Obtaining the bidding and procurement information from the bidding and procurement platforms at the national, provincial, municipal, and district levels, where the bidding and procurement information includes at least one of the public notice name of the winning bid result, bidding number, bidder, winning bidder, winning bid product, and winning bid time;

[0011] The tenderer information is filtered using hospital as the keyword, and the tendering and procurement information is deduplicated according to the tendering number to obtain the tendering and procurement information of each hospital.

[0012] Furthermore, according to the medical device sales data mining method, the medical device bidding and procurement information of each hospital is obtained according to the bidding and procurement information of each hospital, specifically including:

[0013] Screening the public names of the winning bid results and / or the winning products by keywords, or inputting the candidate public names of the winning bid results and / or the winning products into a domain classification model to obtain a domain classification result output by the domain classification model, wherein the domain classification model is trained based on the sample winning bid result names and the sample domain classification results;

[0014] Determine the public announcement name of the candidate winning bid result of the medical device and / or the information represented by the winning product whose field classification result is the target bidding and procurement information;

[0015] The medical device bidding and procurement information includes at least one of the following information: the name of the winning product, the product brand, the manufacturer, the product specifications, the product quantity, the winning unit price, and the winning total price.

[0016] Furthermore, according to the method for mining sales data of medical devices, the sales data of the target medical device is determined according to the bidding and purchasing information of medical devices of each hospital, wherein the sales data includes at least one of the following data: sales price, sales amount, competition pattern, and market capacity. The process of determining the sales data of the target medical device specifically includes:

[0017] Determine the sales price of the target medical device based on the winning product name, product brand, and winning unit price;

[0018] Determine the sales amount of the target medical device based on the winning product name, product brand, and winning total price;

[0019] Determine the competitive landscape and / or market capacity of the target medical product based on the winning product name, product brand, and sales amount.

[0020] Furthermore, according to the method for mining medical device sales data, obtaining the bidding and procurement information specifically includes:

[0021] First, the full text of the bidding and procurement document is obtained by direct extraction and / or text recognition model;

[0022] Secondly, based on the full text of the bidding and procurement documents, the target bidding and procurement information is obtained through entity recognition;

[0023] Among them, the entity recognition model is trained through the full text of the sample tender procurement documents and sample tender procurement information.

[0024] Furthermore, according to the method for mining medical device sales data described above, it further includes:

[0025] Perform standardization processing based on the tender procurement information of each hospital and the medical device tender procurement information, and construct a database of medical device sales data;

[0026] Based on a medical device information query request sent by the client, query and match in the database of medical device sales data to obtain the sales data of the target medical device, where the medical device information includes any one of the product name, product brand, and manufacturing enterprise;

[0027] Return the sales data of the medical device to the client so that the client can display the sales data of the target medical device.

[0028] In a second aspect, an embodiment of the present invention further provides a device for mining medical device sales data, including:

[0029] An information collection module: Obtain the tender procurement information of each hospital;

[0030] An information acquisition module: Obtain the medical device tender procurement information of each hospital according to the tender procurement information of each hospital;

[0031] An information analysis module: Determine the sales data of the target medical device according to the medical device tender procurement information of each hospital.

[0032] In a third aspect, an embodiment of the present invention further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that when the processor executes the program, it implements the steps of the method for mining medical device sales data described in any one of the above.

[0033] In a fourth aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, characterized in that a computer program is stored thereon, and when the computer program is executed by a processor, it implements the steps of the method for mining medical device sales data described in any one of the above.

[0034] By adopting the method for mining medical device sales data according to the embodiments of the present invention, by obtaining the bidding and procurement information of each hospital, and further obtaining the bidding and procurement information of medical devices in each hospital based on the bidding and procurement information of each hospital, and further determining the sales data of the target medical device according to the bidding and procurement information of medical devices in each hospital, the problem that the sales data of the medical device market cannot be obtained in the current market can be solved, helping users quickly, accurately and completely obtain the sales data of the medical device market, so as to further assist users in formulating more reasonable R & D, sales and investment strategies. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0036] Figure 1 It is a flowchart of a method for mining medical device sales data provided by an embodiment of the present invention;

[0037] Figure 2 It is a structural schematic diagram of a device for mining medical device sales data provided by an embodiment of the present invention;

[0038] Figure 3 It is a schematic physical structure diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0039] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0040] The following will describe in detail the embodiments based on the method for mining medical device sales data according to the present invention. As Figure 1 shown, it is a flowchart of the method for mining medical device sales data provided by an embodiment of the present invention, and the specific implementation process includes the following steps:

[0041] Step 110: Obtain the bidding and procurement information of each hospital;

[0042] Specifically, due to the complex circulation links and highly dispersed sales terminals in China's medical device industry, the market sales data of medical device products in China has always been blank. With the increasingly open and transparent transaction information in the public medical system, the equipment procurement of first-level hospitals in each province, city, and county basically follows the open tendering and procurement procedures. Correspondingly, various tendering and procurement information will be disclosed in a vast number of government tendering and procurement announcements at all levels. Therefore, it becomes possible to extract the tendering and procurement information of hospitals and then extract the relevant data of medical devices through the tendering and procurement information of each province, city, and county.

[0043] Therefore, this solution obtains tendering and procurement information from the tendering and procurement platforms at the national, provincial, municipal, and district levels. The tendering and procurement information includes at least one of the information such as the public notice name of the winning bid result, tendering number, tenderer, winning bidder, winning bid product, and winning bid time.

[0044] Furthermore, the tendering and procurement information of each hospital is obtained by screening the tenderer information with the hospital as the keyword.

[0045] Considering that the tendering and procurement information of a hospital may be registered on multiple procurement platforms, such as the national, provincial, municipal, and district where the hospital is located, etc. Therefore, in the embodiment of the present invention, the tendering and procurement information can be deduplicated according to the tendering number to obtain accurate and complete tendering and procurement information of each hospital.

[0046] Step 120: Obtain the tendering and procurement information of medical devices of each hospital according to the tendering and procurement information of each hospital.

[0047] Considering that, on the one hand, the tendering and procurement information of each hospital not only includes the tendering and procurement information of medical devices but also includes the tendering and procurement information in many other fields; on the other hand, some information in the public notice name of the winning bid result and / or the winning bid product of the tendering and procurement information will contain keywords such as "medical equipment" and "medical device", and some public notice names of the winning bid results and / or winning bid products will directly state specific medical devices, such as "color ultrasonic diagnostic instrument", etc.

[0048] Therefore, in the embodiment of the present invention, the public notice name of the winning bid result and / or the winning bid product can be screened through keywords such as "medical equipment" and "medical device", or the candidate public notice name of the winning bid result and / or the winning bid product is input into the domain classification model to obtain the domain classification result output by the domain classification model, and the information represented by the candidate public notice name of the winning bid result with the domain classification result of the medical device is determined as the target tendering and procurement information.

[0049] Specifically, the training steps of the field classification model may specifically include: collecting a large number of winning bid result public announcement names and / or winning bid product information, and labeling whether the winning bid result public announcement names and / or winning bid products belong to medical devices as the field classification results of the winning bid result public announcement names and / or winning bid products. Training the initial model based on the winning bid result public announcement names and / or winning bid product information and the field classification results of the winning bid result public announcement names and / or winning bid products to obtain the field classification model. Preferably, the initial model here may be the mBERT model that can be used for multiple languages.

[0050] The medical device bidding and procurement information includes at least one of the information such as the winning bid product name, product brand, manufacturer, product specification, product quantity, winning bid unit price, and winning bid total price.

[0051] Specifically, when obtaining the hospital bidding and procurement information and further obtaining the medical device bidding and procurement information, the full text of the bidding and procurement document where the bidding and procurement information is located may be a document in a web page, a PDF document, or a Word document, and the embodiments of the present invention do not make specific limitations here.

[0052] For the full text of bidding and procurement documents in different forms, different extraction rules are adopted in this embodiment so that the extraction rules corresponding to the full text of each type of bidding and procurement document can adapt to the full text type of the document, thereby ensuring the integrity and accuracy of the acquired data.

[0053] Based on the above embodiments, for the full text of the bidding and procurement document of the web page type, the full text of the bidding and procurement document can be directly extracted. For the full text of the PDF type document, a text recognition model can be used to obtain the full text of the bidding and procurement document. Here, the text recognition can be implemented through an OCR (Optical Character Recognition) text recognition model.

[0054] Further, based on the full text of the bidding and procurement document, entity recognition is performed on the full text of the hospital bidding and procurement document and the full text of the bidding and procurement document classified as the medical device field to obtain the target bidding and procurement information; the hospital bidding and procurement information includes at least one of the information such as the winning bid result public announcement name, bidding number, bidder, winning bidder, winning bid product, and winning bid time, and the medical device bidding and procurement information includes at least one of the information such as the winning bid product name, product brand, manufacturer, product specification, product quantity, winning bid unit price, and winning bid total price.

[0055] For example,

[0056] Serial number 1 Project number xxxxxxxxx-xx Tenderer xx Hospital Successful bidder xx Company Won the bid product 64-slice 128-layer spiral CT Winning bid time xxxx-xx-xx Name of the product that won the bid Medical X-ray equipment Product brand GE Healthcare Manufacturing enterprise xx Company Product specification Optima CT680 Eepert Quantity of products 1 Unit price of winning the bid (yuan) xxx,xxx.xx Total price of winning the bid (yuan) xxx,xxx.xx

[0057] Step 130: Determine the sales data of the target medical device according to the medical device bidding and procurement information of each hospital;

[0058] The sales data includes at least one of the sales price, sales amount, competition pattern, and market capacity. The process of determining the sales data of the target medical device specifically includes:

[0059] Determine the sales price of the target medical device according to the winning bid product name, product brand, and winning bid unit price;

[0060] Determine the sales amount of the target medical device according to the winning bid product name, product brand, and winning bid total price;

[0061] Specifically, the sales price is the sales unit price of the target medical device in the market, and the sales amount is the total sales amount of the target medical device in the market. Based on the winning bid product name and product brand, the target medical device can be determined. Based on all the winning bid unit prices of the target medical device, the average or median of all the winning bid unit prices corresponding to the target medical device can be statistically analyzed to judge the sales price of the target medical device. The specific statistical method for determining the sales price is not specifically limited in this embodiment; further, based on all the winning bid total prices of the target medical device, the sales amount of the target medical device can be obtained by summing up all the winning bid total prices.

[0062] Further, determine the competition pattern and / or market capacity of the target medical product according to the winning bid product name, product brand, and sales amount.

[0063] Specifically, the competition pattern is the comparison between the corresponding sales amounts of the same medical device with the same product name under different product brands, and the market capacity is the total sales amount of the same medical device with the same product name.

[0064] Specifically, based on the method for determining the sales amount of the target medical device in the above embodiment, the sales amounts of different product brands corresponding to the same product name are obtained, and thus the competition pattern of the target medical device in the market at present can be obtained through comparative analysis, such as the market share of the target medical device, the main competitors, etc.; the market capacity of the target medical device is obtained by summing up the sales amounts of all medical devices with the same product name.

[0065] Based on the sales price, sales amount, competition pattern, and market capacity of the target medical device, it can further guide the enterprise to make more objective and reliable decisions in research and development, sales, and investment strategies.

[0066] Furthermore, in order to facilitate users to obtain objective, accurate, and complete medical device sales data more conveniently and quickly, this solution performs standardized processing according to the hospital bidding and procurement information and the medical device bidding and procurement information, and constructs a database of medical device sales data;

[0067] The standardization process of the tender procurement information includes, for example, converting the format of time information, matching the obtained production enterprise and product name information with the established enterprise dictionary and medical device standard name dictionary respectively to obtain the standard production enterprise and product name information, uniformly processing the format of the winning bid unit price and winning bid total price information, etc.;

[0068] Based on the medical device information query request sent by the client, the sales data of the target medical device is retrieved and matched in the database of the medical device sales data. The medical device information includes any one of the product name, product brand, and production enterprise;

[0069] The sales data of the medical device is returned to the client so that the client can display the sales data of the target medical device.

[0070] By adopting the method for mining medical device sales data described in the embodiments of the present invention, by obtaining the tender procurement information of each hospital, obtaining the medical device tender procurement information of each hospital according to the tender procurement information of each hospital, and determining the sales data of the target medical device according to the medical device tender procurement information of each hospital, the problem that the market sales data of medical devices cannot be obtained in the current market can be solved, helping users to quickly, accurately and completely obtain the sales data of the medical device market, so as to further assist users in formulating more reasonable R & D, sales and investment strategies.

[0071] Corresponding to the above-provided method for mining medical device sales data, the present invention also provides a device for mining medical device sales data. Since the embodiments of this device are similar to the above method embodiments, the description is relatively simple. For the relevant parts, please refer to the description of the above method embodiments. The following description of the embodiments of the device for mining medical device sales data is only illustrative. Please refer to Figure 2 As shown, it is a schematic structural diagram of a device for mining medical device sales data provided by an embodiment of the present invention.

[0072] The device for mining medical device sales data described in the present invention specifically includes the following parts:

[0073] Information collection module 210: Obtain the tender procurement information of each hospital;

[0074] Information acquisition module 220: Obtain the medical device tender procurement information of each hospital according to the tender procurement information of each hospital;

[0075] Information analysis module 230: Determine the sales data of the target medical device according to the medical device tender procurement information of each hospital.

[0076] By adopting a mining device for medical device sales data according to the embodiments of the present invention, by obtaining the bidding and procurement information of each hospital, obtaining the medical device bidding and procurement information of each hospital according to the bidding and procurement information of each hospital, and determining the sales data of the target medical device according to the medical device bidding and procurement information of each hospital, the problem that the sales data of the medical device market cannot be obtained in the current market can be solved, and the user can be helped to quickly, accurately and completely obtain the sales data of the medical device market, so as to further assist the user in formulating more reasonable R & D, sales and investment strategies.

[0077] Corresponding to the above-provided method for mining medical device sales data, the present invention also provides an electronic device. Since the embodiments of this electronic device are similar to the above method embodiments, the description is relatively simple. For related parts, please refer to the description in the above method embodiment section. The following-described electronic device is only illustrative. As Figure 3 shown, it is a schematic diagram of the physical structure of an electronic device disclosed in an embodiment of the present invention. The electronic device may include: a processor 301, a memory 302, and a communication bus 303. Among them, the processor 301 and the memory 302 communicate with each other through the communication bus 303. The processor 301 can call the logical instructions in the memory 302 to execute the method for mining medical device sales data, and this method includes: obtaining the bidding and procurement information of each hospital; obtaining the medical device bidding and procurement information of each hospital according to the bidding and procurement information of each hospital; and determining the sales data of the target medical device according to the medical device bidding and procurement information of each hospital.

[0078] In addition, when the logical instructions in the above-mentioned memory 302 can be implemented in the form of a software functional unit and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk, or an optical disc that can store program codes.

[0079] On the other hand, an embodiment of the present invention further provides a computer program product. The computer program product includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer is capable of executing the method for mining medical device sales data provided in each of the above method embodiments. The method includes: obtaining the bidding and procurement information of each hospital; obtaining the medical device bidding and procurement information of each hospital according to the bidding and procurement information of each hospital; and determining the sales data of the target medical device according to the medical device bidding and procurement information of each hospital.

[0080] In another aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is configured to execute the method for mining medical device sales data provided in each of the above embodiments. The method includes: obtaining the bidding and procurement information of each hospital; obtaining the medical device bidding and procurement information of each hospital according to the bidding and procurement information of each hospital; and determining the sales data of the target medical device according to the medical device bidding and procurement information of each hospital.

[0081] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0082] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, also by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0083] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in each of the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of each embodiment of the present invention.

Claims

1. A method for mining medical device sales data, characterized in that, Including: Obtain the bidding and procurement information of each hospital; Obtain the medical device bidding and procurement information of each hospital according to the bidding and procurement information of each hospital; Determine the sales data of the target medical device according to the medical device bidding and procurement information of each hospital; the sales data includes sales amount, competition pattern, and market capacity; Among them, the steps for obtaining the competition pattern and market capacity include: Obtain the sales amounts corresponding to different product brands under the same product name and conduct comparative analysis to obtain the current competition pattern of the target medical device in the market; Sum up the sales amounts of all medical devices under the same product name to obtain the market capacity of the target medical device.

2. The method for mining medical device sales data according to claim 1, wherein Obtain the bidding and procurement information of each hospital, specifically including: Obtain the bidding and procurement information from the bidding and procurement platforms at the national, provincial, municipal, and district levels. The bidding and procurement information includes at least one of the information such as the public notice name of the winning bid result, bidding number, bidder, winning bidder, winning bid product, and winning bid time; Screen the bidder information with the hospital as the keyword and deduplicate the bidding and procurement information according to the bidding number to obtain the bidding and procurement information of each hospital.

3. The method for mining medical device sales data according to claim 1, wherein Obtain the medical device bidding and procurement information of each hospital according to the bidding and procurement information of each hospital, specifically including: Screen the public notice name of the winning bid result and / or the winning bid product through keywords, or input the candidate public notice name of the winning bid result and / or the winning bid product into the field classification model to obtain the field classification result output by the field classification model. The field classification model is trained based on the sample public notice name of the winning bid result and / or the winning bid product and the sample field classification result; Determine the information represented by the candidate public notice name of the winning bid result and / or the winning bid product with the field classification result of the medical device as the target bidding and procurement information; The medical device bidding and procurement information includes at least one of the information such as the winning bid product name, product brand, manufacturing enterprise, product specification, product quantity, winning bid unit price, and winning bid total price.

4. The method for mining medical device sales data according to claim 1, characterized in that, Determine the sales data of the target medical device according to the medical device bidding and procurement information of each hospital. The sales data also includes the sales price. The process of determining the sales data of the target medical device specifically includes: Determine the sales price of the target medical device according to the winning bid product name, product brand, and winning bid unit price; Determine the sales amount of the target medical device according to the winning bid product name, product brand, and winning bid total price.

5. The method for mining medical device sales data according to claim 2 or 4, characterized in that, Obtain the bidding and procurement information, specifically including: First, obtain the full text of the bidding and procurement document through direct extraction and / or text recognition model for the bidding and procurement document; Secondly, based on the full text of the bidding and procurement document, obtain the target bidding and procurement information through entity recognition; Among them, the entity recognition model is trained through the sample full text of the bidding and procurement document and the sample bidding and procurement information.

6. The method for mining medical device sales data according to any one of claims 1 to 4, characterized in that, Also including: Conduct standardization processing according to the bidding and procurement information of each hospital and the medical device bidding and procurement information, and construct a database of medical device sales data; Based on the medical device information query request sent by the client, query and match the sales data of the target medical device in the database of the medical device sales data, where the medical device information includes any one of the product name, product brand, and manufacturing enterprise; Return the sales data of the medical device to the client so that the client can display the sales data of the target medical device.

7. A mining device for medical device sales data, characterized in that, It includes: Information collection module: Obtain the bidding and procurement information of each hospital; Information acquisition module: Obtain the medical device bidding and procurement information of each hospital according to the bidding and procurement information of each hospital; Information analysis module: Determine the sales data of the target medical device according to the medical device bidding and procurement information of each hospital; The sales data includes sales amount, competition pattern, and market capacity; Among them, the steps for obtaining the competition pattern and market capacity include: Obtain the sales amounts corresponding to different product brands under the same product name and conduct comparative analysis to obtain the current competition pattern of the target medical device in the market; Sum up the sales amounts of all medical devices under the same product name to obtain the market capacity of the target medical device.

8. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the method for mining medical device sales data as described in any one of claims 1-6.

9. A non-transitory computer-readable storage medium, characterized in that, It stores a computer program thereon, characterized in that when the computer program is executed by a processor, it implements the steps of the method for mining medical device sales data as described in any one of claims 1-6.

Images