Disease search sorting method and device, equipment and storage medium

Abstract

The application relates to an artificial intelligence technology and discloses a disease search sorting method, which comprises the following steps: receiving a disease search keyword of a user, performing semantic matching screening on all candidate data in a preset candidate data set according to the disease search keyword, and obtaining one or more initial candidate data; performing disease name component division on the disease search keyword, obtaining one or more component keywords and a component category corresponding to each component keyword; calculating the similarity score of each component keyword corresponding to the component category and the initial candidate data, obtaining the target similarity score of the initial candidate data; sorting all the initial candidate data based on the target similarity score, obtaining a search sorting result, and sending the search sorting result to the user. The application further discloses a disease search sorting device, equipment and medium, which can be used in the medical field and improves the accuracy of disease search sorting.

Description

Technical Field

[0001] This invention relates to the fields of artificial intelligence technology and healthcare, and particularly to a disease search and ranking method, apparatus, electronic device, and storage medium. Background Technology

[0002] In the healthcare field, in order to search for disease-related content or knowledge texts that users want based on the disease search keywords they input, disease search ranking is required.

[0003] However, existing disease search ranking methods directly match and filter the content to be retrieved based on the semantic matching degree between the disease search keywords and the content to be retrieved. The matching and filtering dimensions are too single, which cannot accurately rank the content that users need at the top, resulting in low accuracy of disease search ranking. Summary of the Invention

[0004] This invention provides a disease search and ranking method, apparatus, electronic device, and storage medium, the main purpose of which is to improve the accuracy of disease search and ranking.

[0005] Receive the user's disease search keywords, and perform semantic matching and filtering on all candidate data in the preset candidate dataset based on the disease search keywords to obtain one or more initial candidate data;

[0006] The disease search keywords are divided into disease name components to obtain one or more disease name component keywords and a first name component category corresponding to each disease name component keyword;

[0007] Based on the first name composition category, keywords are extracted from the initial candidate data to obtain candidate keywords of the initial candidate data and a second name composition category corresponding to each candidate keyword;

[0008] Based on the first name composition category and the second name composition category, the word similarity between the disease name composition keywords and candidate keywords corresponding to the same name composition category is calculated to obtain the similarity score of each first name composition category corresponding to the initial candidate data;

[0009] The target similarity score of the initial candidate data is obtained by weighting the preset weight threshold corresponding to each of the first name component categories and the similarity score of each of the first name component categories corresponding to the initial candidate data.

[0010] All the initial candidate data are sorted based on the target similarity score to obtain the search ranking result, and the search ranking result is sent to the user's preset terminal device.

[0011] Optionally, the step of semantically matching and filtering all candidate data in a preset candidate dataset based on the disease search keywords to obtain one or more initial candidate data includes:

[0012] Convert the disease search keywords into search vectors;

[0013] Obtain the candidate vector for each of the candidate data;

[0014] Calculate the vector similarity between each candidate vector and the search vector to obtain the semantic matching degree of each candidate vector;

[0015] Based on the semantic matching degree, all candidate data in the candidate dataset are filtered to obtain the initial candidate data.

[0016] Optionally, the step of filtering all candidate data in the candidate dataset based on the semantic matching degree to obtain the initial candidate data includes:

[0017] The semantic matching degree that is greater than the preset semantic matching threshold is used to determine the target semantic matching degree;

[0018] The candidate vector corresponding to the target semantic matching degree is determined as the target candidate vector;

[0019] The initial candidate data is obtained by filtering the candidate data corresponding to the target candidate vector in the candidate dataset.

[0020] Optionally, the step of dividing the disease search keywords into disease name components to obtain one or more disease name component keywords and a first name component category corresponding to each disease name component keyword includes:

[0021] Obtain a name dictionary tree that categorizes different preset names;

[0022] The disease search keywords are segmented to obtain one or more segmented words;

[0023] The segmented words existing in any of the aforementioned name dictionary trees are determined as keywords to form the name of the disease;

[0024] The preset name composition category corresponding to the name dictionary tree containing the disease name composition keywords is determined as the first name composition category corresponding to the disease name composition keywords.

[0025] Optionally, the step of extracting keywords from the initial candidate data based on the first name composition category to obtain candidate keywords of the initial candidate data and a second name composition category corresponding to each candidate keyword includes:

[0026] The candidate data is segmented into words to obtain one or more candidate words;

[0027] Candidate words that exist in the name dictionary of any of the first name composition categories are identified as candidate keywords;

[0028] The first name composition category corresponding to the name dictionary tree containing the candidate keyword is determined as the second name composition category corresponding to the candidate keyword.

[0029] Optionally, the step of calculating the word similarity between disease name component keywords and candidate keywords corresponding to the same name component category based on the first name component category and the second name component category, to obtain a similarity score for each first name component category corresponding to the initial candidate data, includes:

[0030] Summarize all the categories that make up the first name to obtain the set of categories that make up the first name;

[0031] By summing up all the candidate keywords corresponding to the second name composition categories in the initial candidate data, a set of second name composition categories corresponding to the initial candidate data is obtained.

[0032] Calculate the difference between the second name composition category set and the first name composition category set to obtain the third name composition category set;

[0033] Obtain the preset initial similarity score corresponding to each of the first name categories;

[0034] The preset initial similarity score corresponding to the first name composition category in the third name composition category set is determined as the similarity score of the first name composition category;

[0035] Calculate the word similarity between the disease name composition keywords corresponding to the first name composition category in the second name composition category set and the candidate keywords corresponding to the same name composition category in the initial candidate data, and obtain the similarity score of the first name composition category.

[0036] Optionally, the step of sorting all the initial candidate data based on the target similarity score to obtain a search ranking result, and sending the search ranking result to the user's preset terminal device, includes:

[0037] Sort all the initial candidate data in descending order of their corresponding target similarity scores to obtain the search ranking results;

[0038] The search ranking results are sent to the user's preset terminal device.

[0039] To address the above problems, the present invention also provides a disease search and ranking device, the device comprising:

[0040] The keyword extraction module is used to receive the user's disease search keywords, perform semantic matching and filtering on all candidate data in a preset candidate dataset based on the disease search keywords to obtain one or more initial candidate data; divide the disease search keywords into disease name components to obtain one or more disease name component keywords and a first name component category corresponding to each disease name component keyword; and extract keywords from the initial candidate data based on the first name component category to obtain candidate keywords of the initial candidate data and a second name component category corresponding to each candidate keyword.

[0041] The similarity classification calculation module is used to calculate the word similarity between disease name component keywords and candidate keywords corresponding to the same name component category based on the first name component category and the second name component category, so as to obtain the similarity score of each first name component category corresponding to the initial candidate data; and to perform weighted calculation based on the preset weight threshold corresponding to each first name component category and the similarity score of each first name component category corresponding to the initial candidate data to obtain the target similarity score of the initial candidate data.

[0042] The disease search ranking module is used to rank all the initial candidate data based on the target similarity score, obtain the search ranking result, and send the search ranking result to the user's preset terminal device.

[0043] To address the above problems, the present invention also provides an electronic device, the electronic device comprising:

[0044] Memory, storing at least one computer program; and

[0045] The processor executes the computer program stored in the memory to implement the disease search and ranking method described above.

[0046] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing at least one computer program, which is executed by a processor in an electronic device to implement the disease search and ranking method described above.

[0047] This invention, in its embodiments, performs semantic matching and filtering on all candidate data in a preset candidate dataset based on the disease search keywords, obtaining one or more initial candidate data. It then divides the disease search keywords into disease name components, obtaining one or more disease name component keywords and a first name component category corresponding to each disease name component keyword. Based on the first name component categories, it extracts keywords from the initial candidate data, obtaining candidate keywords and a second name component category corresponding to each candidate keyword. Based on the first and second name component categories, it calculates the word similarity between disease name component keywords and candidate keywords corresponding to the same name component category, obtaining a similarity score for each first name component category corresponding to the initial candidate data. By using disease search keywords for semantic filtering and matching, and calculating the matching degree with the initial candidate data from different components of the disease search keywords, the matching dimensions are more diverse, resulting in higher accuracy in disease search ranking compared to directly using disease search keywords for semantic matching and ranking. Therefore, the disease search ranking method, device, electronic device, and readable storage medium proposed in this invention improve the accuracy of disease search ranking. Attached Figure Description

[0048] Figure 1 This is a flowchart illustrating a disease search and ranking method according to an embodiment of the present invention.

[0049] Figure 2 This is a schematic diagram of a disease search and sorting device according to an embodiment of the present invention;

[0050] Figure 3 This is a schematic diagram of the internal structure of an electronic device for implementing a disease search and ranking method according to an embodiment of the present invention.

[0051] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0052] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0053] This invention provides a disease search and ranking method. The executing entity of the disease search and ranking method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application embodiment: a server, a terminal, etc. In other words, the disease search and ranking method can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster, etc. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0054] Reference Figure 1 The flowchart shown is a disease search and ranking method provided in an embodiment of the present invention. In this embodiment, the disease search and ranking method includes the following steps:

[0055] S1. Receive the user's disease search keywords, and perform semantic matching and filtering on all candidate data in the preset candidate dataset according to the disease search keywords to obtain one or more initial candidate data.

[0056] In this embodiment of the invention, the disease search keywords are the names of diseases that users use to search for related text content, such as: stage one diabetes, etc.

[0057] Furthermore, in this embodiment of the invention, the candidate data is searchable disease-related text content. Based on the disease search keywords, semantic matching and filtering are performed on all candidate data in the preset candidate dataset to obtain one or more initial candidate data.

[0058] In detail, in this embodiment of the invention, the semantic matching and filtering of all candidate data in a preset candidate dataset based on the disease search keywords to obtain one or more initial candidate data includes:

[0059] Convert the disease search keywords into search vectors;

[0060] Obtain the candidate vector for each of the candidate data;

[0061] Calculate the vector similarity between each candidate vector and the search vector to obtain the semantic matching degree of each candidate vector;

[0062] Based on the semantic matching degree, all candidate data in the candidate dataset are filtered to obtain the initial candidate data.

[0063] In detail, in this embodiment of the invention, the disease search keywords are converted into vectors to obtain search vectors. The disease search keywords can be converted into search vectors using a deep learning model (such as the BERT model), or the bag-of-words model, one-hot algorithm, etc. The embodiments of the invention do not limit this.

[0064] Further, in this embodiment of the invention, the process of filtering all candidate data in the candidate dataset based on the semantic matching degree to obtain the initial candidate data includes:

[0065] The semantic matching degree that is greater than the preset semantic matching threshold is used to determine the target semantic matching degree;

[0066] The candidate vector corresponding to the target semantic matching degree is determined as the target candidate vector;

[0067] The initial candidate data is obtained by filtering the candidate data corresponding to the target candidate vector in the candidate dataset.

[0068] In this embodiment of the invention, the candidate vector is a vector transformed from the candidate data. The method for transforming the candidate vector into a candidate vector is similar to the method for transforming the disease search keywords into search vectors, and will not be described in detail here.

[0069] S2. Divide the disease search keywords into disease name components to obtain one or more disease name component keywords and a first name component category corresponding to each disease name component keyword;

[0070] In this embodiment of the invention, when directly matching candidate data using the disease search keywords, the matching dimension is too singular. In order to perform matching in a more multidimensional way, the disease search keywords are divided into disease name components to obtain one or more disease name component keywords and a first name component category corresponding to each disease name component keyword. Matching is then performed from the dimension of each disease name component keyword, and all matching results are combined to optimize the sorting of candidate data in the initial candidate dataset.

[0071] It should be noted that in the embodiments of the present invention, according to the naming rules of diseases, the disease names are divided into different constituent parts, that is, different name composition categories, such as: theme, location, population, stage, level, negation, category, direction, organism, etc. Each target name combination category has its own corresponding keywords, such as: theme: diabetes, hypertension, etc.; location: head, foot, mouth, leg, etc.; population: children, middle-aged, elderly, etc.; stage: stage I, stage a, stage 5, etc.; level: severe, level I, level 2; negation: not accompanied by, no, non; category: group A, group B; direction: left side, right side, two-way, etc.; organism: Helicobacter pylori, Neisseria catarrhalis. In the embodiments of the present invention, if the disease search keyword contains the keyword corresponding to a certain name composition category, then this keyword is determined as the disease name composition keyword, and the composition category corresponding to this disease name composition keyword is determined as the first name composition category.

[0072] Specifically, in the embodiments of the present invention, the division of the disease search keyword into disease name constituent parts to obtain one or more disease name constituent keywords and the first name composition category corresponding to each disease name constituent keyword includes:

[0073] Obtain the name trie trees of different preset name composition categories;

[0074] Segment the disease search keyword to obtain one or more segmented words;

[0075] Determine the segmented words existing in any of the name trie trees as the disease name constituent keywords;

[0076] Determine the preset name composition category corresponding to the name trie tree where the disease name constituent keyword exists as the first name composition category corresponding to this disease name constituent keyword.

[0077] In the embodiments of the present invention, the name trie tree is a trie tree constructed based on the keyword dictionary of the preset name composition category. For example, if the preset name composition category is category A, the name trie tree of category A is a pre-constructed dictionary composed of all keywords of category A.

[0078] Furthermore, in the embodiments of the present invention, if there are multiple segmented words with the same starting character in the name trie tree and there is an inclusion relationship among these segmented words, then the segmented word with the longest character among these segmented words is determined as the disease name constituent keyword. For example: in the name trie tree A, there are two segmented words, namely "gastroenteritis" and "gastrointestinal inflammation", and the starting characters of the two segmented words are both "gastro", and "gastroenteritis" is included in "gastrointestinal inflammation", then the segmented word with the longest character, "gastrointestinal inflammation", is determined as the disease name constituent keyword.

[0079] S3. Based on the first name composition category, extract keywords from the initial candidate data to obtain candidate keywords of the initial candidate data and a second name composition category corresponding to each candidate keyword;

[0080] In this embodiment of the invention, in order to compare the correlation between disease search keywords and each candidate data in the initial candidate dataset from the dimension of each first name component category, candidate keywords corresponding to each first name component category in the initial candidate data are extracted.

[0081] In detail, in this embodiment of the invention, the extraction of candidate keywords corresponding to each of the first name components in the initial candidate data includes:

[0082] The candidate data is segmented into words to obtain one or more candidate words;

[0083] Candidate words that exist in the name dictionary of any of the first name composition categories are identified as candidate keywords;

[0084] The first name composition category corresponding to the name dictionary tree containing the candidate keyword is determined as the second name composition category corresponding to the candidate keyword.

[0085] S4. Based on the first name composition category and the second name composition category, calculate the word similarity between the disease name composition keywords and candidate keywords corresponding to the same name composition category, so as to obtain the similarity score of each first name composition category corresponding to the initial candidate data;

[0086] In detail, in this embodiment of the invention, based on the first name component category and the second name component category, the word similarity between disease name component keywords and candidate keywords corresponding to the same name component category is calculated to obtain a similarity score for each first name component category corresponding to the initial candidate data, including:

[0087] Summarize all the categories that make up the first name to obtain the set of categories that make up the first name;

[0088] By summing up all the candidate keywords corresponding to the second name composition categories in the initial candidate data, a set of second name composition categories corresponding to the initial candidate data is obtained.

[0089] Calculate the difference between the second name composition category set and the first name composition category set to obtain the third name composition category set;

[0090] Obtain the preset initial similarity score corresponding to each of the first name categories;

[0091] The preset initial similarity score corresponding to the first name composition category in the third name composition category set is determined as the similarity score of the first name composition category;

[0092] Calculate the word similarity between the disease name composition keywords corresponding to the first name composition category in the second name composition category set and the candidate keywords corresponding to the same name composition category in the initial candidate data, and obtain the similarity score of the first name composition category.

[0093] For example: There are three first name composition categories, namely category A, category B, and category C; all candidate keywords of the initial candidate data a correspond to two second name composition categories, namely category A and category B; then the first name composition category set contains category A, category B, and category C, the second name composition category set contains category A and category B, and the third name composition category set contains category C; calculate the word similarity between the candidate keywords corresponding to category A in the initial candidate data a and the disease name composition keywords corresponding to category A, to obtain the similarity score of category A corresponding to the initial candidate data a; calculate the word similarity between the candidate keywords corresponding to category B in the initial candidate data a and the disease name composition keywords corresponding to category B, to obtain the similarity score of category B corresponding to the initial candidate data a; and determine the preset initial similarity score corresponding to category C as the similarity score of category C corresponding to the initial candidate data a.

[0094] Specifically, in this embodiment of the invention, if the disease name constituent keywords and candidate keywords corresponding to the same name constituent categories for calculating word similarity are both single words (for example: calculating the word similarity between candidate keywords corresponding to category A in initial candidate data a and disease name constituent keywords corresponding to category A, where candidate keywords corresponding to category A in initial candidate data a are single words, and disease name constituent keywords corresponding to category A are also single words), text similarity (the semantic similarity between disease name constituent keywords and candidate keywords measures word similarity), thesaurus similarity (if disease name constituent keywords and candidate keywords are synonyms, the corresponding similarity score is 1; if disease name constituent keywords and candidate keywords are synonyms, the corresponding similarity score is 0), and graph node similarity (measured based on the distance between the node where the candidate keyword is located and the node where the disease name constituent keyword is located) can be used. The present invention does not limit the word similarity calculation method among the similarity calculation methods such as the word similarity between disease name constituent keywords and candidate keywords; if there are multiple words in the disease name constituent keywords and candidate keywords corresponding to the same name constituent category for calculating word similarity, then the multiple words are concatenated and the word similarity is calculated using text similarity (for example: calculate the word similarity between the candidate keywords corresponding to category A in the initial candidate data a and the disease name constituent keywords corresponding to category A, where the candidate keywords corresponding to category A in the initial candidate data a are multiple words such as "head" and "head", and the disease name constituent keyword corresponding to category A is "head", then the multiple words of the candidate keywords are concatenated to obtain the text "head head", and the text similarity between "head head" and the disease name constituent keyword "head" is calculated, which is the similarity score of category A corresponding to the initial candidate data a).

[0095] Optionally, in this embodiment of the invention, the preset initial similarity score is any real number in the range [0,1].

[0096] S5. Calculate the target similarity score of the initial candidate data by weighting the preset weight threshold corresponding to each of the first name component categories and the similarity score of each of the first name component categories corresponding to the initial candidate data.

[0097] In this embodiment of the invention, the target similarity score of the initial candidate data is obtained by weighting the calculation based on the preset weight threshold corresponding to each of the first name component categories and the similarity score of each of the first name component categories corresponding to the initial candidate data.

[0098] In detail, in this embodiment of the invention, the weighted calculation based on the preset weight threshold corresponding to each of the first name component categories and the similarity score of each of the first name component categories corresponding to the initial candidate data to obtain the target similarity score of the initial candidate data includes:

[0099] The similarity score of each first name component category corresponding to the initial candidate data is multiplied by the preset weight threshold corresponding to the same first name component category to obtain the weighted similarity score of each first name component category corresponding to the initial candidate data.

[0100] The target similarity score of the initial candidate data is obtained by summing the weighted similarity scores of all first name categories corresponding to the initial candidate data.

[0101] S6. Sort all the initial candidate data based on the target similarity score to obtain the search ranking result, and send the search ranking result to the user's preset terminal device.

[0102] In this embodiment of the invention, the target similarity score is used to further measure the degree of association between each initial candidate data and the disease search keyword. In order to ensure that users can see the initial candidate data with a high degree of association first, all the initial candidate data are sorted based on the target similarity score to obtain the search ranking result, and the search ranking result is sent to the user's preset terminal device.

[0103] In detail, in this embodiment of the invention, all the initial candidate data are sorted based on the target similarity score to obtain a search ranking result, and the search ranking result is sent to the user's preset terminal device, including:

[0104] Sort all the initial candidate data in descending order of their corresponding target similarity scores to obtain the search ranking results;

[0105] The search ranking results are sent to the user's preset terminal device.

[0106] In one embodiment of the present invention, sorting all the initial candidate data based on the target similarity score to obtain a search ranking result, and sending the search ranking result to the user's preset terminal device, includes:

[0107] Initial candidate data whose target similarity score is greater than a preset similarity score threshold are identified as target candidate data;

[0108] Sort all the target candidate data in descending order of their corresponding target similarity scores to obtain the search ranking results;

[0109] The search ranking results are sent to the user's preset terminal device.

[0110] In one embodiment of the present invention, sorting all the initial candidate data based on the target similarity score to obtain a search ranking result, and sending the search ranking result to the user's preset terminal device, includes:

[0111] Sort all the initial candidate data in descending order of their corresponding target similarity scores to obtain the initial candidate data sequence;

[0112] The initial candidate data sequence is segmented to obtain all initial candidate data that are in order before a preset segmentation order, thus obtaining the search sorting result;

[0113] The search sorting node is sent to the user's preset terminal device.

[0114] Optionally, the preset terminal device in this embodiment of the invention is a terminal device capable of displaying the initial candidate data, including but not limited to: mobile phones, computers, and tablets.

[0115] like Figure 2 The diagram shown is a functional block diagram of the disease search and sorting device of the present invention.

[0116] The disease search and ranking device 100 of the present invention can be installed in an electronic device. Depending on the functions implemented, the disease search and ranking device may include a keyword extraction module 101, a similarity classification calculation module 102, and a disease search and ranking module 103. The module described in the present invention may also be referred to as a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and are stored in the memory of the electronic device.

[0117] In this embodiment, the functions of each module / unit are as follows:

[0118] The keyword extraction module is used to receive the user's disease search keywords, perform semantic matching and filtering on all candidate data in a preset candidate dataset based on the disease search keywords to obtain one or more initial candidate data; divide the disease search keywords into disease name components to obtain one or more disease name component keywords and a first name component category corresponding to each disease name component keyword; and extract keywords from the initial candidate data based on the first name component category to obtain candidate keywords of the initial candidate data and a second name component category corresponding to each candidate keyword.

[0119] The similarity classification calculation module is used to calculate the word similarity between disease name component keywords and candidate keywords corresponding to the same name component category based on the first name component category and the second name component category, so as to obtain the similarity score of each first name component category corresponding to the initial candidate data; and to perform weighted calculation based on the preset weight threshold corresponding to each first name component category and the similarity score of each first name component category corresponding to the initial candidate data to obtain the target similarity score of the initial candidate data.

[0120] The disease search ranking module is used to rank all the initial candidate data based on the target similarity score, obtain the search ranking result, and send the search ranking result to the user's preset terminal device.

[0121] In detail, each module in the disease search and sorting device 100 described in this embodiment of the invention employs the same methods as described above. Figure 1 The disease search and ranking method described herein uses the same technical means and can produce the same technical effect, so it will not be elaborated here.

[0122] like Figure 3 The diagram shown is a structural schematic of the electronic device that implements the disease search and ranking method of the present invention.

[0123] The electronic device may include a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may also include a computer program, such as a disease search and ranking program, stored in the memory 11 and capable of running on the processor 10.

[0124] The memory 11 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of an electronic device, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device, such as a plug-in portable hard drive, smart media card (SMC), secure digital card (SD), flash card, etc. Furthermore, the memory 11 can include both internal and external storage units of the electronic device. The memory 11 can be used not only to store application software and various types of data installed on the electronic device, such as the code of a disease search and ranking program, but also to temporarily store data that has been output or will be output.

[0125] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules (such as disease search and ranking programs) stored in the memory 11, and calls data stored in the memory 11 to perform various functions of the electronic device and process data.

[0126] The communication bus 12 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. The communication bus 12 is configured to enable communication between the memory 11 and at least one processor 10, etc. For ease of illustration, only one thick line is used in the figure, but this does not indicate that there is only one bus or one type of bus.

[0127] Figure 3 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 3 The structure shown does not constitute a limitation on the electronic device and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0128] For example, although not shown, the electronic device may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault classification circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0129] Optionally, the communication interface 13 may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the electronic device and other electronic devices.

[0130] Optionally, the communication interface 13 may further include a user interface, which may be a display, an input unit (such as a keyboard), or, optionally, a standard wired or wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device and to display a visual user interface.

[0131] It should be understood that the embodiments described are for illustrative purposes only and are not limited to this structure in the scope of the patent application.

[0132] The disease search and ranking program stored in the memory 11 of the electronic device is a combination of multiple computer programs, which, when run in the processor 10, can achieve the following:

[0133] Receive the user's disease search keywords, and perform semantic matching and filtering on all candidate data in the preset candidate dataset based on the disease search keywords to obtain one or more initial candidate data;

[0134] The disease search keywords are divided into disease name components to obtain one or more disease name component keywords and a first name component category corresponding to each disease name component keyword;

[0135] Based on the first name composition category, keywords are extracted from the initial candidate data to obtain candidate keywords of the initial candidate data and a second name composition category corresponding to each candidate keyword;

[0136] Based on the first name composition category and the second name composition category, the word similarity between the disease name composition keywords and candidate keywords corresponding to the same name composition category is calculated to obtain the similarity score of each first name composition category corresponding to the initial candidate data;

[0137] The target similarity score of the initial candidate data is obtained by weighting the preset weight threshold corresponding to each of the first name component categories and the similarity score of each of the first name component categories corresponding to the initial candidate data.

[0138] All the initial candidate data are sorted based on the target similarity score to obtain the search ranking result, and the search ranking result is sent to the user's preset terminal device.

[0139] Specifically, the processor 10's implementation method of the above-mentioned computer program can be found in [reference needed]. Figure 1 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0140] Furthermore, if the modules / units integrated into the electronic device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable medium can be non-volatile or volatile. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0141] Embodiments of the present invention may also provide a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following:

[0142] Receive the user's disease search keywords, and perform semantic matching and filtering on all candidate data in the preset candidate dataset based on the disease search keywords to obtain one or more initial candidate data;

[0143] The disease search keywords are divided into disease name components to obtain one or more disease name component keywords and a first name component category corresponding to each disease name component keyword;

[0144] Based on the first name composition category, keywords are extracted from the initial candidate data to obtain candidate keywords of the initial candidate data and a second name composition category corresponding to each candidate keyword;

[0145] Based on the first name composition category and the second name composition category, the word similarity between the disease name composition keywords and candidate keywords corresponding to the same name composition category is calculated to obtain the similarity score of each first name composition category corresponding to the initial candidate data;

[0146] The target similarity score of the initial candidate data is obtained by weighting the preset weight threshold corresponding to each of the first name component categories and the similarity score of each of the first name component categories corresponding to the initial candidate data.

[0147] All the initial candidate data are sorted based on the target similarity score to obtain the search ranking result, and the search ranking result is sent to the user's preset terminal device.

[0148] Furthermore, the computer's usable storage medium may mainly include a program storage area and a data storage area, wherein the program storage area may store the operating system, applications required for at least one function, etc.; and the data storage area may store data created based on the use of blockchain nodes, etc.

[0149] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0150] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0151] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0152] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0153] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0154] Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within the invention. No appended diagram markings in the claims should be construed as limiting the scope of the claims.

[0155] The blockchain referred to in this invention is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying blockchain platform, a platform product service layer, and an application service layer.

[0156] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in a system claim may also be implemented by a single unit or device through software or hardware. The term "second class" is used to indicate names and does not indicate any specific order.

[0157] 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 it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A disease search and ranking method, characterized in that, The method includes: Receive the user's disease search keywords, and perform semantic matching and filtering on all candidate data in the preset candidate dataset based on the disease search keywords to obtain one or more initial candidate data; The disease search keywords are divided into disease name components to obtain one or more disease name component keywords and a first name component category corresponding to each disease name component keyword; Based on the first name composition category, keywords are extracted from the initial candidate data to obtain candidate keywords of the initial candidate data and a second name composition category corresponding to each candidate keyword; Based on the first name composition category and the second name composition category, the word similarity between the disease name composition keywords and candidate keywords corresponding to the same name composition category is calculated to obtain the similarity score of each first name composition category corresponding to the initial candidate data; The target similarity score of the initial candidate data is obtained by weighting the preset weight threshold corresponding to each of the first name component categories and the similarity score of each of the first name component categories corresponding to the initial candidate data. All the initial candidate data are sorted based on the target similarity score to obtain the search ranking result, and the search ranking result is sent to the user's preset terminal device; The step of calculating the word similarity between disease name component keywords and candidate keywords corresponding to the same name component category based on the first name component category and the second name component category, and obtaining the similarity score for each first name component category corresponding to the initial candidate data, includes: Summarize all the categories that make up the first name to obtain the set of categories that make up the first name; By summing up all the candidate keywords corresponding to the second name composition categories in the initial candidate data, a set of second name composition categories corresponding to the initial candidate data is obtained. Calculate the difference between the second name composition category set and the first name composition category set to obtain the third name composition category set; Obtain the preset initial similarity score corresponding to each of the first name categories; The preset initial similarity score corresponding to the first name composition category in the third name composition category set is determined as the similarity score of the first name composition category; Calculate the word similarity between the disease name composition keywords corresponding to the first name composition category in the second name composition category set and the candidate keywords corresponding to the same name composition category in the initial candidate data, and obtain the similarity score of the first name composition category.

2. The disease search and ranking method as described in claim 1, characterized in that, The step involves semantically matching and filtering all candidate data in a preset candidate dataset based on the disease search keywords to obtain one or more initial candidate data sets, including: Convert the disease search keywords into search vectors; Obtain the candidate vector for each of the candidate data; Calculate the vector similarity between each candidate vector and the search vector to obtain the semantic matching degree of each candidate vector; Based on the semantic matching degree, all candidate data in the candidate dataset are filtered to obtain the initial candidate data.

3. The disease search and ranking method as described in claim 2, characterized in that, The initial candidate data is obtained by filtering all candidate data in the candidate dataset based on the semantic matching degree, including: The semantic matching degree that is greater than the preset semantic matching threshold is used to determine the target semantic matching degree; The candidate vector corresponding to the target semantic matching degree is determined as the target candidate vector; The initial candidate data is obtained by filtering the candidate data corresponding to the target candidate vector in the candidate dataset.

4. The disease search and ranking method as described in claim 1, characterized in that, The step of dividing the disease search keywords into disease name components to obtain one or more disease name component keywords and a first name component category corresponding to each disease name component keyword includes: Obtain a name dictionary tree that categorizes different preset names; The disease search keywords are segmented to obtain one or more segmented words; The segmented words existing in any of the aforementioned name dictionary trees are determined as keywords to form the name of the disease; The preset name composition category corresponding to the name dictionary tree containing the disease name composition keywords is determined as the first name composition category corresponding to the disease name composition keywords.

5. The disease search and ranking method as described in claim 1, characterized in that, The step of extracting keywords from the initial candidate data based on the first name composition category to obtain candidate keywords of the initial candidate data and a second name composition category corresponding to each candidate keyword includes: The candidate data is segmented into words to obtain one or more candidate words; Candidate words that exist in the name dictionary of any of the first name composition categories are identified as candidate keywords; The first name composition category corresponding to the name dictionary tree containing the candidate keyword is determined as the second name composition category corresponding to the candidate keyword.

6. The disease search and ranking method according to any one of claims 1 to 5, characterized in that, The step of sorting all the initial candidate data based on the target similarity score to obtain a search ranking result, and sending the search ranking result to the user's preset terminal device, includes: Sort all the initial candidate data in descending order of their corresponding target similarity scores to obtain the search ranking results; The search ranking results are sent to the user's preset terminal device.

7. A disease search and ranking apparatus for implementing the disease search and ranking method as described in any one of claims 1 to 6, characterized in that, The device includes: The keyword extraction module is used to receive the user's disease search keywords, perform semantic matching and filtering on all candidate data in a preset candidate dataset based on the disease search keywords to obtain one or more initial candidate data; divide the disease search keywords into disease name components to obtain one or more disease name component keywords and a first name component category corresponding to each disease name component keyword; and extract keywords from the initial candidate data based on the first name component category to obtain candidate keywords of the initial candidate data and a second name component category corresponding to each candidate keyword. The similarity classification calculation module is used to calculate the word similarity between disease name component keywords and candidate keywords corresponding to the same name component category based on the first name component category and the second name component category, so as to obtain the similarity score of each first name component category corresponding to the initial candidate data; and to perform weighted calculation based on the preset weight threshold corresponding to each first name component category and the similarity score of each first name component category corresponding to the initial candidate data to obtain the target similarity score of the initial candidate data. The disease search ranking module is used to rank all the initial candidate data based on the target similarity score, obtain the search ranking result, and send the search ranking result to the user's preset terminal device.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and, A memory that is communicatively connected to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the disease search and ranking method as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the disease search and ranking method as described in any one of claims 1 to 6.

Images