Medical data search method and device, electronic equipment and computer readable medium

Abstract

The invention discloses a medical data search method and device, electronic equipment and a computer readable medium, and relates to the technical field of computers.The specific implementation mode comprises the steps that a medical data search request is received, a corresponding search word is obtained, and the search word is split to obtain vocabularies; determining part-of-speech classification corresponding to each vocabulary, and determining synonyms and weights of each vocabulary according to the part-of-speech classification; determining a target service based on each vocabulary, synonym and weight; obtaining current inquiry data, and searching related dynamic real-time data based on the current inquiry data and the target service; and searching based on the dynamic real-time data, the target service, each vocabulary, synonym and weight to obtain search result data. The efficiency and the accuracy of data search are improved, so that the efficiency and the accuracy of data search of doctors in a scene that an internet hospital platform serves patients can be improved.

Description

Technical Field

[0001] The present application relates to the field of Internet medical technology, and in particular to a medical data search method, device, electronic device and computer-readable medium. Background Art

[0002] At present, the Internet hospital platform mainly uses the sale of online and offline medical services as the main means of increasing the gross merchandise volume (GMV). The main buyers are patients. The medical industry is different from the e-commerce field. Patients do not have professional knowledge and it is difficult to choose suitable services. Therefore, 80% of the scenarios rely on patients' compliance with doctors to make services a single. At first, the platform only had some basic services such as pictures, texts, telephones, and videos, with a small variety. Doctors could also easily recommend and guide patients. However, as the overall ecology becomes richer, there are currently more than 10 major categories of services on the platform, and there are more than 10,000 service items in terms of detailed content. This number has far exceeded the cognitive load of a doctor, and it is impossible for a doctor to remember so many services. As a result, doctors are inefficient and prone to errors when serving patients on the Internet hospital platform. Summary of the invention

[0003] In view of this, the embodiments of the present application provide a medical data search method, device, electronic device and computer-readable medium, which can solve the problems of low work efficiency and easy errors of existing doctors when serving patients on the Internet hospital platform.

[0004] To achieve the above-mentioned purpose, according to one aspect of an embodiment of the present application, a medical data search method is provided, including: receiving a medical data search request, obtaining corresponding search terms, splitting the search terms to obtain individual words; determining the part-of-speech classification corresponding to each word, and determining the synonyms and weights of each word based on the part-of-speech classification; determining a target service based on each word, synonyms and weights; obtaining current consultation data, and searching for related dynamic real-time data based on the current consultation data and the target service; searching based on the dynamic real-time data, the target service, each word, synonyms and weights to obtain search result data.

[0005] Optionally, determining the synonyms of each word includes: performing synonym conversion on the words corresponding to the part-of-speech classification corresponding to the supply range to obtain corresponding synonyms.

[0006] Optionally, determining the target service includes: determining one or more services corresponding to the vocabulary and synonyms corresponding to the maximum weight as the target service.

[0007] Optionally, searching for relevant dynamic real-time data based on current consultation data and target service includes: obtaining relevant historical consultation data based on current consultation data, and obtaining coordinate positioning from current consultation data; searching for dynamic real-time data related to the target service based on coordinate positioning and historical consultation data.

[0008] Optionally, the search term is split to obtain individual words, including: identifying meaningless words in the search term, removing meaningless words from the search term to obtain pre-processed search terms; splitting the pre-processed search terms to obtain individual words.

[0009] Optionally, a search is performed based on dynamic real-time data, target services, various words, synonyms and weights to obtain search result data, including: using dynamic real-time data, target services, various words, synonyms and weights as parameter values ​​of the search algorithm, and executing the assigned search algorithm to obtain search result data.

[0010] Optionally, the method further includes: when the executed search statement recall is empty, generating a search record based on the search term, dynamic real-time data, target service, various words, synonyms and weights; adding the search record to a no-service supply record pool.

[0011] In addition, the present application also provides a medical data search device, including: a receiving unit, configured to receive a medical data search request, obtain a corresponding search term, and split the search term to obtain individual words; a classification unit, configured to determine the part-of-speech classification corresponding to each word, and determine the synonyms and weights of each word based on the part-of-speech classification; a target service determination unit, configured to determine the target service based on each word, synonyms and weights; a first search unit, configured to obtain current consultation data, and search for related dynamic real-time data based on the current consultation data and the target service; a second search unit, configured to search based on the dynamic real-time data, the target service, each word, synonyms and weights to obtain search result data.

[0012] Optionally, the classification unit is further configured to: perform synonym conversion on the vocabulary corresponding to the part-of-speech classification corresponding to the supply range to obtain corresponding synonyms.

[0013] Optionally, the target service determination unit is further configured to: determine one or more services corresponding to the vocabulary and synonyms corresponding to the maximum weight as the target service.

[0014] Optionally, the first search unit is further configured to: obtain relevant historical consultation data based on current consultation data, and obtain coordinate positioning from the current consultation data; and search for dynamic real-time data related to the target service based on the coordinate positioning and historical consultation data.

[0015] Optionally, the receiving unit is further configured to: identify meaningless words in the search terms, remove the meaningless words from the search terms to obtain pre-processed search terms; and split the pre-processed search terms to obtain individual words.

[0016] Optionally, the second search unit is further configured to: use the dynamic real-time data, target service, various words, synonyms and weights as parameter values ​​of the search algorithm, and execute the assigned search algorithm to obtain search result data.

[0017] Optionally, the medical data search device also includes a search record adding unit, which is configured to: when the executed search statement recall is empty, generate a search record based on the search term, dynamic real-time data, target service, various words, synonyms and weights; add the search record to the no-service supply record pool.

[0018] In addition, the present application also provides a medical data search electronic device, including: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by one or more processors, the one or more processors implement the medical data search method as described above.

[0019] In addition, the present application also provides a computer-readable medium on which a computer program is stored, and when the program is executed by a processor, the medical data search method as described above is implemented.

[0020] To achieve the above objective, according to another aspect of the embodiments of the present application, a computer program product is provided.

[0021] A computer program product according to an embodiment of the present application includes a computer program, which, when executed by a processor, implements the medical data search method provided in the embodiment of the present application.

[0022] One embodiment of the above invention has the following advantages or beneficial effects: the present application receives a medical data search request, obtains the corresponding search terms, splits the search terms to obtain individual words; determines the part-of-speech classification corresponding to each word, and determines the synonyms and weights of each word according to the part-of-speech classification; determines the target service based on each word, synonym and weight; obtains the current consultation data, searches for related dynamic real-time data based on the current consultation data and the target service; searches based on the dynamic real-time data, the target service, each word, synonym and weight to obtain the search result data. The efficiency and accuracy of data search are improved, thereby improving the efficiency and accuracy of data search by doctors in the scenario of Internet hospital platform serving patients.

[0023] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The accompanying drawings are used to better understand the present application and do not constitute an improper limitation on the present application.

[0025] Figure 1 is a schematic diagram of the main process of a medical data search method according to an embodiment of the present application;

[0026] Figure 2 is a schematic diagram of the main process of a medical data search method according to an embodiment of the present application;

[0027] Figure 3 is a schematic diagram of the overall process of a medical data search method according to an embodiment of the present application;

[0028] Figure 4 is a service union diagram of a medical data search method according to an embodiment of the present application;

[0029] Figure 5 It is a schematic diagram of part-of-speech analysis and determining the weight of a word in a search sentence according to a medical data search method according to an embodiment of the present application;

[0030] Figure 6 It is a schematic diagram of a four-level link query and dynamic real-time data implantation process of a medical data search method according to an embodiment of the present application;

[0031] Figure 7 is a schematic diagram of main units of a medical data search device according to an embodiment of the present application;

[0032] Figure 8 is an exemplary system architecture diagram to which the embodiments of the present application can be applied;

[0033] Fig. 9 It is a structural diagram of a computer system of a terminal device or server suitable for implementing an embodiment of the present application. DETAILED DESCRIPTION

[0034] The following is an explanation of the exemplary embodiments of the present application in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding, which should be considered as merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, the description of known functions and structures is omitted in the following description. It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of the present application are in compliance with the relevant provisions of national laws and regulations. It should be noted that in the embodiments of the present application, certain software, components, models, and other existing solutions in the industry may be mentioned, which should be considered as exemplary, and their purpose is only to illustrate the feasibility of the implementation of the technical solution of the present application, but it does not mean that the applicant has or must have used the solution. In the technical solution of the present application, the collection, collection, update, analysis, processing, use, transmission, storage, etc. of the user personal information involved are in compliance with the provisions of relevant laws and regulations, are used for legal and reasonable purposes, and do not violate public order and good customs, are not shared, leaked or sold outside these legal uses, and are subject to supervision and management by regulatory authorities. Take necessary measures to prevent illegal access to such user personal information data, maintain the security of user personal information, network security and national security, ensure that persons who have access to personal information data comply with relevant laws and regulations, and ensure the security of user personal information. Once such user personal information data is no longer needed, the risk should be minimized by limiting or even prohibiting data collection and / or deleting data.

[0035] When used, including in certain related applications, user privacy is protected by de-identifying data, such as by removing specific identifiers when used, controlling the amount or specificity of data stored, controlling how data is stored, and / or other methods of de-identification.

[0036] Figure 1 is a schematic diagram of the main process of the medical data search method according to an embodiment of the present application, such as Figure 1 As shown, the medical data search method mainly includes the following steps S101 to S105.

[0037] Step S101, receiving a medical data search request, obtaining a corresponding search term, and splitting the search term to obtain individual words.

[0038] In this embodiment, the execution subject of the medical data search method (for example, a server) can receive a medical data search request through a wired connection or a wireless connection. The search words in the medical data search request are obtained, such as a good blood transplant nearby. The search words are split based on the part of speech to obtain individual words, such as nearby, good, and blood transplant.

[0039] Step S102, determining the part-of-speech classification corresponding to each word, and determining the synonyms and weights of each word according to the part-of-speech classification.

[0040] For example, the individual words obtained by splitting the search term may be: nearby, good, blood transplantation, and the part-of-speech classification corresponding to each word may be: supply distance, supply quality, and supply range.

[0041] Specifically, determining the synonyms of each word includes: performing synonym conversion on the words corresponding to the part-of-speech classification corresponding to the supply range to obtain corresponding synonyms.

[0042] The supply scope is the part of speech corresponding to the project. It is necessary to perform synonym conversion to improve the accuracy of data search. The words corresponding to the supply scope in each word obtained by splitting the search term are converted into synonyms to obtain synonyms of the words corresponding to the supply scope. For example, synonym conversion is performed on blood transplantation to obtain synonyms such as blood transplantation, blood transfusion, and blood transplantation surgery. Different parts of speech can correspond to different weights. After obtaining the part of speech classification of each word, the execution subject can determine the weight corresponding to each word based on the weight ranking table. For example, in the weight ranking table, the weight corresponding to the supply distance is 0.5, the weight corresponding to the supply quality is 0.3, and the weight corresponding to the supply scope is 0.55.

[0043] Step S103, determining the target service based on each vocabulary, synonym and weight.

[0044] Specifically, determining the target service includes: determining one or more services corresponding to the vocabulary and synonyms corresponding to the largest weight as the target service.

[0045] The target service is one or more available services corresponding to the vocabulary and synonyms corresponding to the largest weight. For example, the maximum weight may be 0.55, and the maximum weight corresponds to the supply range. The vocabulary and synonyms corresponding to the supply range may be blood transplantation, blood transplantation, blood transfusion, and blood transplantation surgery. The corresponding downgradable route is offline hospital-follow-up plan, and the corresponding target service may be offline hospital and follow-up plan. It is necessary to find available services from offline hospitals (high priority) or follow-up plans (low priority, only when no suitable supply services can be found from offline hospitals will the follow-up plan be searched for services).

[0046] Step S104, obtaining current consultation data, and searching for relevant dynamic real-time data based on the current consultation data and the target service.

[0047] The current consultation data may be "I am 22 years old and came to YY County from XX. I want to make an appointment with xx department to consult xxx problem. My symptom is xxxx and my patient ID is yy". The execution entity may determine the patient's current coordinate location based on location-based services (LBS) based on "YY County" in the current consultation data, and search for hospitals within a preset range near the current coordinate location. The search priority may be tertiary hospitals>secondary hospitals>community hospitals, and the execution entity may search for the patient's historical transaction data based on the "patient ID yy". For example, if a record of "the patient purchased a private doctor service worth over 10,000 yuan online in aa" is found, "the patient's current coordinate location" and "the patient purchased a private doctor service worth over 10,000 yuan online in aa" may be embedded into the search conditions as dynamic real-time data to make the search results more accurate.

[0048] Step S105, searching based on dynamic real-time data, target services, various words, synonyms and weights to obtain search result data.

[0049] Specifically, a search is performed based on dynamic real-time data, target services, various words, synonyms and weights to obtain search result data, including: using dynamic real-time data, target services, various words, synonyms and weights as parameter values ​​of the search algorithm, executing the assigned search algorithm to obtain search result data from a database of the field corresponding to the search term.

[0050] Specifically, the method also includes: when the executed search statement recall is empty, generating a search record based on the search term, dynamic real-time data, target service, various words, synonyms and weights; adding the search record to the no-service supply record pool.

[0051] When a service cannot be found, the corresponding search record is added to the no-service pool. Although it cannot be found, if a large number of doctors search frequently, it actually means that this service may be very common and it is necessary to expand the business. Therefore, it is recorded first and wait for BD personnel to make further expansion.

[0052] The embodiment of the present application provides doctors with search results that match as much as possible when they search for services. First, the services are united to facilitate their positioning. Secondly, a four-level search link is executed to ensure the unification of platform-level logic. At the same time, weighted linear weighting and dynamic real-time information intervention are adopted to take into account the individual factors of doctors and patients themselves.

[0053] In this embodiment, by receiving a medical data search request, the corresponding search term is obtained, and the search term is split to obtain each word; the part-of-speech classification corresponding to each word is determined, and based on the part-of-speech classification, the synonyms and weights of each word are determined; based on each word, synonyms and weights, the target service is determined; the current consultation data is obtained, and relevant dynamic real-time data is searched based on the current consultation data and the target service; based on the dynamic real-time data, target service, each word, synonyms and weights, a search is performed to obtain search result data. This improves the efficiency and accuracy of data search, thereby improving the efficiency and accuracy of doctors' data search in the scenario of serving patients on the Internet hospital platform.

[0054] Figure 2 It is a schematic diagram of the main process of a medical data search method according to an embodiment of the present application, as Figure 2 shown, the medical data search method mainly includes the following steps S201-step S206.

[0055] Step S201, receive a medical data search request, obtain the corresponding search term, and split the search term to obtain each word.

[0056] Specifically, splitting the search term to obtain each word includes: identifying words with no search meaning in the search term, removing the words with no search meaning from the search term to obtain a preprocessed search term; splitting the preprocessed search term to obtain each word.

[0057] Identify words with no search meaning in the search term, such as "de", "le", "dian", etc., remove the words with no search meaning "de", "le", "dian", etc. from the search term to obtain a preprocessed search term; split the preprocessed search term (such as near good blood transplantation) to obtain each word (such as, near, good, blood transplantation).

[0058] Step S202, determine the part-of-speech classification corresponding to each word, and based on the part-of-speech classification, determine the synonyms and weights of each word.

[0059] Refer to the supply classification table to determine the part-of-speech classification of each obtained word. For example, near (supply distance), good (supply quality), blood transplantation (supply scope).

[0060] Different parts of speech can correspond to different weights. After the execution entity obtains the part-of-speech classification of each word, it can determine the weight corresponding to each word based on the weight ranking table. By way of example, in the weight ranking table, the weight corresponding to supply distance is 0.5, the weight corresponding to supply quality is 0.3, and the weight corresponding to supply scope is 0.55.

[0061] Step S203, based on each word, synonyms and weights, determine the target service.

[0062] The execution subject can determine the corresponding degradable route based on the vocabulary corresponding to the part of speech corresponding to the weight greater than the preset threshold, and then determine the target service according to one or more degradable routes, thereby improving the comprehensiveness and accuracy of data search.

[0063] For example, the vocabulary corresponding to the part of speech corresponding to the weight greater than the preset organization can be used as the first route node in the downgradable route, such as medicine, and the corresponding downgradable route can include: medicine-test form-scale-patient education article, medicine-test form-follow-up plan-patient education article, etc.; for another example, if the first route node is a test form, the corresponding downgradable route can include: test form-scale-patient education article; for another example, if the first route node is a consultation service, the corresponding downgradable route can include: consultation service-follow-up plan-patient education article; for another example, if the first route node is an offline hospital, the corresponding downgradable route can include: offline hospital-consultation service-follow-up plan-patient education article. According to the determined downgradable route, each route node in the downgradable route can be used as a target service to improve the comprehensiveness and accuracy of data search.

[0064] Step S204, obtaining current medical consultation data, obtaining relevant historical medical consultation data based on the current medical consultation data, and obtaining coordinate positioning from the current medical consultation data.

[0065] The current consultation data may include the current location data provided by the patient, the patient's ID data, etc. The execution entity may determine the patient's current coordinate location based on the current location data provided by the patient.

[0066] Step S205, searching for dynamic real-time data related to the target service based on the coordinate positioning and the historical consultation data.

[0067] The executing entity can use coordinate positioning to find hospitals that meet the patient's requirements within a preset range nearby, and can query the patient's historical order transaction data based on the patient's ID data, so as to analyze the price of the follow-up plan that the patient can afford, and embed the hospitals that meet the patient's requirements and the price of the follow-up plan that the patient can afford as dynamic real-time data into the search conditions to make the data search more accurate.

[0068] Step S206, searching based on dynamic real-time data, target service, various words, synonyms and weights to obtain search result data.

[0069] The execution entity can call the search engine to search from the database of the field corresponding to the search term based on dynamic real-time data, target services, various words, synonyms and weights to accurately obtain search result data.

[0070] In the embodiments of the present application, search: refers to the process of finding specific content in a large amount of information, data or resources through certain methods or techniques. In the fields of computer science and information retrieval, search generally refers to the use of search engines or database query systems to find user-specified information. Supply: Service refers to the process of providing services, including the resources, facilities and manpower required to provide services. In the present invention, it specifically refers to medical services. Intent analysis: Do you want to know about intent analysis in natural language processing? Intent analysis refers to the process of identifying the intention or purpose of a user in text or speech. Common applications include chatbots, virtual assistants, and customer service. Dynamic real-time information: Dynamic real-time information refers to data or information that is updated in real time, usually referring to content that is acquired and displayed in real time. In the embodiments of the present application, it specifically refers to information such as the patient's address and age.

[0071] Figure 3 FIG. 1 is a schematic diagram of the overall process of a medical data search method according to an embodiment of the present application. Figure 3As shown, obtain a search term, such as "<Good blood transplantation nearby>", and conduct legal compliance inspection on the search term through the AI risk control system "<Good blood transplantation nearby>". Perform word discarding on stop words, that is, delete unimportant auxiliary words in the search term, such as "de" (的), "le" (了), etc. Here, the original search term is "<Good blood transplantation nearby>", and in this step, the two stop words "dian" (点) and "de" (的) are discarded. Then, conduct part-of-speech analysis and synonym conversion. For example, part-of-speech analysis: "<Nearby (distance) Good (quality) Blood transplantation (project)>", and synonym conversion: "<Nearby Good (Blood transplantation|Blood transfusion|Blood transplantation surgery)>". Then, conduct intention analysis. For example, through manual marking by service providers, such as through a supply classification table (unionization of all supply services), and through the configuration center for weight splitting rule sorting, obtain the intention recognition result after intention analysis: "<Offline cooperative hospital>", and the weight splitting result: "<Nearby 0.5 Good 0.3 Blood transplantation 0.55>". Based on the intention recognition result, weight splitting result, and synonym conversion result, conduct a four-level link query "<Nearby (distance) Good (quality) Blood transplantation (hospital)>". During the query execution process, inject dynamic real-time information (such as: 1. The patient is in XX; 2. The patient has purchased a private doctor worth 10,000 yuan online and has a certain economic strength) captured from the business system in real time as search conditions for the search. If the search result shows no supply service, perform a secondary recall "<Nearby (distance) Good (quality) Blood transplantation (Follow-up service)>" to obtain recommended results, such as: 1) Follow-up at a price of 1,190 yuan; 2) Follow-up at a price of 658 yuan. If no supply service is found after the secondary recall, add the corresponding search record to the non-service supply record pool, and it requires offline expansion by Business Development (BD), for example, mark a certain hospital in XX.

[0072] The embodiment of this application provides a complete technical-level search process for the scenario of doctor search services, mainly including a preprocessing link, stop word processing, followed by intention analysis and weight splitting links, that is, conduct part-of-speech analysis and decomposition on the search Query and then assign weights. Next is the most core four-level link query link. In this link, inject dynamic real-time information, such as location, quality, etc., to recall more compliant search results. In addition, when the recall is empty, perform automated recording to facilitate subsequent BD expansion.

[0073] For example, the medical data search method of the embodiment of this application includes the following 1)-6):

[0074] 1) Preprocessing link:

[0075] Detect risk words for the search term, including sensitive word scanning. During important meetings, enhanced supervision is required to ensure that the entire vocabulary is legal and compliant. After passing the legal compliance check, stop words will be processed for the search term. Words such as "de", "hen", "te" that have little significance for the search will be removed to improve the search accuracy. For example, if the original search term is <nearby good blood transplantation>, after removing the stop words, it becomes <nearby blood transplantation>.

[0076] 2) Part-of-speech analysis & synonym conversion:

[0077] In this step, the search term is split and synonyms are converted. <Nearby> is marked as distance, <good> is marked as quality, and <blood transplantation> is marked as a project. These markings are for preparing the weight splitting in the next step (different markings correspond to different weights). At the same time, some synonyms will also be converted. For example, blood transplantation is equivalent to blood transfusion, blood transfusion operation, etc., and they will also be used as search terms for searching. These part-of-speech analyses and synonym conversions also rely on the pre-stored dictionary.

[0078] 3) Intention analysis & weight splitting:

[0079] In the intention analysis step, when doctors search, since they are searching for services that can be provided in multiple dimensions, it is difficult for the execution entity to accurately understand the doctors' intentions and it is easy to misunderstand. For example, when a doctor enters "anxiety", it is impossible to accurately determine whether to help the patient contact an offline psychological counseling agency or to recommend a scale to test the patient's psychological anxiety. Another example is that when a doctor enters drug A, it is impossible to accurately determine whether the doctor wants to prescribe such a drug or to recommend a relevant patient education article for the patient. Since the online consultation time is short, doctors cannot spend a lot of time searching repeatedly, and even some doctors only look at the first page and will not turn the page. Therefore, it is very necessary to improve the accuracy of intention recognition in this scenario. However, at the same time, the expansion of the business also needs to be considered, that is, how to degrade when no suitable supply is found to assist the business development. Three steps are provided for intention recognition. First, classify and label the existing available services. Second, classify and analyze the doctors' search terms. Finally, rank them in order. The following is a specific description:

[0080] First, service unionization: Unionize all the available services, that is, classify all the available services as a whole to form a complete and detailed classification system, which can help improve the overall retrieval accuracy. This classification process is a logical classification formed by business and product personnel sorting out the past search logs and the existing services and continuously maintaining them. Generally speaking, it can be divided into more than 10 categories and more than 10,000 sub-items. Figure 4This is a simplified general classification diagram.

[0081] Figure 4 FIG. 1 is a schematic diagram of a service unionization of a medical data search method according to an embodiment of the present application. Figure 4 As shown, the supply scope is Unionized, and the results are: medicines: A, B, C; follow-up plan: rehabilitation treatment, doctor's rounds, medication reminders; test orders: blood transplantation, urine test, blood lipid test; scale: questionnaire, test paper, chronic disease rehabilitation review (CRF); consultation services: private doctors, expert teams, convenient follow-up visits; patient education articles: fetal preservation, pregnancy preparation, babies; offline hospitals: blood transplantation, psychiatric treatment, premarital examination.

[0082] Secondly, the analysis and classification of search terms: the overall process includes two parts: part of speech analysis and determining the importance of the word in the search sentence. The specific process is as follows: Figure 5 shown.

[0083] Figure 5 It is a schematic diagram of the weight of the word in the search sentence according to the medical data search method of an embodiment of the present application. Regarding the part-of-speech classification, all high-frequency words are classified into parts of speech to obtain a part-of-speech classification table. In the part-of-speech classification table, there are currently 5 categories, including supply range (blood transplantation, cold, blood test and other words), supply timeliness (hours, fast, immediately, urgent and other words), supply distance (near, far, hospital, online, downstairs and other words), supply quality (three-class, good, good reviews, high-quality, assured and other words), supply personalization (children, pregnancy, coupons and other words), and a complete vocabulary is configured in advance under its category. For example, words such as blood transplantation, cold, blood test actually correspond to the supply range, and the supply range is the 10+ categories mentioned above, that is, the range is unionized, and the vocabulary corresponding to the timeliness includes words such as hours, fast, and immediately. In this way, different words are defined at the business level to have different parts of speech. After splitting the original search words, the corresponding part-of-speech table can be found, thereby giving the words a given nature.

[0084] Finally, weight splitting and sorting: It needs to be based on a weight ranking table, which includes the following: supply range requirement 0.55, supply timeliness requirement 0.53, supply distance requirement 0.5, supply quality requirement 0.3, and supply personalization requirement 0.28, among which 0.55, 0.53, 0.5, 0.3, and 0.28 are all weights. For each vocabulary, the weight will be assigned and sorted in advance, that is, after a word is assigned to a part of speech, different parts of speech have different weights in the same sentence, that is, different priorities, which will lay the foundation for the subsequent real search process. For example, the supply range is usually the highest priority, because the project must be symptomatic first to ensure the patient's treatment effect, followed by timeliness, distance, quality and other information. The process of part-of-speech analysis and weight splitting of search terms can be as follows: Search term: <good blood transplantation nearby>, the part-of-speech analysis results based on the part-of-speech classification table are: <nearby> (distance requirement), <good> (quality requirement), <blood transplantation> (range requirement), based on the part-of-speech analysis results, they are sorted according to the weight ranking table, and in sequence, we get <blood transplantation> (range requirement) (hospital> follow-up) - <nearby> (distance requirement) (3KM>5KM>10KM) - <good> (quality requirement) (3000>2000>1000>500).

[0085] 4) Four-level link query & dynamic real-time data implantation: In order to balance the accuracy of search and business expansion, the embodiment of the present application adopts technical means such as four-level link query, dynamic real-time information implantation, and no-supply service business expansion. Here we introduce the four-level link query and dynamic real-time information implantation. Figure 6 shown.

[0086] Figure 6 FIG. 1 is a schematic diagram of a four-level link query and dynamic real-time data implantation process of a medical data search method according to an embodiment of the present application. Figure 6 As shown, the first-level supply scope: medicines, follow-up plans, test orders, scales, consultation services, patient education articles, offline hospitals; the second-level supply scope: test orders, follow-up plans, consultation services; the third-level supply scope: scales, follow-up plans; the fourth-level supply scope: patient education articles. Downgraded branches (i.e. downgraded routes) can include: offline hospitals-consultation services-follow-up plans-patient education articles. In the process of executing offline hospital searches, dynamic real-time data implantation 1: For example, the coordinate positioning of the patient's LBS (XX) (hospital: tertiary hospital>secondary hospital>community hospital). In the process of executing follow-up plan searches, dynamic real-time data implantation 2: patients have strong consumption power and require higher-quality supplies (follow-up: 1,190 yuan>658 yuan).

[0087] Downgrade branches (i.e. downgrade routes) may also include: drugs-test forms-scales-patient education articles, drugs-test forms-follow-up plan-patient education articles, test forms-scales-patient education articles, and consultation services-follow-up plan-patient education articles.

[0088] For all available services, we sort out downgradable routes. Downgrading is to deal with the situation that when a supply range is queried and no recall results are found, we can downgrade in order. Generally, we recommend some service categories first. Service categories can usually directly bring growth and GMV. Finally, patient education articles are used as a backup. As a popular science article, although patient education articles do not have much economic benefits, they can also be used as a means of publicity. In this scenario, for example, offline hospital services are the highest through cooperation with hospitals. If there is no corresponding cooperative hospital, it can be downgraded to consultation services. Usually, consultation services include private doctors, expert teams, etc., with services of about 1,000 yuan. If there is no such service, it can be downgraded to follow-up plans, which can provide tens of yuan of income. Finally, patient education articles are used as a backup. Similarly, for other branches, downgrading from test orders to scales and from scales to patient education articles are the same idea. In this scenario, the "blood transplant" service is needed, and the "blood transplant" service corresponds to the two supply services of offline hospitals and follow-up plans. First, start looking for offline hospitals. If the offline hospital does not have the corresponding service, it will be downgraded to follow-up services. Finally, patient education articles will be used as a backup. This link is actually determined at the beginning. After the link is determined, it will be executed, and during the execution process, real-time dynamic information must be implanted, that is, some information from this consultation must be extracted as search conditions. When searching for offline hospitals in this scenario, the patient's LBS is used to find that the patient is in XX, so the search is conducted near XX. Similarly, according to the weight split, there will be distance, such as priority within 3KM, then within 5KM, and there are quality requirements, first tertiary hospitals, then secondary hospitals, and communities. In this scenario, since there is no blood transplant program near XX, that is, there is no cooperating hospital, it is downgraded to the follow-up plan by default. In the follow-up plan, the patient's past purchase record is brought up, and a private doctor with a higher purchase amount is added. Therefore, it is determined that some higher-priced follow-up services can be recommended. The follow-up plan for blood transplantation has two products, 1190 and 658. The high-priced follow-up plan 1190 is recommended first.

[0089] 5) Search and recall algorithm: This embodiment of the application provides an improved algorithm:

[0090] First define the relevant properties:

[0091] The final search recall algorithm is:

[0092] 6) No service supply record pool: When the service supply cannot be found, the corresponding search record will be added to the no service supply pool. Although it cannot be found, if a large number of doctors search frequently, it actually means that this service supply may be very common and it is necessary to expand the business. Therefore, it should be recorded first and wait for BD personnel to make further expansion.

[0093] The embodiment of the present application provides a technical solution that can judge the doctor's search intention, dynamically implant real-time information, provide no service supply records, and provide data guidance to BD in reverse, thereby improving the conversion rate of service sales, the accuracy of doctor search, and the expansion rate of service expansion. A set of technical search processes is designed to perform part-of-speech analysis on the search query, match union services, assign weights, and execute a four-level search link, while injecting the information in this doctor-patient consultation in real time, thereby achieving the core goal of improving search accuracy and recall rate.

[0094] Figure 7 Schematic diagram of the main units of the medical data search device according to an embodiment of the present application. Figure 7 As shown, the medical data search device 700 includes a receiving unit 701, a classification unit 702, a target service determination unit 703, a first search unit 704 and a second search unit 705.

[0095] The receiving unit 701 is configured to receive a medical data search request, obtain a corresponding search term, and split the search term to obtain individual words.

[0096] The classification unit 702 is configured to determine the part-of-speech classification corresponding to each word, and determine the synonyms and weights of each word according to the part-of-speech classification.

[0097] The target service determination unit 703 is configured to determine the target service based on each vocabulary, synonym and weight.

[0098] The first search unit 704 is configured to obtain current medical consultation data, and search for relevant dynamic real-time data based on the current medical consultation data and the target service.

[0099] The second search unit 705 is configured to search based on dynamic real-time data, target services, various words, synonyms and weights to obtain search result data.

[0100] In some embodiments, the classification unit 702 is further configured to: perform synonym conversion on the vocabulary corresponding to the part-of-speech classification corresponding to the supply range to obtain corresponding synonyms.

[0101] In some embodiments, the target service determination unit 703 is further configured to: determine one or more services corresponding to the vocabulary and synonyms corresponding to the largest weight as target services.

[0102] In some embodiments, the first search unit 704 is further configured to: obtain relevant historical consultation data based on current consultation data, obtain coordinate positioning from the current consultation data; and search for dynamic real-time data related to the target service based on the coordinate positioning and historical consultation data.

[0103] In some embodiments, the receiving unit 701 is further configured to: identify meaningless words in the search terms, remove meaningless words from the search terms to obtain preprocessed search terms; and split the preprocessed search terms to obtain individual words.

[0104] In some embodiments, the second search unit 705 is further configured to: use dynamic real-time data, target services, various words, synonyms and weights as parameter values ​​of the search algorithm, and execute the assigned search algorithm to obtain search result data.

[0105] In some embodiments, the medical data search device further includes Figure 7 The search record adding unit not shown in the figure is configured to: when the executed search statement recall is empty, generate search records based on search terms, dynamic real-time data, target services, various vocabulary, synonyms and weights; add search records to the service-free supply record pool.

[0106] It should be noted that the medical data search method and the medical data search device of the present application have a corresponding relationship in terms of specific implementation contents, so the repeated contents will not be described again.

[0107] Figure 8 An exemplary system architecture 800 is shown to which the medical data search method or medical data search device according to the embodiments of the present application can be applied.

[0108] like Figure 8 As shown, system architecture 800 may include terminal devices 801, 802, 803, a network 804, and a server 805. Network 804 is used to provide a medium for communication links between terminal devices 801, 802, 803 and server 805. Network 804 may include various connection types, such as wired, wireless communication links, or optical fiber cables, etc.

[0109] Users can use terminal devices 801, 802, and 803 to interact with server 805 through network 804 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 801, 802, and 803, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only examples).

[0110] The terminal devices 801 , 802 , and 803 may be various electronic devices having a data search processing screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0111] Server 805 can be a server that provides various services, such as a background management server that provides support for medical data search requests submitted by users using terminal devices 801, 802, and 803 (only as an example). The background management server can receive medical data search requests, obtain corresponding search terms, split the search terms to obtain individual words; determine the part-of-speech classification corresponding to each word, and determine the synonyms and weights of each word based on the part-of-speech classification; determine the target service based on each word, synonym and weight; obtain current consultation data, search for related dynamic real-time data based on the current consultation data and the target service; search based on dynamic real-time data, target service, each word, synonym and weight to obtain search result data. Improve the efficiency and accuracy of data search, thereby improving the efficiency and accuracy of data search by doctors in the scenario of Internet hospital platform serving patients.

[0112] It should be noted that the medical data search method provided in the embodiment of the present application is generally executed by the server 805 , and accordingly, the medical data search device is generally set in the server 805 .

[0113] It should be understood that Figure 8 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0114] Reference below Fig. 9 , which shows a schematic diagram of the structure of a computer system 900 of a terminal device suitable for implementing an embodiment of the present application. Fig. 9 The terminal device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0115] like Fig. 9As shown, the computer system 900 includes a central processing unit (CPU) 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage part 908 into a random access memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the computer system 900 are also stored. The CPU 901, the ROM 902, and the RAM 903 are connected to each other through a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0116] The following components are connected to the I / O interface 905: an input section 906 including a keyboard, a mouse, etc.; an output section 907 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 908 including a hard disk, etc.; and a communication section 909 including a network interface card such as a LAN card, a modem, etc. The communication section 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to the I / O interface 905 as needed. A removable medium 911, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 910 as needed, so that a computer program read therefrom is installed into the storage section 908 as needed.

[0117] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 909, and / or installed from the removable medium 911. When the computer program is executed by the central processing unit (CPU) 901, the above-mentioned functions defined in the system of the present application are executed.

[0118] It should be noted that the computer-readable medium shown in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. Computer-readable storage media may include, for example, but are not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0119] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the above-mentioned module, program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0120] The units involved in the embodiments described in the present application may be implemented by software or hardware. The units described may also be set in a processor, for example, it may be described as: a processor includes a receiving unit, a classification unit, a target service determination unit, a first search unit, and a second search unit. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0121] As another aspect, the present application also provides a computer-readable medium, which may be included in the device described in the above embodiment; or it may exist independently and not be assembled into the device. The above computer-readable medium carries one or more programs. When the above one or more programs are executed by a device, the device receives a medical data search request, obtains the corresponding search terms, splits the search terms to obtain individual words; determines the part-of-speech classification corresponding to each word, and determines the synonyms and weights of each word based on the part-of-speech classification; determines the target service based on each word, synonym and weight; obtains the current consultation data, and searches for related dynamic real-time data based on the current consultation data and the target service; searches based on the dynamic real-time data, the target service, each word, synonym and weight to obtain the search result data.

[0122] The computer program product of the present application includes a computer program, and when the computer program is executed by a processor, the medical data search method in the embodiment of the present application is implemented.

[0123] According to the technical solution of the embodiment of the present application, the efficiency and accuracy of data search can be improved, thereby improving the efficiency and accuracy of data search performed by doctors in the scenario of serving patients on the Internet hospital platform.

[0124] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A medical data search method, characterized in that: include: Receiving a medical data search request, obtaining a corresponding search term, and splitting the search term to obtain individual words; Determine the part-of-speech classification corresponding to each word, and determine the synonyms and weights of each word according to the part-of-speech classification; Determining a target service based on the respective words, the synonyms and the weights; Acquire current consultation data, and search for relevant dynamic real-time data based on the current consultation data and the target service; A search is performed based on the dynamic real-time data, the target service, the various words, the synonyms and the weights to obtain search result data.

2. The method according to claim 1, characterized in that Determining the synonyms of each word includes: The words corresponding to the part-of-speech classification corresponding to the supply range are converted into synonyms to obtain corresponding synonyms.

3. The method according to claim 1, characterized in that The target service determination includes: One or more services corresponding to the vocabulary and synonyms corresponding to the greatest weight are determined as target services.

4. The method according to claim 1, characterized in that: The dynamic real-time data related to the search based on the current consultation data and the target service includes: Based on the current medical consultation data, obtain relevant historical medical consultation data, and obtain coordinate positioning from the current medical consultation data; Dynamic real-time data related to the target service is searched based on the coordinate positioning and the historical consultation data.

5. The method according to claim 1, characterized in that The step of splitting the search term to obtain individual words includes: Identifying meaningless words in the search terms, and removing the meaningless words from the search terms to obtain preprocessed search terms; The preprocessed search term is split to obtain individual words.

6. The method according to claim 1, characterized in that The searching based on the dynamic real-time data, the target service, the various words, the synonyms and the weights to obtain search result data includes: The dynamic real-time data, the target service, the various words, the synonyms and the weights are used as parameter values ​​of a search algorithm, and the search algorithm after the assignment is executed to obtain search result data.

7. The method according to claim 1, characterized in that The method further comprises: When the executed search statement recall is empty, generating a search record based on the search term, the dynamic real-time data, the target service, the respective words, the synonyms and the weight; Add the search record to the no-service-provided record pool.

8. A medical data search device, characterized in that: include: A receiving unit configured to receive a medical data search request, obtain a corresponding search term, and split the search term to obtain individual words; A classification unit configured to determine the part-of-speech classification corresponding to each word, and determine the synonyms and weights of each word according to the part-of-speech classification; a target service determination unit configured to determine a target service based on the respective words, the synonyms and the weights; A first search unit is configured to obtain current consultation data and search for relevant dynamic real-time data based on the current consultation data and the target service; The second search unit is configured to search based on the dynamic real-time data, the target service, the various words, the synonyms and the weights to obtain search result data.

9. An electronic device for searching medical data, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images