Method, device, electronic device and storage medium for determining target patient reception users

Abstract

The present invention discloses a method, device, electronic device and storage medium for determining target users for treatment. The method comprises: determining dynamic tags and static tags corresponding to the users for treatment; determining the users to be selected for treatment associated with the target search terms; and determining at least one target user for treatment from the users to be selected for treatment based on the dynamic tags and static tags. The embodiments of the present invention solve the problem that the traditional method for determining the target user for treatment only relies on the user's offline personalized tags, cannot understand the user's current willingness for treatment in real time and give recommendation information, resulting in low accuracy of system recommendations, thereby improving the accuracy of recommendations and better meeting user needs.

Description

Technical Field

[0001] The embodiments of the present invention relate to computer processing technology, and more particularly to a method, device, electronic device and storage medium for determining a target user for consultation. Background Art

[0002] With the popularization of the Internet, a large amount of information on patients and receiving users has been accumulated in the medical field. When a patient chooses a receiving user, the server will determine and push the most suitable receiving user resources for the patient, so as to better meet the medical treatment needs of netizens.

[0003] At present, in the prior art, a receiving user that is compatible with the visiting user is determined for the visiting user based on the visiting user attributes and the receiving user attributes. This universal determination method cannot adapt to the user's personalized needs, resulting in the information pushed by the server often not being the information required by the user, causing a technical problem of poor user experience. Summary of the invention

[0004] The embodiments of the present invention provide a method, device, electronic device and storage medium for determining a target user for receiving treatment, so as to achieve the technical effect of recommending a more suitable target user for receiving treatment, thereby improving the efficiency of treatment.

[0005] In a first aspect, an embodiment of the present invention provides a method for determining a target patient, including:

[0006] Determine dynamic tags and static tags corresponding to the patient;

[0007] Determine the users to be selected for consultation associated with the target search term;

[0008] At least one target user is determined from the users to be selected for consultation according to the dynamic tags and the static tags.

[0009] In a second aspect, an embodiment of the present invention further provides a device for determining a target user for consultation, the device comprising:

[0010] A label determination module, used to determine dynamic labels and static labels corresponding to the patient;

[0011] A module for determining users to be selected for consultation, used for determining users to be selected for consultation associated with a target search term;

[0012] The target user determination module is used to determine at least one target user from the users to be selected for treatment according to the dynamic tags and the static tags.

[0013] In a third aspect, an embodiment of the present invention further provides an electronic device for determining a target user for consultation, the electronic device comprising:

[0014] one or more processors;

[0015] a storage device for storing one or more programs,

[0016] When the one or more programs are executed by the one or more processors, the one or more processors implement the method for determining the target user for consultation as described in any one of the embodiments of the present invention.

[0017] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for determining a target user for consultation provided by any embodiment of the present invention.

[0018] The embodiment of the present invention generates dynamic tags by acquiring the search behavior data, click behavior data and order behavior data of the visiting user, calculates the target tag weight of each dynamic tag, takes into account the user's real-time personalized tag attributes, combines the tag weight corresponding to the static tag generated by the offline data of the visiting user and the receiving user weight of the user to be selected, calculates the attribute evaluation value of each user to be selected, and then determines the target receiving user, which solves the problem that the target receiving user suitable for the visiting user is currently determined based on the visiting user attributes and the receiving user attributes, which cannot be adapted to the user's personalized needs, resulting in the determined target receiving user information often not being compatible with the visiting user, resulting in a poor user experience. By combining the offline tags corresponding to the visiting user information and the dynamic tags, a target receiving user who is more suitable for the visiting user is determined for the visiting user, thereby improving the adaptation rate of the visiting user and the target receiving user, and at the same time achieving the effect of improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required to describe the embodiments. Obviously, the drawings introduced are only drawings of a part of the embodiments to be described in the present invention, rather than all the drawings. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 A flowchart of a method for determining a target patient to be treated provided by the first embodiment of the present invention;

[0021] Figure 2 A schematic diagram of a method for determining a target user for consultation provided by Embodiment 2 of the present invention;

[0022] Figure 3 A structural block diagram of a device for determining a target user for consultation provided by a fourth embodiment of the present invention;

[0023] Figure 4 This is a schematic diagram of the structure of an electronic device provided in Embodiment 5 of the present invention. DETAILED DESCRIPTION

[0024] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0025] Embodiment 1

[0026] Figure 1 This is a flow chart of a method for determining a target user for treatment provided in the first embodiment of the present invention. This embodiment can be applied to the case of determining the user who is most suitable for the patient. The method can be executed by the device for determining the target user for treatment in the embodiment of the present invention. The device can be implemented in software and / or hardware. Optionally, it can be implemented by an electronic device, which can be a mobile terminal, a PC or a server. The device can be configured in a computing device. The method for determining the target user for treatment provided in this embodiment specifically includes the following steps:

[0027] S110: Determine dynamic tags and static tags corresponding to the patient visiting the clinic.

[0028] Among them, the visiting user can be understood as a patient or a user who buys medicine. The label can be information marked according to a certain behavioral characteristic of the user. The behavioral characteristic can be a behavioral characteristic such as searching, clicking or registering on the terminal by the user. For example, the name of the hospital searched by the user can be used as a label, or the registration information of the visiting user can be used as a label. Further, the label corresponding to the visiting user represents the attention of the visiting user to each doctor, hospital or department, which is used to characterize the needs of the visiting user. Dynamic labels can be label information that changes with the user's behavioral characteristics. For example, based on a certain behavioral characteristic of the user, the label that best matches this behavioral characteristic can be determined and used as a dynamic label. Static labels can be label information that has been stored in the user's historical electronic medical records and / or electronic prescriptions and will not change in real time according to the changes in the user's behavioral characteristics. It can also be label information that the user marked according to the behavioral characteristics on the previous day and before. For example, the name of the hospital searched by the user between the previous day and the previous N days can be used as a static label, where N is a normal number.

[0029] It should be noted that, the dynamic tag corresponding to the patient can be determined based on the operational behavior data of the patient. For example, the tag data related to the operational behavior can be obtained through the operational behavior of the patient, wherein the operational behavior can be the search behavior, click behavior or order behavior of the patient, and the tag data information corresponding to the operational behavior of the patient is used as the dynamic tag.

[0030] It should also be noted that the static tag corresponding to the patient can be determined based on the offline data of the patient. For example, the historical diagnosis record of the patient can be obtained, and the data information on the electronic medical record and / or electronic prescription of the patient can be extracted as the offline data of the patient, and the offline data tag can be used as the static tag.

[0031] Specifically, the dynamic tags and static tags corresponding to the patient can be determined based on the operation behavior data and offline data of the patient. For example, the behavior data and offline data in the patient's historical behavior log or the patient's historical diagnosis record are extracted, and accordingly, the operation behavior data tag information and offline data tag information corresponding to the patient can be obtained.

[0032] Optionally, determining the dynamic tags and static tags corresponding to the patient's visiting user includes: determining the dynamic tags based on the patient's operational behavior data; wherein the operational behavior data includes search behavior data, click behavior data, and order behavior data; determining the offline tags corresponding to the patient's visiting user, and using the offline tags as the static tags.

[0033] Among them, the search behavior can be understood as the behavior of the patient using a certain input device on a certain terminal to search for certain information, and then the information data searched according to the patient's search behavior is used as the search behavior data, for example, the search behavior data can be the doctor word, department word or hospital word searched by the patient. Click behavior can be understood as the behavior of the patient using a certain input device on a certain terminal to click on certain information, and then the information data confirmed according to the patient's click behavior is used as the click behavior data, for example, the click behavior data can be the doctor, the department where the doctor is located or the hospital where the doctor is located on the terminal page clicked by the patient using the input device. Order behavior can be understood as the behavior of the patient generating an order by registering or placing an order, and then the information data corresponding to the patient's order behavior is used as the order behavior data, for example, the order behavior data can be the information data on the registration form obtained by the patient performing the registration operation, and the data can be the hospital name, doctor's name or test items, etc. The search behavior data, click behavior data and order behavior data of the visiting users can be extracted from the historical behavior logs of the visiting users, and then the dynamic tags corresponding to the search behavior data, click behavior data and order behavior data of the visiting users can be determined to obtain dynamic tag information.

[0034] Among them, the offline tag can be understood as the data tag information corresponding to the historical behavior of the patient stored in the terminal database, which can be the historical diagnosis record of the patient. By extracting the offline data information on the electronic medical record and / or electronic prescription in the historical diagnosis record of the patient, the label information of the offline data of the patient is obtained, and the offline tag is used as a static tag.

[0035] By determining dynamic tags based on the operational behavior data of the patient, and determining static tags based on the offline tags corresponding to the patient, it not only takes into account the tag information of the patient in the offline state, but also monitors the patient's intentions in real time, thereby improving the accuracy of recommendations.

[0036] It should be noted that, by determining the dynamic label based on the operational behavior data of the patient, the label information corresponding to the operational behavior data can be extracted based on the conditions for obtaining the operational behavior. For example, based on the operational behavior of the patient within a preset time or preset quantity, the operational behavior data can be obtained, and then the label information corresponding to the operational behavior data can be determined to obtain the dynamic label information.

[0037] It should also be noted that the operation behavior includes search behavior, click behavior and order behavior.

[0038] Specifically, based on the operation behavior data of the visiting user within a preset time or a preset number, label information corresponding to the operation behavior data is obtained, and accordingly, a dynamic label corresponding to the operation behavior data is obtained.

[0039] In this embodiment, determining the dynamic tag based on the operational behavior data of the visiting user includes: obtaining the operational behavior data of the visiting user for a preset time period or a preset number; determining the search tag of each search behavior data, the click tag of each click behavior data, and the order tag of each order behavior data in the operational behavior data, and using the search tag, click tag, and order tag as dynamic tags.

[0040] Among them, the preset duration can be the number of days information preset for the operation behavior of the patient user. For example, the preset duration is 1 day, and the operation behavior data of the patient user in the last 1 day can be obtained. If the operation behavior data in the last 1 day is not found, the preset duration can be increased, which can be 2 days or 3 days. The preset number refers to the quantity information preset for the operation behavior of the patient user. For example, the preset number is 20, and the operation behavior data of the patient user in the last 20 times can be obtained. There is no limitation on the preset duration and preset number here. The search tag can be understood as the tag information corresponding to the search behavior data determined by each search behavior of the patient user. For example, the search tag can be the tag information generated by the patient user data obtained by each search operation of the patient user, such as the tag corresponding to the patient user such as the doctor, hospital or department can be generated. The click tag can be understood as the tag information corresponding to the click behavior data determined by each click behavior of the patient user. For example, the click tag can be the tag information generated by the patient user data obtained by each click operation of the patient user, such as the tag corresponding to the patient user such as the doctor, hospital or department can be generated. The order label can be understood as the label information corresponding to the order behavior data determined by each order behavior of the patient. For example, the order label can be the label information generated by the patient data of the patient's order obtained each time the patient performs an order operation. For example, labels corresponding to the patient's doctor, hospital or department can be generated. By obtaining the patient's operation behavior data for a preset time or a preset number, the label of each operation behavior data is determined. Accordingly, the search label of each search behavior data, the click label of each click behavior data and the order label of each order behavior data are obtained. Then, the dynamic label information is obtained, and the use needs of the patient are determined more accurately, which facilitates the subsequent more effective recommendation of the patient.

[0041] S120: Determine the user to be selected for consultation who is associated with the target search term.

[0042] Among them, the target search term can be understood as the search term information searched by the patient in the search edit box, and the corresponding search content can be obtained based on these search terms. For example, the patient searches for "diabetes" in the search edit box, and can use "diabetes" as the target search term to obtain a series of search contents based on the diabetes search term, such as diabetes hospitals, diabetes doctors, or diabetes drugs. The patient can be a doctor, but in order to improve the efficiency of consultation and treatment, the patient can also correspond to different departments, different titles, and different cities. For example, the patient users of different regions, departments, and titles can register on the consultation platform, and after passing the authentication, they can receive the corresponding online consultation tasks. The patient to be selected can be understood as the patient user information associated with the target search term. For example, if the target search term is diabetes, the patient to be selected can be the patient user whose search, click, or order behavior data contains label information such as diabetes, diabetes doctors, or diabetes drugs. Optionally, the patient to be selected associated with the target search term can be determined based on the label information generated by the target search term and the search, click, or order behavior data of each patient.

[0043] It should be noted that when each user to be selected for treatment registers on the website, he or she can edit information to complete the user information. The complete user information may include information such as the type of disease, region, department or hospital that the user is good at. Furthermore, the type of disease that the user is good at can be used as a label to facilitate subsequent users to complete the label information based on the user's comments.

[0044] It should also be noted that the users to be selected and associated with the target search term can be determined by determining the relationship between the target search term and each seeing user. For example, the association information between the target search term and each seeing user can be obtained based on the target search term information of the seeing user. The seeing user information whose matching degree with the target search term is higher than a preset threshold can be extracted from the association information of each seeing user. Accordingly, the seeing users whose matching degree with the target search term is higher than a preset threshold can be used as the users to be selected and associated with the target search term.

[0045] Optionally, the determining of the to-be-selected users associated with the target search term includes: determining the to-be-selected users associated with the target search term based on association information between the target search term and each of the users being treated.

[0046] Among them, the associated information includes the main treatment information of the receiving user and the comment information of the receiving user. The main treatment information can be understood as the relevant information of certain diseases that the receiving user is good at treating. For example, the main treatment information can be the orthopedic surgery information that the doctor is good at, such as various types of fractures, bone tumors, bone tuberculosis or osteomyelitis, etc. The main treatment information can also be the information of various treatable diseases included in the orthopedic surgery department. Comment information can be understood as some analytical language information for the receiving user. This language information can objectively evaluate the receiving user. It should be noted that the receiving user can make an appointment with each receiving user. When the receiving user finishes the consultation, he can comment on the target receiving user and generate comment information. When determining the target receiving user, the main treatment information and comment information of the receiving user can be combined to improve the accuracy of the consultation.

[0047] In a specific application, by obtaining the attending physician information of each patient and the comment information of the patient, the patient corresponding to the information whose associated information matches the target search term higher than a preset threshold is found, and the patient whose match degree with the target search term is higher than a preset threshold is determined among all the patients. Then, the patient to be selected associated with the target search term is determined, taking into account both the attending physician information and the comment information of the patient, thereby improving the accuracy of the consultation, better meeting the needs of the patient, and recommending better quality patient information to the patient.

[0048] It should be noted that the associated information of each receiving user can be adjusted dynamically, the comment information can increase as the comments of the receiving user on the receiving user increase, and the main treatment information can also be continuously improved based on the comment information of the receiving user. For example, the receiving user has made an appointment with a target receiving user. After the patient's consultation, the receiving user can comment on the target receiving user. The server can update the label for the target receiving user in real time based on the information of the patient's comments on the target receiving user. That is, the label corresponding to the target receiving user can be dynamically adjusted, and accordingly, the associated information corresponding to the target receiving user is also dynamically adjusted.

[0049] Furthermore, in order to improve the convenience of determining the target user, the comment information corresponding to the target user can be pre-processed to dynamically adjust the associated information corresponding to the target user. For example, a machine learning model can be used to take each comment information as input, and the keywords corresponding to each comment information can be output. The server can use the keyword information to extract the keywords, and then determine the label corresponding to the user according to the frequency of the keyword, and update the label for the target user to dynamically adjust the associated information corresponding to the target user.

[0050] S130: Determine at least one target user from the users to be selected for treatment according to the dynamic tags and the static tags.

[0051] Among them, the target receiving user can be understood as the receiving user who matches the target search term of the receiving user. Based on the dynamic tags generated by the operating behavior data of the receiving user and the static tags corresponding to the receiving user, the receiving user to be selected is determined in combination with the target search term of the receiving user and the associated information of each receiving user. Then, at least one target receiving user is determined from the receiving users to be selected. For example, the receiving user to be selected is determined based on the matching degree between the target search term and the main treatment information of each receiving user and the comment information of the receiving user. Accordingly, the dynamic tags and static tags of the receiving user are generated by extracting the operating behavior data and offline data of the receiving user. According to the tag information of the receiving user and the receiving user to be selected, at least one target receiving user is determined from the receiving users to be selected.

[0052] It should be noted that after obtaining each dynamic tag in each operation behavior data, in order to better determine the matching relationship between the dynamic tag corresponding to the patient and the user to be selected for treatment, a weight can be assigned to each dynamic tag, and then the tag generated by each piece of data can obtain the corresponding weight, and accordingly, the weight corresponding to each search tag, click tag and order tag can be determined.

[0053] It should also be noted that the dynamic tags generated by each operation behavior data may be affected by factors such as its own behavior weight, the time when the behavior is generated, or the current access time. Dynamic tags include search tags for each search behavior data, click tags for each click behavior data, and order tags for each order behavior data.

[0054] Optionally, after determining the search tag of each search behavior data, the click tag of each click behavior data, and the order tag of each order behavior data in the operation behavior data, it also includes: for each search tag, click tag, and order tag, according to the behavior weight corresponding to the current tag, the time when the behavior corresponding to the current tag is generated, and the current access time, determining the to-be-processed tag weight of the current tag.

[0055] Among them, the current label can be understood as when the same processing is performed on the dynamic label generated by each operation behavior data, any dynamic label being processed can be used as the current label. For example, the behavior weight of the dynamic label can be processed. The specific processing method will not be repeated here, and the processing of one of the labels as the current label will be explained. The behavior weight refers to the weight information of the current operation behavior corresponding to the current label. The behavior generation time refers to the time information when the operation behavior corresponding to the current label is generated. For example, it can be the time when the user who visits the clinic performs this search behavior. The current access time refers to the time information when the operation behavior corresponding to the current label accesses the page. The weight of the label to be processed can be understood as the weight corresponding to the label generated by each operation behavior data. After determining the search tag of each search behavior data, the click tag of each click behavior data, and the order tag of each order behavior data in the operation behavior data, the behavior weight, behavior generation time, and current access time corresponding to the tag generated by each operation behavior data are obtained according to each search tag, click tag, and order tag, and then the tag weight generated by each operation behavior data is determined. For example, the "diabetes" tag generated by the search behavior data can be used as the current tag, and the "diabetes" tag is processed by obtaining the search behavior generation time or the current page access time, calculating the difference between the behavior generation time and the current page access time, and combining the behavior weight of this search behavior to determine the weight of the current tag "diabetes". Correspondingly, the weight of the tag to be processed corresponding to each dynamic tag can be obtained. Real-time acquisition of the information of the patient fully considers the real-time personalized factors of the user and improves the accuracy of the patient's consultation.

[0056] It should be noted that in order to better determine the attention of the patients to each user to be selected based on the dynamic tags and static tags, the weights of the dynamic tags and static tags corresponding to the patients can be processed. For example, the weights of the to-be-processed tags of the same tag corresponding to the patients can be processed. Furthermore, the weights of the same tag corresponding to the patients can be determined based on the search behavior, click behavior and order behavior of the patients. At the same time, the corresponding weight information can also be set for the static tags. According to the weight information of the same tag in the dynamic tags and the weights corresponding to the static tags, the suitable target patients can be recommended to the patients more accurately.

[0057] Optionally, determining at least one target reception user from the users to be selected for reception based on the dynamic tags and the static tags includes: merging the weights of pending tags of the same tag to obtain a target tag weight corresponding to the same tag; and determining at least one target reception user from the users to be selected for reception based on the target tag weight, the tag weight corresponding to the static tag, and the reception user weight of the user to be selected for reception.

[0058] Among them, the target label weight can be understood as a label for the current user, the label weight determined based on all the operation behaviors of the user, the label weight refers to the label weight determined based on the static label of the user, and the receiving user weight can be understood as the weight information of the receiving user set based on the matching information between the target search term and the user to be selected. By processing all the tags of the visiting users, the weights of the tags to be processed of the same tag in the dynamic tags generated based on different operation behavior data can be added to obtain the target tag weight based on this tag. For example, the 20 most recent search behavior data of the visiting users can be obtained to generate corresponding tags, the 20 most recent click behavior data of the visiting users can be obtained to generate corresponding tags, and the 5 most recent order behavior data of the visiting users can be obtained to generate corresponding tags. The tags obtained from the three operation behaviors may have repeated tags. For repeated tags, for example, the repeated tag is the "diabetes" tag, the weight of the "diabetes" tag in the search behavior data, the weight of the "diabetes" tag in the click behavior data, and the weight of the "diabetes" tag generated in the order behavior data can be added to obtain the target tag weight of the "diabetes" tag. Furthermore, in order to prevent the target tag weight corresponding to the dynamic tag from increasing infinitely, the target tag weight can be normalized, and then the processed tag weight is used as the final target tag weight. At the same time, corresponding weights are set for static tags generated based on offline data. Further, at least one target user can be determined from the users to be selected based on the user weight of the user to be selected, the target tag weight, and the tag weight corresponding to the static tag.

[0059] It should be noted that, based on the target label weight, the label weight corresponding to the static label, and the receiving user weight of the user to be selected, the attributes of each user to be selected can be evaluated. For example, the evaluation value of each user to be selected relative to the receiving user can be calculated based on the attributes of each user to be selected. In order to facilitate the subsequent selection of receiving users with high evaluation values, the evaluation values ​​of each user to be selected can be sorted, so that the receiving user can find the information of each user to be selected according to the evaluation value. The receiving user with an evaluation value higher than a set threshold can also be recommended to the receiving user, thereby determining the target receiving user.

[0060] Optionally, determining at least one target reception user from the users to be selected based on the target label weight, the label weight corresponding to the static label, and the reception user weight of the users to be selected includes: determining the attribute evaluation value of each user to be selected based on the target label weight, the label weight of the static label, and the reception user weight; determining the target reception user based on the attribute evaluation value of each user to be selected.

[0061] Among them, the attribute evaluation value can be understood as the evaluation score value of each to-be-selected user relative to the patient, and the attribute evaluation value is used to characterize the preference of each to-be-selected user for the target patient. The target label weight corresponding to the dynamic label of the patient and the label weight of the static label are combined with the patient weight of the to-be-selected user to calculate the evaluation value of the attribute of each to-be-selected user relative to the patient. In order to facilitate the patient to find the information of each to-be-selected user according to the evaluation value, the evaluation value of each to-be-selected user can be sorted, and the to-be-selected users corresponding to the first k evaluation values ​​can be recommended to the patient, where k is a normal number. The to-be-selected users whose evaluation values ​​are higher than a certain set threshold can also be recommended to the patient, and then the target patient is determined, ensuring that the target patient is determined to be the most suitable for the patient, and better meeting the user experience requirements.

[0062] The technical solution of this embodiment generates dynamic tags by obtaining the search behavior data, click behavior data and order behavior data of the visiting users, calculates the target tag weight of each dynamic tag, takes into account the user's real-time personalized tag attributes, combines the tag weight corresponding to the static tag generated by the visiting users' offline data and the receiving user weight of the user to be selected, calculates the attribute evaluation value of each user to be selected, and then determines the target receiving user, which solves the problem that the target receiving user who is suitable for the visiting user is currently determined based on the visiting user attributes and the receiving user attributes, which cannot be adapted to the user's personalized needs, resulting in the determined target receiving user information often not being compatible with the visiting user, resulting in a poor user experience. By combining the offline tags corresponding to the visiting user information and the dynamic tags, a target receiving user who is more suitable for the visiting user is determined for the visiting user, thereby improving the adaptation rate between the visiting user and the target receiving user, and at the same time achieving the effect of improving the user experience.

[0063] Embodiment 2

[0064] As an alternative embodiment of the above embodiment, Figure 2 This is a flowchart of a method for determining a target user for consultation provided in the second embodiment of the present invention. For details, please refer to the following specific content.

[0065] like Figure 2 As shown, the target patient user can be determined by determining the matching score between the patient's offline personalized tags and the patient's treatment user, the matching score between the search term and the patient's treatment user, and the matching score between the patient's real-time personalized tags and the patient's treatment user.

[0066] Determine the matching score between the offline personalized tags of the visiting user and the receiving user, see Box 1, by obtaining the offline data of the visiting user, generate the offline personalized tags of the visiting user, and determine the weight information of the corresponding tags, and obtain the matching score between the offline personalized tags of the visiting user and the receiving user. Determine the matching score between the search term and the receiving user, see Box 2, according to the matching of the search term and the receiving user document, determine the weight information of the search term and the visiting user, and obtain the matching score between the search term and the receiving user.

[0067] Determine the matching score between the real-time personalized tag of the visiting user and the receiving user, see Box 3, by obtaining the latest 20 search behavior data of the visiting user, generating a corresponding tag for each search behavior data, and determining the weight information of the corresponding tag, obtaining the latest 20 click behavior data of the visiting user, generating a corresponding tag for each click behavior data, and determining the weight information of the corresponding tag, obtaining the latest 20 order behavior data of the visiting user, generating a corresponding tag for each order behavior data, and determining the weight information of the corresponding tag, obtaining the real-time personalized tag information of the visiting user and the tag weight information, and obtaining the matching score between the real-time personalized tag of the visiting user and the receiving user.

[0068] According to the matching score between the offline personalized tags of the visiting users and the seeing users, the matching score between the search terms and the seeing users, and the matching score between the real-time personalized tags of the visiting users and the seeing users, the attribute evaluation value of the seeing users corresponding to the target seeing users is determined, the attribute evaluation values ​​of the seeing users are sorted, and the seeing users information with evaluation values ​​higher than a preset threshold is recommended to the visiting users, thereby obtaining the target seeing users information.

[0069] For example, the 20 most recent search behavior data of the patient are taken. The search data includes doctor words, hospital words, department words, disease words, and symptom words. From the basic database of a certain hospital, find the data in the basic database corresponding to the search words in each search behavior data and generate the corresponding label. Calculate the label generated by each data and its corresponding weight. The weight calculation formula is as follows:

[0070]

[0071] Among them, α is the time attenuation coefficient, which is a constant; T now is the visit time of the patient, T action The time when the patient's behavior occurs; T now -T action The difference is converted into hours for calculation; w is the weight of this behavior; S is the label weight generated for each behavior data.

[0072] Get the 20 most recent click behavior data of the patient. Get the doctor clicked by the patient, the department the doctor is in, and the hospital the doctor is in, and generate the corresponding doctor, hospital, and department labels. Get the hospital data clicked by the patient, and generate the corresponding hospital label. Calculate the label generated by each piece of data and its corresponding weight. The weight formula is the same as formula (1).

[0073] Get the five most recent order behavior data of the patient. According to the registration and expert consultation order information placed by the patient, obtain the doctor who placed the order, the department where the doctor is located, the hospital where the doctor is located, and the disease label information filled in the order, and generate the corresponding doctor, hospital, department, and disease labels. Calculate the label generated by each data and its corresponding weight. The weight formula is the same as formula (1).

[0074] The tags generated by the search behavior, click behavior, and order behavior data are combined and summarized to obtain the user's real-time personalized tags and their weights. Aggregate according to each tag, such as the "diabetes" tag. Add the weights of the diabetes tags obtained by the search tag, click tag, and order tag to get the weight of the diabetes tag of the visiting user.

[0075] In this embodiment, in order to prevent the weight corresponding to the real-time personalized tag of the visiting user from increasing infinitely, the weight corresponding to the real-time personalized tag is first normalized, and the conversion formula is as follows:

[0076] S=lnS+300 (2)

[0077] In order to eliminate abnormal data, after conversion, if S is less than 0, it is treated as 0; when S is greater than 350, it is treated as 350.

[0078] The real-time personalized tags of the visiting user are matched with the receiving user's document. The weight sum of the matched real-time personalized tags is the matching score between the real-time personalized tags of the visiting user and the receiving user, recorded as S 1 .

[0079] Add real-time personalized tags of patients to the sorting process to influence the sorting of patients.

[0080] S new =S 1 *a+S 2 *b (3)

[0081] Among them, S 2 is the matching score between the offline personalized label of the patient and the receiving user, a and b are the distribution coefficients, S new is the attribute evaluation value of the receiving user. The receiving user presses S new Sort by evaluation value.

[0082] The technical solution of this embodiment generates dynamic tags by obtaining the search behavior data, click behavior data and order behavior data of the visiting users, calculates the target tag weight of each dynamic tag, takes into account the user's real-time personalized tag attributes, combines the tag weight corresponding to the static tag generated by the visiting users' offline data and the receiving user weight of the user to be selected, calculates the attribute evaluation value of each user to be selected, and then determines the target receiving user, which solves the problem that the target receiving user who is suitable for the visiting user is currently determined based on the visiting user attributes and the receiving user attributes, which cannot be adapted to the user's personalized needs, resulting in the determined target receiving user information often not being compatible with the visiting user, resulting in a poor user experience. By combining the offline tags corresponding to the visiting user information and the dynamic tags, a target receiving user who is more suitable for the visiting user is determined for the visiting user, thereby improving the adaptation rate between the visiting user and the target receiving user, and at the same time achieving the effect of improving the user experience.

[0083] Embodiment 3

[0084] Figure 3 This is a structural block diagram of a device for determining a target user for consultation provided in Embodiment 3 of the present invention. The device comprises: a tag determination module 310 , a to-be-selected user determination module 320 , and a target user determination module 330 .

[0085] The tag determination module 310 is used to determine the dynamic tags and static tags corresponding to the patient;

[0086] A to-be-selected user determination module 320 is used to determine a to-be-selected user associated with a target search term;

[0087] The target user determination module 330 is used to determine at least one target user from the users to be selected for treatment according to the dynamic tags and the static tags.

[0088] The technical solution of this embodiment generates dynamic tags by obtaining the search behavior data, click behavior data and order behavior data of the visiting users, calculates the target tag weight of each dynamic tag, takes into account the user's real-time personalized tag attributes, combines the tag weight corresponding to the static tag generated by the visiting users' offline data and the receiving user weight of the user to be selected, calculates the attribute evaluation value of each user to be selected, and then determines the target receiving user, which solves the problem that the target receiving user who is suitable for the visiting user is currently determined based on the visiting user attributes and the receiving user attributes, which cannot be adapted to the user's personalized needs, resulting in the determined target receiving user information often not being compatible with the visiting user, resulting in a poor user experience. By combining the offline tags corresponding to the visiting user information and the dynamic tags, a target receiving user who is more suitable for the visiting user is determined for the visiting user, thereby improving the adaptation rate between the visiting user and the target receiving user, and at the same time achieving the effect of improving the user experience.

[0089] In the above device, optionally, the tag determination module 310 includes:

[0090] A dynamic tag determination unit, used to determine a dynamic tag according to the operation behavior data of the patient; wherein the operation behavior data includes search behavior data, click behavior data and order behavior data;

[0091] The static tag determining unit is used to determine the offline tag corresponding to the patient visiting the clinic, and use the offline tag as the static tag.

[0092] In the above device, optionally, the dynamic tag determining unit includes:

[0093] An operation behavior data acquisition subunit is used to acquire the operation behavior data of the patient in a preset time or a preset amount;

[0094] The dynamic tag determination subunit is used to determine the search tag of each search behavior data, the click tag of each click behavior data and the order tag of each order behavior data in the operation behavior data, and use the search tag, click tag and order tag as dynamic tags.

[0095] In the above device, optionally, the dynamic tag determination unit further includes:

[0096] The subunit for determining the weight of tags to be processed is used to determine the weight of tags to be processed of the current tag for each search tag, click tag and order tag according to the behavior weight corresponding to the current tag, the time when the behavior corresponding to the current tag is generated and the current access time.

[0097] In the above-mentioned device, optionally, the module for determining the user to be selected 320 is specifically used to determine the user to be selected associated with the target search term based on the associated information between the target search term and each user to be selected; wherein the associated information includes the main treatment information of the user to be selected and the comment information on the user to be selected.

[0098] In the above device, optionally, the target user determination module 330 includes:

[0099] A target tag weight determination unit, configured to obtain a target tag weight corresponding to the same tag by merging the tag weights to be processed of the same tag;

[0100] The target user determination unit is used to determine at least one target user from the users to be selected according to the target tag weight, the tag weight corresponding to the static tag, and the user weight of the user to be selected.

[0101] In the above device, optionally, the target user determination unit includes:

[0102] The attribute evaluation value determination subunit is used to determine the attribute evaluation value of each to-be-selected user according to the target label weight, the label weight of the static label and the weight of the user to be treated;

[0103] The target user determination subunit is used to determine the target user according to the attribute evaluation value of each user to be selected for treatment.

[0104] Embodiment 4

[0105] Figure 4 A schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. Figure 4 A block diagram of an exemplary electronic device 40 suitable for implementing exemplary embodiments of the present invention is shown. Figure 4 The electronic device 40 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0106] like Figure 4 As shown, the electronic device 40 is in the form of a general computing device. The components of the electronic device 40 may include but are not limited to: one or more processors or processing units 401, a system memory 402, and a bus 403 connecting different system components (including the system memory 402 and the processing unit 401).

[0107] Bus 403 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnect (PCI) bus.

[0108] The electronic device 40 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 40, including volatile and non-volatile media, removable and non-removable media.

[0109] System memory 402 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 404 and / or cache memory 405. Electronic device 40 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 406 may be used to read and write non-removable, non-volatile magnetic media ( Figure 4 not shown, usually called a "hard drive"). Although Figure 4 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 403 via one or more data medium interfaces. Memory 402 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of various embodiments of the present invention.

[0110] A program / utility 408 having a set (at least one) of program modules 407 may be stored, for example, in memory 402, such program modules 407 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 407 generally perform the functions and / or methods of the embodiments described herein.

[0111] The electronic device 40 may also communicate with one or more external devices 409 (e.g., keyboards, pointing devices, displays 410, etc.), may communicate with one or more devices that enable a user to interact with the electronic device 40, and / or may communicate with any device that enables the electronic device 40 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface 411. Furthermore, the electronic device 40 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 412. As shown, the network adapter 412 communicates with other modules of the electronic device 40 via the bus 403. It should be understood that although Figure 4 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 40, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0112] The processing unit 401 executes various functional applications and data processing by running the programs stored in the system memory 402, for example, implementing the method for determining the target user provided in the embodiment of the present invention.

[0113] Embodiment 5

[0114] Embodiment 5 of the present invention further provides a storage medium including computer executable instructions, wherein the computer executable instructions are used to execute a method for determining a target user when executed by a computer processor.

[0115] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: 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 this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0116] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals 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 a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0117] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0118] Computer program code for performing the operation of embodiments of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0119] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for determining target users, characterized in that: include: Determine dynamic tags and static tags corresponding to the patient; Determine the users to be selected for consultation associated with the target search term; Determine at least one target user from the users to be selected for treatment according to the dynamic tags and the static tags; Wherein, determining the dynamic tag corresponding to the patient user includes: determining the dynamic tag according to the operation behavior data of the patient user, including: determining the search tag of each search behavior data, the click tag of each click behavior data and the order tag of each order behavior data in the operation behavior data, and using the search tag, click tag and order tag as dynamic tags; The method further includes: for each search tag, click tag and order tag, determining the tag weight to be processed of the current tag according to the behavior weight corresponding to the current tag, the behavior generation time corresponding to the current tag and the current access time; wherein the calculation formula for determining the tag weight to be processed of the current tag is: Where α is the time attenuation coefficient; T now is the current visit time of the patient, T action is the time when the user's behavior occurs; w is the behavior weight; S is the weight of the tag to be processed for each piece of behavior data; Determining at least one target user from the users to be selected for consultation based on the dynamic tags and the static tags includes: By merging the weights of the tags to be processed with the same tag, the target tag weight corresponding to the same tag is obtained; Normalizing the target label weights, and using the processed label weights as the final target label weights; At least one target seeing user is determined from the seeing users to be selected according to the target tag weight, the tag weight corresponding to the static tag, and the seeing user weight of the seeing user to be selected.

2. The method according to claim 1, characterized in that The step of determining the dynamic tags and static tags corresponding to the patient visiting the clinic includes: Determine the dynamic tag according to the operation behavior data of the patient; wherein the operation behavior data includes search behavior data, click behavior data and order behavior data; An offline tag corresponding to the patient visiting the clinic is determined, and the offline tag is used as the static tag.

3. The method according to claim 2, characterized in that Determining the dynamic tag according to the operation behavior data of the visiting user includes: The operation behavior data of the patient visiting the clinic in a preset time period or a preset amount are obtained to determine a dynamic tag according to the operation behavior data of the patient visiting the clinic.

4. The method according to claim 1, characterized in that The step of determining the user to be selected for consultation associated with the target search term includes: Determining the to-be-selected user associated with the target search term according to the association information between the target search term and each user to be treated; The associated information includes the main medical information of the patient and the comment information of the patient.

5. The method according to claim 1, characterized in that The step of determining at least one target patient receiving user from the patients to be selected according to the target label weight, the label weight corresponding to the static label, and the patient receiving user weight of the patient receiving user to be selected comprises: Determine the attribute evaluation value of each user to be selected for treatment according to the target label weight, the label weight of the static label and the treatment user weight; The target user for treatment is determined based on the attribute evaluation value of each user to be selected for treatment.

6. A device for determining a target patient, characterized in that: include: A label determination module, used to determine dynamic labels and static labels corresponding to the patient; A module for determining users to be selected for consultation, used for determining users to be selected for consultation associated with a target search term; A target user determination module, used to determine at least one target user from the users to be selected for treatment according to the dynamic tags and the static tags; A tag determination module, used to determine a dynamic tag according to the operation behavior data of the patient; The tag determination module includes a dynamic tag determination unit; The dynamic tag determination unit includes: the dynamic tag determination subunit, which is used to determine the search tag of each search behavior data, the click tag of each click behavior data, and the order tag of each order behavior data in the operation behavior data, and use the search tag, click tag, and order tag as dynamic tags: The dynamic tag determination unit further includes: a tag weight determination subunit for processing, which is used to determine the tag weight for processing of the current tag according to the behavior weight corresponding to the current tag, the behavior generation time corresponding to the current tag, and the current access time for each search tag, click tag, and order tag; wherein the calculation formula for determining the tag weight for processing of the current tag is: Where α is the time attenuation coefficient; T now is the current visit time of the patient, T action is the time when the user's behavior occurs; w is the behavior weight; S is the weight of the tag to be processed for each piece of behavior data; The target user determination module includes: a target label weight determination unit, which is used to obtain a target label weight corresponding to the same label by merging the label weights to be processed of the same label; the target label weight determination unit is also used to normalize the target label weight and use the processed label weight as the final target label weight; a target user determination unit is used to determine at least one target user from the users to be selected based on the target label weight, the label weight corresponding to the static label, and the user weight of the user to be selected.

7. An electronic device, characterized in that: The device comprises: 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 for determining a target user for consultation as described in any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for determining a target user for consultation as described in any one of claims 1 to 5 is implemented.

Images