Data recommendation method, device, electronic device and computer readable medium

Abstract

The present application discloses a data recommendation method, device, electronic device and computer-readable medium, which relates to the field of big data processing technology. The method includes: if the user logs in successfully, displaying an online ordering page; obtaining a user ID to call an information acquisition interface to obtain medical information, and then extracting a target field value, combining the medical result field value and the doctor's advice field value contained in the target field value according to a preset priority to obtain a combined field value, and then converting it into a high-dimensional vector and performing similarity calculation with the vectors corresponding to each dish label in the dish portrait, determining the dish label corresponding to the similarity greater than a preset threshold as the recommended dish name, and the preset priority is determined according to the character length of the medical result field value and the doctor's advice field value; determining the target dish name according to the check operation; if the order payment is successful, obtaining the target address and generating a delivery task in combination with the target dish name and sending it to the food delivery terminal. Improve the rationality and personalization of data recommendation.

Description

Technical Field

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

[0002] At present, many hospitals have meal ordering QR codes posted in front of the beds. Users can order meals online by scanning the QR codes, which has brought convenience to many patients. However, not all patients understand the relationship between their personal illness and diet. This may result in patients ordering the wrong food online, causing the patients to recover less quickly, or even worsening of their illness and the occurrence of complications. It is impossible to recommend suitable dishes based on the patients' conditions. Summary of the invention

[0003] In view of this, the embodiments of the present application provide a data recommendation method, device, electronic device and computer-readable medium, which can solve the problem that the existing online ordering system cannot recommend suitable dishes according to the patient's condition.

[0004] To achieve the above objective, according to one aspect of an embodiment of the present application, a data recommendation method is provided, comprising:

[0005] In response to the user scanning the graphic code, jumping to the login page, and in response to the user successfully logging in, displaying the online ordering page;

[0006] Obtain a user ID, and then call an information acquisition interface according to the user ID to obtain diagnosis and treatment information;

[0007] Extracting a target field value from the diagnosis and treatment information, matching the target field value with a dish label in a preset dish recommendation portrait to determine a recommended dish name; matching the target field value with a dish label in a preset dish recommendation portrait to determine a recommended dish name, including: combining the diagnosis and treatment result field value and the doctor's advice field value contained in the target field value according to a preset priority to obtain a combined field value, converting the combined field value into a high-dimensional vector through word embedding, calculating the similarity between the high-dimensional vector and the vector corresponding to each dish label in the preset dish portrait, and then determining the dish label corresponding to the vector corresponding to the similarity greater than a preset threshold as the recommended dish name, wherein the preset priority is determined according to the character length of the diagnosis and treatment result field value and the doctor's advice field value;

[0008] Display the dish name to the user and determine the target dish name based on the user's check operation;

[0009] In response to successful order payment, the target address is obtained, and a delivery task is generated and sent to the food delivery terminal based on the target dish name and the target address.

[0010] Optionally, display the online ordering page, including:

[0011] The service channel identifier corresponding to the service channel used by the user is obtained, and the corresponding online ordering page is displayed based on the service channel identifier.

[0012] Optionally, calling an information acquisition interface according to the user identifier to obtain diagnosis and treatment information includes:

[0013] The information acquisition authority is verified according to the user identification and the information acquisition interface. In response to the information acquisition authority verification being passed, the information acquisition interface is called to acquire the diagnosis and treatment information corresponding to the user identification.

[0014] Optionally, extracting target field values ​​in the diagnosis and treatment information includes:

[0015] Extract the diagnosis and treatment result field value and the medical advice field value in the diagnosis and treatment information.

[0016] Optionally, the target field value is matched with a dish label in a preset dish recommendation portrait to determine the recommended dish name, including:

[0017] Combine the diagnosis and treatment result field value with the doctor's order field value to obtain a combined field value;

[0018] The combined field value is matched with the dish label in the preset dish recommendation portrait for similarity, so as to determine the dish label corresponding to the similarity greater than the preset threshold as the recommended dish name.

[0019] Optionally, the target field value is matched with a dish label in a preset dish recommendation portrait to determine the recommended dish name, including:

[0020] Convert the diagnosis and treatment result field value into a first vector, and convert the doctor's order field value into a second vector;

[0021] Calculate the sum of the first vector and the second vector to obtain a third vector;

[0022] Convert the dish label in the preset dish recommendation portrait into a fourth vector;

[0023] The similarity between the third vector and each fourth vector is calculated to determine the dish label corresponding to the fourth vector corresponding to the similarity greater than a preset threshold as the recommended dish name.

[0024] In addition, the present application also provides a data recommendation device, including:

[0025] A login unit, configured to jump to a login page in response to a user scanning a graphic code, and to display an online ordering page in response to a successful user login;

[0026] an acquisition unit, configured to acquire a user identifier, and then call an information acquisition interface according to the user identifier to acquire diagnosis and treatment information;

[0027] A matching unit is configured to extract a target field value in the diagnosis and treatment information, match the target field value with a dish label in a preset dish recommendation portrait to determine a recommended dish name; match the target field value with a dish label in a preset dish recommendation portrait to determine a recommended dish name, including: combining the diagnosis and treatment result field value and the doctor's advice field value contained in the target field value according to a preset priority to obtain a combined field value, converting the combined field value into a high-dimensional vector through word embedding, calculating the similarity between the high-dimensional vector and the vector corresponding to each dish label in the preset dish portrait, and then determining the dish label corresponding to the vector corresponding to the similarity greater than a preset threshold as the recommended dish name, wherein the preset priority is determined according to the character length of the diagnosis and treatment result field value and the doctor's advice field value;

[0028] a target dish name determination unit, configured to display the dish name to the user and determine the target dish name according to the user's check operation;

[0029] The sending unit is configured to obtain a target address in response to successful order payment, generate a delivery task according to the target dish name and the target address, and send the task to the food delivery terminal.

[0030] Optionally, the login unit is further configured to:

[0031] The service channel identifier corresponding to the service channel used by the user is obtained, and the corresponding online ordering page is displayed based on the service channel identifier.

[0032] Optionally, the acquisition unit is further configured to:

[0033] The information acquisition authority is verified according to the user identification and the information acquisition interface. In response to the information acquisition authority verification being passed, the information acquisition interface is called to acquire the diagnosis and treatment information corresponding to the user identification.

[0034] Optionally, the matching unit is further configured to:

[0035] Extract the diagnosis and treatment result field value and the medical advice field value in the diagnosis and treatment information.

[0036] Optionally, the matching unit is further configured to:

[0037] Combine the diagnosis and treatment result field value with the doctor's order field value to obtain a combined field value;

[0038] The combined field value is matched with the dish label in the preset dish recommendation portrait for similarity, so as to determine the dish label corresponding to the similarity greater than the preset threshold as the recommended dish name.

[0039] Optionally, the matching unit is further configured to:

[0040] Convert the diagnosis and treatment result field value into a first vector, and convert the doctor's order field value into a second vector;

[0041] Calculate the sum of the first vector and the second vector to obtain a third vector;

[0042] Convert the dish label in the preset dish recommendation portrait into a fourth vector;

[0043] The similarity between the third vector and each fourth vector is calculated to determine the dish label corresponding to the fourth vector corresponding to the similarity greater than a preset threshold as the recommended dish name.

[0044] In addition, the present application also provides a data recommendation 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 data recommendation method as described above.

[0045] 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 data recommendation method as described above is implemented.

[0046] To achieve the above objective, according to another aspect of the embodiments of the present application, a computer program product is provided.

[0047] A computer program product according to an embodiment of the present application includes a computer program, and when the program is executed by a processor, the data recommendation method provided by the embodiment of the present application is implemented.

[0048] An embodiment of the above invention has the following advantages or beneficial effects: the present application jumps to the login page in response to the user scanning the graphic code, and displays the online ordering page in response to the user successfully logging in; obtains the user identification, and then calls the information acquisition interface according to the user identification to obtain the diagnosis and treatment information; extracts the target field value in the diagnosis and treatment information, matches the target field value with the dish label in the preset dish recommendation portrait to determine the recommended dish name; matches the target field value with the dish label in the preset dish recommendation portrait to determine the recommended dish name, including: matching the diagnosis and treatment result field value and the doctor's advice field value contained in the target field value according to the diagnosis and treatment result field value and the doctor's advice field value according to the diagnosis and treatment result field value; Combine according to the preset priority to obtain the combined field value, convert the combined field value into a high-dimensional vector through word embedding, calculate the similarity between the high-dimensional vector and the vector corresponding to each dish label in the preset dish portrait, and then determine the dish label corresponding to the vector corresponding to the similarity greater than the preset threshold as the recommended dish name, wherein the preset priority is determined according to the character length of the diagnosis and treatment result field value and the doctor's order field value; display the dish name to the user and determine the target dish name according to the user's check operation; in response to the successful order payment, obtain the target address, generate a delivery task according to the target dish name and target address, and send it to the food delivery terminal. Improve the rationality and personalization of data recommendations, and recommend suitable dishes reasonably and personally according to the patient's condition.

[0049] 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

[0050] The accompanying drawings are used to better understand the present application and do not constitute an improper limitation on the present application.

[0051] Figure 1 is a schematic diagram of the main process of a data recommendation method according to an embodiment of the present application;

[0052] Figure 2 is a schematic diagram of the main process of a data recommendation method according to an embodiment of the present application;

[0053] Figure 3 is a system architecture diagram of a data recommendation method according to an embodiment of the present application;

[0054] Figure 4 is a schematic diagram of the overall process of a data recommendation method according to an embodiment of the present application;

[0055] Figure 5 is a schematic diagram of a mapping relationship of a data recommendation method according to an embodiment of the present application;

[0056] Figure 6 is a schematic diagram of main units of a data recommendation device according to an embodiment of the present application;

[0057] Figure 7 is an exemplary system architecture diagram to which the embodiments of the present application can be applied;

[0058] Figure 8 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

[0059] The following is a description 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, and they 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, analysis, use, transmission, storage, and other aspects of the user's personal information involved are in compliance with the provisions of relevant laws and regulations, and are used for legal and reasonable purposes, and are not shared, leaked, or sold outside of these legal uses, and are subject to supervision and management by regulatory authorities. Take necessary measures to prevent illegal access to such personal information, ensure that persons with access to personal information comply with relevant laws and regulations, and ensure the security of personal information. Once such personal information is no longer needed, risks should be minimized by limiting or even prohibiting data collection and / or deleting data.

[0060] 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.

[0061] Figure 1 is a schematic diagram of the main process of the data recommendation method according to an embodiment of the present application, such as Figure 1 As shown, the data recommendation method mainly includes the following steps S101 to S105.

[0062] Step S101, in response to the user scanning the graphic code, jump to the login page, and in response to the user successfully logging in, display the online ordering page.

[0063] In this embodiment, when the executing entity of the data recommendation method (for example, it may be a server at the ordering user end, which may interact with the ordering system, the hospital system, and the printer) detects that the user scans a graphic code (such as a QR code or a barcode) through the ordering user end, it may jump to the login page to prompt the user to log in. When it is detected that the user enters the medical card number corresponding to the patient's medical card on the login page to log in, the hospital patient information interface is called according to the input medical card number. If the information corresponding to the patient's medical card number can be fed back, it means that the login is successful. Otherwise, the login fails. In response to the user's successful login, the online ordering page is displayed for the user to place an order.

[0064] Step S102, obtaining a user identifier, and then calling an information acquisition interface according to the user identifier to obtain diagnosis and treatment information.

[0065] Specifically, the information acquisition interface is called according to the user identifier to obtain medical information, including: information acquisition authority verification is performed according to the user identifier and the information acquisition interface, and in response to the information acquisition authority verification being passed, the information acquisition interface is called to obtain the medical information corresponding to the user identifier.

[0066] The user identifier, for example, may be the user's medical card number. The information acquisition interface (for example, a hospital patient information interface) is called based on the medical card number input by the user to first perform an authorization check. If the authorization check based on the user identifier passes, the information acquisition interface is called to obtain the medical information corresponding to the user identifier, wherein the medical information may include information such as the patient's disease and the doctor's orders.

[0067] Step S103, extract the target field value in the medical information, match the target field value with the dish label in the preset dish recommendation portrait to determine the recommended dish name; match the target field value with the dish label in the preset dish recommendation portrait to determine the recommended dish name, including: combining the medical result field value and the medical advice field value contained in the target field value according to a preset priority to obtain a combined field value, converting the combined field value into a high-dimensional vector through word embedding, calculating the similarity between the high-dimensional vector and the vector corresponding to each dish label in the preset dish portrait, and then determining the dish label corresponding to the vector corresponding to the similarity greater than a preset threshold as the recommended dish name, wherein the preset priority is determined according to the character length of the medical result field value and the medical advice field value.

[0068] In some embodiments, the target field value may include a diagnosis and treatment result field value and a doctor's advice field value. Specifically, the target field value is matched with a dish label in a preset dish recommendation portrait to determine the recommended dish name, including: converting the diagnosis and treatment result field value into a first vector, converting the doctor's advice field value into a second vector; calculating the sum of the first vector and the second vector to obtain a third vector; converting the dish label in the preset dish recommendation portrait into a fourth vector; calculating the similarity between the third vector and each fourth vector, so as to determine the dish label corresponding to the fourth vector corresponding to the similarity greater than a preset threshold as the recommended dish name.

[0069] After converting the diagnosis and treatment result field value and the medical advice field value contained in the target field value into vectors respectively, the cosine similarity is calculated by adding the vectors corresponding to the diagnosis and treatment result field value and the medical advice field value and the vectors corresponding to each dish label in the preset dish recommendation portrait, so as to accurately determine the recommended dish name based on the comparison result of the calculated cosine similarity with the preset threshold.

[0070] In some embodiments, the target field value is matched with the dish label in a preset dish recommendation portrait to determine the recommended dish name, including: combining the diagnosis and treatment result field value and the medical advice field value contained in the target field value according to a preset priority to obtain a combined field value, converting the combined field value into a high-dimensional vector through word embedding, calculating the similarity between the high-dimensional vector and the vector corresponding to each dish label in the preset dish portrait, and then determining the dish label corresponding to the vector corresponding to the similarity greater than a preset threshold as the recommended dish name, wherein the preset priority is determined according to the character length of the diagnosis and treatment result field value and the medical advice field value.

[0071] The combined field value is obtained by first combining the diagnosis and treatment result field value and the doctor's order field value in the target field value according to a preset priority determined based on the character length, and then vector similarity calculation is performed based on the combined field value and each dish label in the preset dish portrait. In this way, the diagnosis and treatment result field value and the doctor's order field value in the target field value in the medical information can be fully utilized, so that the semantics expressed by the combined field value is more precise, and the recommended dish name finally determined based on the vector similarity is more accurate.

[0072] Step S104, displaying the dish names to the user and determining the target dish name according to the user's check operation.

[0073] After determining the name of the dish to be recommended to the user, the execution entity can display the recommended dish name to the user and obtain the user's check operation on the optional box corresponding to the displayed dish name, and determine the dish name selected by the user, that is, the target dish name, based on the check operation.

[0074] Step S105, in response to successful order payment, the target address is obtained, and a delivery task is generated according to the target dish name and the target address and sent to the food delivery terminal.

[0075] After determining the name of the target dish selected by the user, the execution entity can prompt the user to pay the order, for example, remind the user of the remaining time for order payment, and detect in real time whether the user has successfully paid. When it is detected that the user's order payment is successful, the detailed delivery address associated with the successfully paid order, that is, the target address, can be obtained. The target address can be found based on the maintained binding relationship between the order QR code and the bed. A delivery task is generated based on the target dish name and the target address, and the delivery task is sent to the meal delivery terminal, which assigns it to the deliveryman to deliver the meal to the bed. The embodiment of the present application solves the problem of patient dietary health. By linking the patient's condition and intelligently recommending dishes to the patient, the patient can intuitively view the relationship between his or her personal condition and diet, thereby avoiding the occurrence of situations such as worsening of the patient's condition due to eating the wrong food.

[0076] In this embodiment, in response to the user scanning the graphic code, the user jumps to the login page, and in response to the user successfully logging in, the online ordering page is displayed; the user identification is obtained, and then the information acquisition interface is called according to the user identification to obtain the diagnosis and treatment information; the target field value in the diagnosis and treatment information is extracted, and the target field value is matched with the dish label in the preset dish recommendation portrait to determine the recommended dish name; the dish name is displayed to the user and the target dish name is determined according to the user's check operation; in response to the order payment being successful, the target address is obtained, and according to the target dish name and target address, a delivery task is generated and sent to the food delivery terminal. The rationality and personalization of data recommendations are improved, and suitable dishes can be reasonably and personalized recommended according to the patient's condition.

[0077] Figure 2 is a schematic diagram of the main flow of a data recommendation method according to an embodiment of the present application. Figure 2 As shown, the data recommendation method mainly includes the following steps S201 to S206.

[0078] Step S201, in response to the user scanning the graphic code, jump to the login page, in response to the user successfully logging in, obtain the service channel identifier corresponding to the service channel used by the user, and display the corresponding online ordering page based on the service channel identifier.

[0079] After detecting that the user scans the graphic code to jump to the login page and the user logs in successfully, the executing entity can obtain the service channel identifier of the service channel used by the user. Since different service channels correspond to different online ordering pages, the executing entity can display the personalized online ordering page of the service channel used by the user according to the service channel identifier, so as to improve the rationality and personalization of data recommendations and realize reasonable and personalized recommendations of suitable dishes based on the patient's condition.

[0080] Step S202, obtaining a user identifier, and then calling an information acquisition interface according to the user identifier to obtain diagnosis and treatment information.

[0081] The executing entity can call the information acquisition interface to perform authority verification based on the obtained user ID, and only obtain the corresponding diagnosis and treatment information after the authority verification is passed to ensure the security of user information.

[0082] Step S203, extracting the diagnosis and treatment result field value and the medical advice field value in the diagnosis and treatment information, and combining the diagnosis and treatment result field value with the medical advice field value to obtain a combined field value.

[0083] Step S204, performing similarity matching between the combined field value and the dish label in the preset dish recommendation portrait, so as to determine the dish label corresponding to the similarity greater than the preset threshold as the recommended dish name.

[0084] The combined field value is obtained by first combining the diagnosis and treatment result field value and the doctor's order field value in the diagnosis and treatment information, and then the combined field value is input into the semantic extraction model to output semantic data corresponding to the combined field value. The semantic data is matched with the dish label in the preset dish recommendation portrait by cosine similarity, so as to determine the dish label corresponding to the similarity greater than the preset threshold as the recommended dish name, thereby improving the accuracy of determining the recommended dish name and thus improving the rationality of data recommendation.

[0085] Step S205, displaying the dish names to the user and determining the target dish name according to the user's check operation.

[0086] The executing entity can display the recommended dishes and dish names to the user in the form of dynamic pictures, and obtain the user's check operation data. If it is detected that the number of recommended dishes checked by the user exceeds the preset threshold, a pop-up window can be displayed to remind the user so that the user can correct the wrong selected dishes in time. When the user has made a check operation and has not made another check operation within a preset time period, the executing entity can confirm that the user has selected the dish, and determine the name of the dish checked at this time as the target dish name, thereby strengthening the interaction with the user when selecting dishes, assisting the user in choosing suitable dishes, improving the rationality and personalization of data recommendations, and reasonably and personally recommending suitable dishes based on the patient's condition.

[0087] Step S206, in response to successful payment of the order, the target address is obtained, and a delivery task is generated according to the target dish name and the target address and sent to the food delivery terminal.

[0088] After determining the name of the target menu, the executing entity can remind the user through voice or pop-up window that they need to pay for the order, and inform the user of the order payment methods they can choose, such as pay now and then, credit card payment, bank card payment, etc., so that the user can flexibly choose payment. When the order payment is detected to be successful, the target address is obtained, and based on the target dish name and target address, a delivery task is generated and sent to the delivery terminal to promptly assign a delivery person to deliver the meal to the bed.

[0089] Figure 3 1 is a system architecture diagram of a data recommendation method according to an embodiment of the present application. The data recommendation method of the embodiment of the present application relates to an online ordering system and a hospital system. Figure 3 As shown in the figure, the online ordering system interacts with C-end users (referring to the end users who purchase and use products or services) and management users. Among them, C-end users include employees and patients, and management users include medical users, logistics users, and financial users. Users can interact with the online ordering system through service channels (such as website channels, which can manage backend websites; WeChat channels: ordering H5; Alipay channels: ordering H5; customers' own channels: mini programs, APPs, and public accounts). The online ordering system includes a basic layer, a data layer, and an application support layer, which can provide application services to users. The online ordering system complies with the standard specification system. The basic layer provides servers, storage, networks, security and other infrastructure environments; the data layer stores financial databases, data warehouses, and identity databases; the application support layer is equipped with financial data centers, data resource centers, and information management centers; the application services of the online ordering system include ordering management modules and hospital linkage modules. The ordering management module can realize dish management, dish publishing, dish label management, meal management, classification management, ordering report management, stall management, recipe management, and printer management. The hospital linkage module can realize patient information management, bed ordering code management, patient login management, patient dish management, diagnosis and treatment information management, and nutritional analysis management. The online ordering system interacts with the hospital system that complies with the security system through the external connection adaptation layer. The hospital system stores disease information, patient information, diagnosis and treatment information, and bed information.

[0090] For example, the online ordering system includes an ordering management module and a hospital linkage module. Ordering management module: responsible for the management of online dishes, including stall information management, dish management, meal management, dish label management, and various report management. Hospital linkage module: responsible for two major relationship management: the relationship between dishes and diseases, such as binding hypertension with foods rich in trace elements such as potassium, magnesium, and calcium, such as kelp, seaweed, celery, etc.; diabetes with low-sugar, low-fat, and high-fiber foods, such as coarse grains, vegetables, and fruits; relationship management between ordering QR codes and beds: each ordering QR code is bound to each bed, and the information of each bed includes a specific location, such as 1201, Building 1, Building 5, Inpatient Department. After the patient scans a certain ordering code to place an order, the background can know the specific bed number for delivery. Hospital system: provides disease information, patient information, diagnosis and treatment information, and bed information to the ordering system. Based on the linkage between the online ordering system and the hospital system, when hospital patients order online, the ordering system can intelligently recommend dishes that meet the patient's condition to the patient.

[0091] Figure 4 FIG. 1 is a schematic diagram of the overall process of a data recommendation method according to an embodiment of the present application. Figure 4 As shown, (1) the hospital disease database information is called through the hospital system, and the disease database information is stored in the ordering system (in this embodiment of the application, it can be Figure 3 (2) maintaining the relationship between diseases and dishes, such as Figure 5As shown, diseases - gastroenteritis (dish label: rich in protein (dish name: lean meat, steamed sea bass, steamed egg), liquid food (millet porridge, chicken soup)), hypertension (dish label: rich in trace elements (dish name: kelp, seaweed, celery)), coronary heart disease (dish label: rich in trace elements (dish name: kelp, seaweed, celery)), diabetes - (dish label: low sugar (dish name: fried cucumber with lean meat, fried broccoli)); (3) call the hospital bed information through the hospital system and save the bed information in the ordering system ; (4) Maintain the relationship between the ordering code and the bed. Create an ordering QR code in the ordering system background and bind it to the bed number. The corresponding bed address can be found according to the ordering QR code, for example: ordering QR code-bed number-bed 1, room 1305, 13th floor, building A, inpatient department; (5) Maintain and publish food information for patients to order online; (6) Users scan the ordering QR code through the ordering user terminal to enter the login page of the ordering system; (7) The user (who can be a patient) enters the medical card number corresponding to the patient's medical card on the login page to log in (8) Call the hospital patient information interface according to the input medical card number. If the information corresponding to the patient's medical card number can be fed back, it means that the login is successful, otherwise the login fails; (9) After the user logs in successfully, enter the online ordering page to order online; (10) Call the hospital patient medical information acquisition interface according to the medical card number to obtain the hospital patient medical information, such as the patient's condition and other medical information, which can be the patient's disease and doctor's advice; (11) According to the maintained relationship between the disease and the dish and the patient's medical information returned by the hospital, The system uses the information to find dishes that are suitable for the patient's condition. For example, if the disease listed in the patient Zhang San's medical information is diabetes, based on the relationship between the disease and dishes maintained in the ordering system, it can be found that the recommended dishes for diabetes are stir-fried cucumber with lean meat and stir-fried broccoli; (12) Dishes that match the patient's condition are recommended; (13) The user successfully pays; (14) The order information is sent to the printer. The order information includes the specific address of the bed to be delivered. The address can be found based on the maintained binding relationship between the ordering QR code and the bed; (15) The delivery person delivers the meal to the bed.

[0092] The embodiments of the present application solve the problem of dietary health of patients. By linking with the patient's condition and intelligently recommending dishes to the patient, the patient can intuitively view the relationship between his or her personal condition and diet, thus avoiding the occurrence of situations such as worsening of the patient's condition due to eating the wrong food.

[0093] Figure 6 is a schematic diagram of the main units of the data recommendation device according to an embodiment of the present application. Figure 6 As shown, the data recommendation device 600 includes a login unit 601 , an acquisition unit 602 , a matching unit 603 , a target dish name determination unit 604 and a sending unit 605 .

[0094] The login unit 601 is configured to jump to the login page in response to the user scanning the graphic code, and to display the online ordering page in response to the user successfully logging in.

[0095] The acquisition unit 602 is configured to acquire a user identifier, and then call an information acquisition interface according to the user identifier to acquire diagnosis and treatment information.

[0096] The matching unit 603 is configured to extract the target field value in the medical information, match the target field value with the dish label in the preset dish recommendation portrait to determine the recommended dish name; match the target field value with the dish label in the preset dish recommendation portrait to determine the recommended dish name, including: combining the medical result field value and the medical advice field value contained in the target field value according to a preset priority to obtain a combined field value, converting the combined field value into a high-dimensional vector through word embedding, calculating the similarity between the high-dimensional vector and the vector corresponding to each dish label in the preset dish portrait, and then determining the dish label corresponding to the vector corresponding to the similarity greater than a preset threshold as the recommended dish name, wherein the preset priority is determined according to the character length of the medical result field value and the medical advice field value.

[0097] The target dish name determination unit 604 is configured to display the dish name to the user and determine the target dish name according to the user's check operation.

[0098] The sending unit 605 is configured to obtain the target address in response to successful order payment, generate a delivery task according to the target dish name and the target address, and send it to the food delivery terminal.

[0099] In some embodiments, the login unit 601 is further configured to: obtain a service channel identifier corresponding to the service channel used by the user, and display a corresponding online ordering page based on the service channel identifier.

[0100] In some embodiments, the acquisition unit 602 is further configured to: perform information acquisition authority verification based on the user identifier and the information acquisition interface, and in response to the information acquisition authority verification being passed, call the information acquisition interface to acquire the diagnosis and treatment information corresponding to the user identifier.

[0101] In some embodiments, the matching unit 603 is further configured to extract the diagnosis and treatment result field value and the medical advice field value in the diagnosis and treatment information.

[0102] In some embodiments, the matching unit 603 is further configured to: combine the diagnosis and treatment result field value with the medical advice field value to obtain a combined field value; perform similarity matching between the combined field value and the dish label in the preset dish recommendation portrait to determine the dish label corresponding to the similarity greater than a preset threshold as the recommended dish name.

[0103] In some embodiments, the matching unit 603 is further configured to: convert the diagnosis and treatment result field value into a first vector, and convert the medical advice field value into a second vector; calculate the sum of the first vector and the second vector to obtain a third vector; convert the dish label in the preset dish recommendation portrait into a fourth vector; calculate the similarity between the third vector and each fourth vector, so as to determine the dish label corresponding to the fourth vector corresponding to the similarity greater than a preset threshold as the recommended dish name.

[0104] It should be noted that the data recommendation method and the data recommendation device of the present application have a corresponding relationship in terms of specific implementation contents, so the repeated contents will not be described again.

[0105] Figure 7 An exemplary system architecture 700 to which the data recommendation method or data recommendation device according to the embodiments of the present application can be applied is shown.

[0106] like Figure 7 As shown, system architecture 700 may include terminal devices 701, 702, 703, network 704 and server 705. Network 704 is used to provide a medium for communication links between terminal devices 701, 702, 703 and server 705. Network 704 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0107] Users can use terminal devices 701, 702, and 703 to interact with server 705 through network 704 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 701, 702, and 703, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only examples).

[0108] The terminal devices 701 , 702 , and 703 may be various electronic devices having a data recommendation processing screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0109] Server 705 can be a server that provides various services, such as a background management server that provides support when a user scans a graphic code using terminal devices 701, 702, and 703 (only as an example). The background management server can jump to the login page in response to the user scanning the graphic code, and display the online ordering page in response to the user successfully logging in; obtain the user ID, and then call the information acquisition interface according to the user ID to obtain medical information; extract the target field value in the medical information, match the target field value with the dish label in the preset dish recommendation portrait to determine the recommended dish name; match the target field value with the dish label in the preset dish recommendation portrait to determine the recommended dish name, including: grouping the medical result field value and the doctor's advice field value contained in the target field value according to the preset priority; Combine to obtain the combined field value, convert the combined field value into a high-dimensional vector through word embedding, calculate the similarity between the high-dimensional vector and the vector corresponding to each dish label in the preset dish portrait, and then determine the dish label corresponding to the vector corresponding to the similarity greater than the preset threshold as the recommended dish name, wherein the preset priority is determined according to the character length of the diagnosis and treatment result field value and the doctor's order field value; display the dish name to the user and determine the target dish name according to the user's check operation; in response to the successful order payment, obtain the target address, generate a delivery task according to the target dish name and target address, and send it to the food delivery terminal. Improve the rationality and personalization of data recommendations, and recommend suitable dishes reasonably and personally according to the patient's condition.

[0110] It should be noted that the data recommendation method provided in the embodiment of the present application is generally executed by the server 705 , and accordingly, the data recommendation device is generally arranged in the server 705 .

[0111] It should be understood that Figure 7 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.

[0112] Reference below Figure 8 , which shows a schematic diagram of the structure of a computer system 800 of a terminal device suitable for implementing an embodiment of the present application. Figure 8 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.

[0113] like Figure 8As shown, the computer system 800 includes a central processing unit (CPU) 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage part 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the computer system 800 are also stored. The CPU 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0114] The following components are connected to the I / O interface 805: an input section 806 including a keyboard, a mouse, etc.; an output section 807 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 808 including a hard disk, etc.; and a communication section 809 including a network interface card such as a LAN card, a modem, etc. The communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to the I / O interface 805 as needed. A removable medium 811, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 810 as needed, so that a computer program read therefrom is installed into the storage section 808 as needed.

[0115] 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 includes a 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 809, and / or installed from the removable medium 811. When the computer program is executed by the central processing unit (CPU) 801, the above-mentioned functions defined in the system of the present application are executed.

[0116] 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, in which a computer-readable program code is carried. 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.

[0117] 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.

[0118] 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 login unit, an acquisition unit, a matching unit, a target dish name determination unit, and a sending unit. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0119] 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 jumps to the login page in response to the user scanning the graphic code, and displays the online ordering page in response to the user successfully logging in; obtains the user ID, and then calls the information acquisition interface according to the user ID to obtain the diagnosis and treatment information; extracts the target field value in the diagnosis and treatment information, and matches the target field value with the dish label in the preset dish recommendation portrait to determine the recommended dish name; matches the target field value with the dish label in the preset dish recommendation portrait to determine the recommended dish name, including: matching the diagnosis and treatment results contained in the target field value The field value and the doctor's order field value are combined according to a preset priority to obtain a combined field value, the combined field value is converted into a high-dimensional vector through word embedding, the high-dimensional vector is similarly calculated with the vector corresponding to each dish label in the preset dish portrait, and then the dish label corresponding to the vector corresponding to the similarity greater than a preset threshold is determined as the recommended dish name, wherein the preset priority is determined according to the character length of the diagnosis and treatment result field value and the doctor's order field value; the dish name is displayed to the user and the target dish name is determined according to the user's check operation; in response to a successful order payment, the target address is obtained, and a delivery task is generated according to the target dish name and the target address and sent to the food delivery terminal.

[0120] The computer program product of the present application includes a computer program, and when the computer program is executed by a processor, the data recommendation method in the embodiment of the present application is implemented.

[0121] According to the technical solution of the embodiment of the present application, the rationality and personalization of data recommendation can be improved, and suitable dishes can be reasonably and personally recommended according to the patient's condition.

[0122] 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 data recommendation method, characterized in that: include: In response to the user scanning the graphic code, jumping to the login page, and in response to the user successfully logging in, displaying the online ordering page; Obtaining a user identifier, and then calling an information acquisition interface according to the user identifier to obtain diagnosis and treatment information; Extracting the target field value in the diagnosis and treatment information, and matching the target field value with the dish label in the preset dish recommendation portrait to determine the recommended dish name; The matching of the target field value with the dish label in the preset dish recommendation portrait to determine the recommended dish name includes: combining the diagnosis and treatment result field value and the doctor's advice field value contained in the target field value according to a preset priority to obtain a combined field value, converting the combined field value into a high-dimensional vector through word embedding, performing similarity calculation between the high-dimensional vector and the vector corresponding to each dish label in the preset dish portrait, and then determining the dish label corresponding to the vector corresponding to the similarity greater than a preset threshold as the recommended dish name, wherein the preset priority is determined according to the character length of the diagnosis and treatment result field value and the doctor's advice field value; Displaying the dish name to the user and determining the target dish name according to the user's selection operation; In response to successful order payment, the target address is obtained, and a delivery task is generated and sent to the food delivery terminal based on the target dish name and the target address.

2. The method according to claim 1, characterized in that The online ordering page includes: A service channel identifier corresponding to the service channel used by the user is obtained, and a corresponding online ordering page is displayed based on the service channel identifier.

3. The method according to claim 1, characterized in that The calling of the information acquisition interface according to the user identifier to acquire diagnosis and treatment information includes: The information acquisition authority verification is performed according to the user identification and the information acquisition interface. In response to the information acquisition authority verification being passed, the information acquisition interface is called to acquire the diagnosis and treatment information corresponding to the user identification.

4. The method according to claim 1, characterized in that The extracting the target field value in the diagnosis and treatment information includes: Extract the diagnosis and treatment result field value and the medical advice field value in the diagnosis and treatment information.

5. The method according to claim 4, characterized in that The step of matching the target field value with a dish label in a preset dish recommendation portrait to determine a recommended dish name includes: Combining the diagnosis and treatment result field value with the medical advice field value to obtain a combined field value; The combined field value is matched with the dish label in the preset dish recommendation portrait for similarity, so as to determine the dish label corresponding to the similarity greater than the preset threshold as the recommended dish name.

6. The method according to claim 4, characterized in that The step of matching the target field value with a dish label in a preset dish recommendation portrait to determine a recommended dish name includes: Convert the diagnosis and treatment result field value into a first vector, and convert the medical advice field value into a second vector; Calculating the sum of the first vector and the second vector to obtain a third vector; Convert the dish label in the preset dish recommendation portrait into a fourth vector; The similarity between the third vector and each of the fourth vectors is calculated to determine the dish label corresponding to the fourth vector corresponding to the similarity greater than a preset threshold as the recommended dish name.

7. A data recommendation device, characterized in that: include: A login unit, configured to jump to a login page in response to a user scanning a graphic code, and to display an online ordering page in response to a successful user login; an acquisition unit, configured to acquire a user identifier, and then call an information acquisition interface according to the user identifier to acquire diagnosis and treatment information; a matching unit configured to extract a target field value in the diagnosis and treatment information, and match the target field value with a dish label in a preset dish recommendation portrait to determine a recommended dish name; The matching of the target field value with the dish label in the preset dish recommendation portrait to determine the recommended dish name includes: combining the diagnosis and treatment result field value and the doctor's advice field value contained in the target field value according to a preset priority to obtain a combined field value, converting the combined field value into a high-dimensional vector through word embedding, performing similarity calculation between the high-dimensional vector and the vector corresponding to each dish label in the preset dish portrait, and then determining the dish label corresponding to the vector corresponding to the similarity greater than a preset threshold as the recommended dish name, wherein the preset priority is determined according to the character length of the diagnosis and treatment result field value and the doctor's advice field value; a target dish name determining unit, configured to display the dish name to the user and determine the target dish name according to the user's ticking operation; The sending unit is configured to obtain a target address in response to successful order payment, generate a delivery task according to the target dish name and the target address, and send the task to the food delivery terminal.

8. The device according to claim 7, characterized in that The login unit is further configured to: A service channel identifier corresponding to the service channel used by the user is obtained, and a corresponding online ordering page is displayed based on the service channel identifier.

9. The device according to claim 7, characterized in that The acquisition unit is further configured to: The information acquisition authority verification is performed according to the user identification and the information acquisition interface. In response to the information acquisition authority verification being passed, the information acquisition interface is called to acquire the diagnosis and treatment information corresponding to the user identification.

10. The device according to claim 7, characterized in that The matching unit is further configured to: Extract the diagnosis and treatment result field value and the medical advice field value in the diagnosis and treatment information.

11. The device according to claim 10, characterized in that The matching unit is further configured to: Combining the diagnosis and treatment result field value with the medical advice field value to obtain a combined field value; The combined field value is matched with the dish label in the preset dish recommendation portrait for similarity, so as to determine the dish label corresponding to the similarity greater than the preset threshold as the recommended dish name.

12. The device according to claim 10, characterized in that The matching unit is further configured to: Convert the diagnosis and treatment result field value into a first vector, and convert the medical advice field value into a second vector; Calculating the sum of the first vector and the second vector to obtain a third vector; Convert the dish label in the preset dish recommendation portrait into a fourth vector; The similarity between the third vector and each of the fourth vectors is calculated to determine the dish label corresponding to the fourth vector corresponding to the similarity greater than a preset threshold as the recommended dish name.

13. A data recommendation electronic device, 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 6.

14. 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 6 is implemented.

15. 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 6 is implemented.

Images