Science popularization knowledge recommendation method and system based on bidirectional health manager and user

Abstract

The invention provides a science popularization knowledge recommendation method and system based on bidirectional health manager and user. The method comprises the following steps: acquiring a first science popularization knowledge recommendation content set to which a user should pay attention and a second science popularization knowledge recommendation content set to which the user actually pay attention; based on the first and second popular science knowledge recommendation content sets, performing similarity calculation to obtain a health manager and user attention matching degree; when the matching degree is greater than a set threshold value, performing attention ranking on the contents in the two content sets, filtering out the contents which are ranked in the later set positions in the second popular science knowledge content set, and equivalently replacing the contents which are ranked in the front set positions in the first popular science knowledge content set; when the matching degree is smaller than or equal to a set threshold value, the HIS information is obtained again, a first popular science knowledge recommendation content set which the latest user should pay attention to is obtained, and the content to be recommended is obtained. According to the method, the matching degree of the bidirectional recommendation contents of the health manager and the user is calculated to recommend the popular science knowledge, so that the prognosis rate can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing and recommendation algorithms, and in particular to a method and system for recommending popular science knowledge based on a two-way communication between health managers and users, as well as a corresponding computer terminal and computer-readable storage medium. Background Art

[0002] With the advancement of computer storage technology, the amount of data has exploded. Data mining technology has emerged to uncover hidden, valuable information and patterns within this vast amount of data. In recommendation algorithms, data mining is used to collect and preprocess user and product data. Furthermore, with the embedding of knowledge graphs, these graphs contain various entities (such as users, items, and concepts) and the relationships between them. By analyzing these relationship paths, we can discover potential connections between different entities, thereby implementing personalized recommendation algorithm models.

[0003] (1) When traditional recommendation algorithms recommend popular science knowledge to users of home health management, they often only extract features based on HIS information and make algorithmic recommendations. They ignore the user's external semantic information. Therefore, in the user home health management scenario, recommendation algorithms based on the user's HIS information attention often recommend content that the user should pay attention to, while ignoring the content that the user wants to pay attention to. The proportion of the recommendation algorithm comes from the health manager, resulting in users not being interested in the recommended content, which loses the meaning of popular science knowledge recommendation.

[0004] (2) In the scenario of user home health management, there is a deviation between the content that the health manager should pay attention to after guiding the user to manage his home health and the content that the user actually pays attention to. It is impossible to effectively track and discover this phenomenon, and it is impossible to eliminate the user's various concerns about the health management plan in a timely manner. Summary of the Invention

[0005] In view of the above-mentioned deficiencies in the prior art, the present invention provides a method and system for recommending popular science knowledge based on a two-way communication between health managers and users, and also provides a corresponding computer terminal and computer-readable storage medium.

[0006] According to one aspect of the present invention, a method for recommending popular science knowledge based on a two-way communication between health managers and users is provided, comprising:

[0007] Based on the user's HIS information, obtain the first set of recommended popular science knowledge that the user should pay attention to;

[0008] Based on the user's home health management behavior, obtain the second set of recommended popular science knowledge that the user is actually interested in;

[0009] Based on the first popular science knowledge recommendation content set and the second popular science knowledge recommendation content set, perform similarity calculation to obtain the matching degree between the health manager and the user's concerns;

[0010] When the matching degree between the health manager and the user's concerns is greater than the set threshold, use the second popular science knowledge recommendation content set as the main recommended content, sort the content in both content sets in descending order of attention, filter out the content ranked in the last few positions in the second popular science knowledge content set, and replace it equally with the content ranked in the first few positions in the first popular science knowledge content set to obtain the content to be recommended;

[0011] When the matching degree between the health manager and the user's concerns is less than or equal to the set threshold, re-obtain the HIS information through follow-up, and obtain the latest first popular science knowledge recommendation content set that the user should pay attention to according to the new HIS information; repeat the process of obtaining the matching degree between the health manager and the user's concerns and replacing the content in the second popular science knowledge recommendation content set to obtain the content to be recommended.

[0012] According to another aspect of the present invention, a popular science knowledge recommendation system based on the two-way attention between the health manager and the user is provided, including:

[0013] A recommended content construction module, which obtains the first popular science knowledge recommendation content set that the user should pay attention to based on the user's HIS information; and obtains the second popular science knowledge recommendation content set that the user actually pays attention to based on the user's home health management behavior;

[0014] A concern matching degree calculation module, which performs similarity calculation based on the first popular science knowledge recommendation content set and the second popular science knowledge recommendation content set to obtain the matching degree between the health manager and the user's concerns;

[0015] A content-to-be-recommended generation module, which is used to use the second popular science knowledge recommendation content set as the main recommended content when the matching degree between the health manager and the user's concerns is greater than the set threshold, sort the content in both content sets in descending order of attention, filter out the content ranked in the last few positions in the second popular science knowledge content set, and replace it equally with the content ranked in the first few positions in the first popular science knowledge content set to obtain the content to be recommended; when the matching degree between the health manager and the user's concerns is less than or equal to the set threshold, re-obtain the HIS information through follow-up, and obtain the latest first popular science knowledge recommendation content set that the user should pay attention to according to the new HIS information.

[0016] According to a third aspect of the present invention, a computer terminal is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the terminal can be used to execute any one of the methods described above in the present invention, or to execute any one of the systems described above in the present invention.

[0017] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, it can be used to perform any of the above methods of the present invention, or to run any of the above systems of the present invention.

[0018] Due to the adoption of the above technical solution, the present invention has at least one of the following beneficial effects compared with the prior art:

[0019] The present invention provides a method and system for recommending scientific knowledge based on a two-way interaction between health managers and users. This method is designed for recommending scientific knowledge to users after they have completed home health management. By using user HIS information and user behavior information, the system calculates whether the health manager and user attention are in a two-way match. If a match occurs, the system enhances the recommended content. If a match does not occur, the system can promptly understand the user's health status and adjust the health management plan to improve the match between the health manager and user attention. This specific scenario of recommending scientific knowledge to hospitalized users after they have completed home health management can more effectively enhance users' home health management.

[0020] The method and system for recommending popular science knowledge based on a two-way communication between health managers and users provided by the present invention add a reinforcement algorithm to the recommendation algorithm. By replacing the content that does not meet the needs of users that the health managers want the users to pay attention to among the content that users pay more attention to, the user's correct focus on health conditions can be strengthened, thereby intelligently and correctly guiding users to pay attention to beneficial popular science knowledge and strengthening the guidance of home health management.

[0021] The method and system for recommending popular science knowledge based on two-way communication between health managers and users provided by the present invention can timely discover whether the medical popular science knowledge that users are concerned about deviates from the expectations of health managers by calculating the two-way attention of health managers and users, and can timely discover the reasons for the deviation through follow-up, thereby improving the user's prognosis rate, improving the user's prognosis, and also improving the user's medication management. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Other features, objects and advantages of the present invention will become more apparent upon reading the detailed description of non-limiting embodiments with reference to the following drawings:

[0023] Figure 1 This is a workflow diagram of a method for recommending popular science knowledge based on two-way communication between health managers and users in one embodiment of the present invention.

[0024] Figure 2 This is a schematic diagram of the component modules of a popular science knowledge recommendation system based on the two-way attention of health managers and users in an embodiment of the present invention.

[0025] Figure 3 This is a flowchart of the working process of a popular science knowledge recommendation method and system based on the two-way interaction between health managers and users in a preferred embodiment of the present invention. Specific embodiments

[0026] The following is a detailed description of the embodiments of the present invention: These embodiments are implemented on the premise of the technical solution of the present invention, and detailed implementation manners and specific operation processes are given. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention.

[0027] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data that have been authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0028] Using a recommendation algorithm to recommend popular science knowledge to users is of great significance. However, traditional recommendation algorithms often only extract features based on HIS information and perform algorithm recommendations, resulting in the recommended content being possibly uninteresting to users, or there being a deviation between the content that users should pay attention to and the content that users actually pay attention to.

[0029] To address the above problems, an embodiment of the present invention provides a popular science knowledge recommendation method based on the two-way interaction between health managers and users. This method calculates the matching degree of the recommended content between health managers and users to recommend popular science knowledge, which helps to improve the prognosis rate.

[0030] Specifically, as Figure 1 shown, the popular science knowledge recommendation method based on the two-way interaction between health managers and users provided by this embodiment can include the following operations:

[0031] S1. Based on the HIS information of the user, obtain the first set of recommended popular science knowledge content that the user should pay attention to;

[0032] S2. Based on the user's home health management behavior, obtain the second set of recommended popular science knowledge content that the user actually pays attention to;

[0033] S3. Based on the first set of recommended popular science knowledge content and the second set of recommended popular science knowledge content, perform similarity calculation to obtain the attention matching degree between the health manager and the user;

[0034] S4: When the matching degree between the health manager and the user's attention is greater than a set threshold, the second popular science knowledge recommendation content set is used as the main recommendation content, and the contents of the two content sets are sorted in descending order of attention. The contents ranked in the second popular science knowledge content set with the set number of digits lower are filtered out, and replaced with the contents ranked in the first popular science knowledge content set with the set number of digits higher, thereby obtaining the content to be recommended;

[0035] S5, when the matching degree between the health manager and the user's attention is less than or equal to the set threshold, the HIS information is re-obtained through follow-up, and the latest first set of popular science knowledge recommended content that the user should pay attention to is obtained based on the new HIS information; S3 and S4 are repeated to obtain the content to be recommended.

[0036] In order to obtain popular science content that the health manager hopes the user will pay attention to, in some preferred embodiments, the above S1, based on the user's HIS information, obtains the first set of recommended popular science content that the user should pay attention to, and may further include the following operations:

[0037] S11, obtaining the user's HIS information, extracting features from the HIS information, and forming feature information;

[0038] S12, based on feature information, uses the knowledge graph algorithm and content tags in the popular science knowledge base to obtain popular science knowledge that users should pay attention to, and constructs the first popular science knowledge recommendation content set.

[0039] In some preferred embodiments, the above S11, HIS information, includes: user information, user health status summary and prescribed drug information.

[0040] In order to obtain popular science content that the user is actually interested in, the above S2, based on the user's home health management behavior, obtains a second set of recommended popular science content that the user is actually interested in, and may further include the following operations:

[0041] S21, obtaining the user's home health management behavior information, extracting features from the home health management behavior information, and forming feature information;

[0042] S22, based on feature information, uses the knowledge graph algorithm and content tags in the popular science knowledge base to obtain the popular science knowledge that users are actually concerned about, and constructs the second popular science knowledge recommendation content set.

[0043] In some preferred implementations, the above-mentioned S21, home health management behavior information, includes: browsing history, consultation content and medication status information.

[0044] In order to obtain the degree of matching between the two different dimensions of attention content, in some preferred embodiments, the above S3, based on the first popular science knowledge content recommendation set and the second popular science knowledge content recommendation set, performs similarity calculation to obtain the matching degree between the health manager and the user's attention content, and may further include the following operations:

[0045] The similarity between each content in the first popular science knowledge recommendation content set and the second popular science knowledge recommendation content set is cross-calculated in the label dimension to obtain the matching degree between the health manager and the user's attention. Specifically: The health manager and the user's attention are obtained through the Jaccard similarity algorithm. The first popular science knowledge recommendation content set that the user should pay attention to is set A, and the second popular science knowledge recommendation content set that the user actually pays attention to is set B. The set of all content labels in set A is taken as A1, and the set of all content labels in set B is taken as B1. Calculate Obtain the matching degree between health managers and user attention.

[0046] In some preferred implementations, the above S4, sorting the contents of the two content sets in descending order of attention, may further include the following operations:

[0047] The angle cosine value calculation method is used to calculate the attention of each content in the content set;

[0048] Sort the content in the content set according to the calculated attention.

[0049] In order to replace the content that does not meet the user's expectations from the health manager among the content with high user attention, the user's focus on health conditions can be strengthened, thereby intelligently and correctly guiding the user to pay attention to useful popular science knowledge. In some preferred embodiments, in the above S4, when the matching degree is greater than the set threshold, the second popular science knowledge recommendation content set is used as the main recommendation content, including:

[0050] Based on the second set of recommended popular science knowledge, a reinforcement algorithm is used to recommend content. The reinforcement algorithm filters and replaces the second set of recommended popular science knowledge. In a specific application example, assuming the second set of recommended popular science knowledge consists of four oncology articles and six cardiovascular science articles, while the first set of recommended popular science knowledge consists of ten oncology articles, then based on the sorting, the six cardiovascular science articles in the second set are replaced with the six oncology articles in the first set, bringing the second set to ten oncology articles. This strengthens the recommendations of popular science knowledge on oncology for users.

[0051] In order to timely detect the deviation between the user's attention and the health manager's expectation and improve the two-way attention matching degree, in some preferred embodiments, in the above S5, when the matching degree is less than or equal to the set threshold, HIS information is re-obtained through follow-up, including:

[0052] When the matching degree is less than or equal to the set threshold N, the health manager is triggered to follow up on the users of home health management, obtain the reasons for the popular science knowledge that the users actually focus on recently and the users' health conditions, generate a follow-up summary and update the users' HIS information.

[0053] Based on the same inventive concept, an embodiment of the present invention further provides a popular science knowledge recommendation system based on the two-way attention degree between the health manager and the user.

[0054] Specifically, as Figure 2 shown, the popular science knowledge recommendation system based on the two-way attention degree between the health manager and the user provided by this embodiment may include the following modules:

[0055] A recommended content construction module, which obtains the first set of recommended popular science knowledge content that the user should focus on based on the user's HIS information; and obtains the second set of recommended popular science knowledge content that the user actually focuses on based on the user's home health management behavior.

[0056] A attention matching degree calculation module, which calculates the similarity based on the first set of recommended popular science knowledge content and the second set of recommended popular science knowledge content to obtain the attention matching degree between the health manager and the user.

[0057] A content to be recommended generation module, which is used to, when the matching degree is greater than the set threshold, use the second set of recommended popular science knowledge content as the main recommended content, sort the content in the two sets of content in descending order of attention degree, filter out the content ranked in the following set number of positions in the second set of popular science knowledge content, and replace it equally with the content ranked in the previous set number of positions in the first set of popular science knowledge content to obtain the content to be recommended; when the matching value is less than or equal to the set threshold, re-obtain the HIS information through follow-up, and obtain the latest first set of recommended popular science knowledge content that the user should focus on according to the new HIS information.

[0058] The following further details the work content to be achieved by the functional modules of the popular science knowledge recommendation system based on the two-way attention degree between the health manager and the user provided in the above embodiments of the present invention.

[0059] As Figure 3 shown, for the popular science knowledge recommendation system based on the two-way attention degree between the health manager and the user provided in the above embodiments of the present invention, the work flow implemented by each functional module specifically includes:

[0060] Recommendation content construction module, which is used to obtain the recommended content set and its recommended knowledge attention. Further, based on the HIS information generated by the attending health manager for the user during hospitalization and the recommendation algorithm based on the medical knowledge graph, the user's recommended popular science knowledge content set A is obtained. Based on the user's browsing and social behavior during hospitalization, and the recommendation algorithm based on the medical knowledge graph, the popular science knowledge content set B that the user is interested in is obtained; where:

[0061] Extract features from the hospitalization information of inpatients: user information, sections, and prescription drug information to form feature information, and calculate the recommended content collection that the user should pay attention to through the knowledge graph algorithm and the content tags in the hospital knowledge base.

[0062] Extract features from the user's home health management behaviors: behavior information such as browsing records, consultation content, and medication conditions to form feature information, and calculate the recommended content collection that the user actually pays attention to through the knowledge graph algorithm and the content tags in the hospital knowledge base.

[0063] Attention matching degree calculation module, which is used to obtain the attention matching degree between the health manager and the user. Further, calculate the similarity of the tags of the popular science knowledge content set A and the popular science knowledge content set B to obtain the specific value of the attention matching degree between the health manager and the user. Where:

[0064] Calculate the similarity of each content in the two recommended content sets in terms of the tag dimension to obtain the matching value of the attention between the health manager and the user.

[0065] To-be-recommended content generation module, when the attention matching degree between the health manager and the user is high, mainly recommend the content that the user pays attention to, sort according to the content attention, filter out the content with a low attention matching degree ranking between the health manager and the user, and replace it equally with the popular science knowledge content recommended by the health manager; when the attention matching degree between the health manager and the user is low, the attending health manager initiates a follow-up visit to understand the specific reasons for the mismatch between the user and the content that the health manager pays attention to, record the user's specific reasons, refine the HIS information according to the follow-up section of the health manager for the user, and recalculate the popular science knowledge content that the user should pay attention to. Where:

[0066] If the specific value of the attention matching degree between the health manager and the user is higher than a certain threshold N, then recommend content according to the enhanced algorithm based on the recommended content that the user actually pays attention to, and use the content with a high attention ranking in the recommended content that the user should pay attention to to replace the content with a low attention ranking in the recommended content that the user actually pays attention to.

[0067] If the specific value of the matching degree between the health manager and the user's concerns is lower than a certain threshold N, it triggers the health manager to conduct a follow-up visit to the home user, asking about the reasons for the content the user has recently been concerned about. After understanding the health condition, a follow-up summary is generated to update the user's HIS information. Based on the updated HIS information, step 1 is re-executed to calculate the latest set of recommended content that the user should be concerned about, thereby improving the matching degree between the health manager and the user's concerns.

[0068] It should be noted that the steps in the method provided by the present invention can be implemented by using the corresponding components in the system, etc. Those skilled in the art can refer to the technical solution of the system to implement the step flow of the method, or refer to the technical solution of the method to implement the composition of the system. That is, the embodiments in the system and the embodiments in the method can be understood as preferred examples of each other and will not be elaborated here.

[0069] An embodiment of the present invention also provides a computer terminal, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it can be used to execute the method of any one of the above embodiments of the present invention, or run the system of any one of the above embodiments of the present invention.

[0070] Optionally, the memory is used to store programs; the memory can include volatile memory (English: volatile memory), such as random access memory (English: random-access memory, abbreviation: RAM), such as static random access memory (English: static random-access memory, abbreviation: SRAM), double data rate synchronous dynamic random access memory (English: Double Data Rate Synchronous Dynamic Random Access Memory, abbreviation: DDR SDRAM), etc.; the memory can also include non-volatile memory (English: non-volati le memory), such as flash memory (English: flash memory). The memory is used to store computer programs (such as application programs and functional modules for implementing the above method), computer instructions, etc. The above computer programs, computer instructions, etc. can be stored in one or more memories in a partitioned manner. And the above computer programs, computer instructions, data, etc. can be called by the processor.

[0071] The above computer programs, computer instructions, etc. can be stored in one or more memories in a partitioned manner. And the above computer programs, computer instructions, data, etc. can be called by the processor.

[0072] A processor is configured to execute a computer program stored in a memory to implement each step in the method or each module in the system as described in the above embodiments. For specific details, please refer to the relevant descriptions in the foregoing method and system embodiments.

[0073] The processor and the memory may be of an independent structure or an integrated structure integrated together. When the processor and the memory are of an independent structure, the memory and the processor may be coupled through a bus.

[0074] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it can be used to execute the method of any one of the above embodiments of the present invention, or to run the system of any one of the above embodiments of the present invention.

[0075] Among them, the computer-readable medium includes a computer storage medium and a communication medium. The communication medium includes any medium that facilitates the transmission of a computer program from one place to another. The storage medium may be any available medium that can be accessed by a general-purpose or special-purpose computer. An exemplary storage medium is coupled to the processor, enabling the processor to read information from the storage medium and write information to the storage medium. Of course, the storage medium may also be a component of the processor. The processor and the storage medium may be located in an ASIC. Additionally, the ASIC may be located in a user device. Of course, the processor and the storage medium may also exist as discrete components in a communication device.

[0076] The method and system for recommending popular science knowledge based on the two-way interaction between a health manager and a user provided in the above embodiments of the present invention are applicable to the scenario of recommending popular science knowledge for users' home health management. By using the user's HIS information and user behavior information from two different dimensions, it is calculated whether the attention of the health manager and the user matches bidirectionally. When they match, the recommended content is strengthened. When they do not match, the user's health condition can be understood in a timely manner, and after adjusting the health management plan, the matching value of the attention of the health manager and the user is increased. For the specific scenario of recommending popular science knowledge for users' home health management, it can more effectively enhance users' home health management. In the recommendation algorithm, by adding a strengthening algorithm, in the content with relatively high user attention, the content that does not meet what the health manager wants the user to focus on is replaced, which can strengthen the user's correct focus on health conditions, thereby realizing the intelligent and correct guidance of users to pay attention to beneficial popular science knowledge and strengthening the guidance of home health management. By calculating the two-way attention of the health manager and the user, it can be timely discovered whether the medical popular science knowledge that the user pays attention to deviates from what the health manager expects. The reason for the deviation can be discovered in a timely manner through follow-up visits, improving the user's prognosis rate, improving the user's prognosis, and also being able to improve the user's medication management.

[0077] Matters not described in detail in the above embodiments of the present invention are all well-known technologies in the art.

[0078] The specific embodiments of the present invention have been described above. It should be understood that the present invention is not limited to the above specific embodiments, and those skilled in the art can make various deformations or modifications within the scope of the claims, which do not affect the essence of the present invention.

Claims

1. A method for recommending popular science knowledge in a two-way manner between health managers and users, characterized in that, Including: Based on the user's HIS information, obtain the first set of recommended popular science knowledge content that the user should pay attention to; Based on the user's home behaviors, obtain the second set of recommended popular science knowledge content that the user actually pays attention to; Based on the first set of recommended popular science knowledge content and the second set of recommended popular science knowledge content, calculate the similarity to obtain the matching degree between the health manager and the user's attention; When the matching degree between the health manager and the user's attention is greater than the set threshold, use the second set of recommended popular science knowledge content as the main recommended content, sort the content in both content sets in descending order of attention, filter out the content ranked in the last set number in the second set of popular science knowledge content, and equally replace it with the content ranked in the first set number in the first set of popular science knowledge content to obtain the content to be recommended; When the matching degree between the health manager and the user's attention is less than or equal to the set threshold, re-obtain the HIS information through follow-up, and obtain the latest first set of recommended popular science knowledge content that the user should pay attention to according to the new HIS information; Repeat the process of obtaining the matching degree between the health manager and the user's attention and replacing the content in the second set of recommended popular science knowledge content to obtain the content to be recommended.

2. The popular science knowledge recommendation method based on two-way interaction between health managers and users according to claim 1, wherein The obtaining of the first set of recommended popular science knowledge content that the user should pay attention to based on the user's HIS information includes: Obtain the user's HIS information, extract features from the HIS information to form feature information; Based on the feature information, use the knowledge graph algorithm and the content tags in the popular science knowledge base to obtain the popular science knowledge that the user should pay attention to, and construct the first set of recommended popular science knowledge content.

3. The popular science knowledge recommendation method based on the two-way interaction between a health manager and a user according to claim 2, wherein, The HIS information includes: user information, a summary of the user's health condition, and the drug information in the prescription.

4. The popular science knowledge recommendation method based on two-way interaction between health managers and users according to claim 1, characterized in that, The obtaining of the second set of recommended popular science knowledge content that the user actually pays attention to based on the user's home health management behaviors includes: Obtain the user's home health management behavior information, extract features from the home health management behavior information to form feature information; Based on the feature information, use the knowledge graph algorithm and the content tags in the popular science knowledge base to obtain the popular science knowledge that the user actually pays attention to, and construct the second set of recommended popular science knowledge content.

5. The popular science knowledge recommendation method based on the two-way interaction between health managers and users according to claim 4, characterized in that, The home health management behavior information includes: browsing records, consultation content, and medication situation information.

6. The popular science knowledge recommendation method based on the two-way interaction between a health manager and a user according to claim 1, wherein, The calculating of the similarity based on the first set of recommended popular science knowledge content and the second set of recommended popular science knowledge content to obtain the matching value of the attention between the health manager and the user includes: Calculate the similarity of each content in the first set of recommended popular science knowledge content and the second set of recommended popular science knowledge content in terms of the label dimension to obtain the matching degree between the health manager and the user's attention; where: The method of calculating the label dimension cross uses the Jaccard similarity algorithm, including: Taking the first popular science knowledge recommendation content set as set A, taking the second popular science knowledge recommendation content set as set B, taking the set of all content tags in set A as A1, taking the set of all content tags in set B as B1, calculate Obtain the matching degree between the health manager and the user's concerns.

7. The popular science knowledge recommendation method based on two-way interaction between health managers and users according to claim 1, wherein, When the matching degree between the health manager and the user's attention is less than or equal to the set threshold, re-obtain the HIS information through follow-up, including: When the attention matching degree between the health manager and the user is less than or equal to the set threshold N, the health manager is triggered to conduct a follow-up visit to the users of home health management, obtain the reasons for the popular science knowledge that the users actually focus on recently and the users' health conditions, generate a follow-up summary and update the users' HIS information.

8. A popular science knowledge recommendation system based on the two-way attention of health managers and users, characterized in that, Including: A recommended content construction module, which obtains the first set of recommended popular science knowledge content that the user should focus on based on the user's HIS information; Based on the user's home health management behavior, obtain the second set of recommended popular science knowledge content that the user actually focuses on; An attention matching degree calculation module, which calculates the similarity based on the first set of recommended popular science knowledge content and the second set of recommended popular science knowledge content, and obtains the attention matching degree between the health manager and the user; A content to be recommended generation module, which is used to, when the attention matching degree between the health manager and the user is greater than the set threshold, use the second set of recommended popular science knowledge content as the main recommended content, sort the content in the two sets of content in descending order of attention, filter out the content ranked in the following set number of positions in the second set of popular science knowledge content, and replace it equally with the content ranked in the previous set number of positions in the first set of popular science knowledge content to obtain the content to be recommended; when the matching value is less than or equal to the set threshold, re-obtain the HIS information through follow-up visits, and obtain the latest first set of recommended popular science knowledge content that the user should focus on according to the new HIS information.

9. A computer terminal, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it can be used to execute the method described in any one of claims 1-7, or, run the system described in claim 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it can be used to execute the method described in any one of claims 1-7, or, run the system described in claim 8.

Images