A behavior analysis and medical service push method and system based on big data

Abstract

The present invention belongs to the field of big data technology, and specifically relates to a method and system for behavior analysis and medical service push based on big data. The method includes: matching each medical service information with a medical service dictionary to obtain characteristic vocabulary of each medical service information; establishing an association network of the medical service dictionary based on the frequency of simultaneous appearance of different characteristic vocabulary of the medical service information; obtaining the credibility of each medical service information based on the scope and clustering of the characteristic vocabulary of each medical service information in the association network of the medical service dictionary; obtaining the positive and negative sentiment indexes of each medical service information based on the emotional vocabulary expression of each medical service information; obtaining the credibility of each medical service noun, and using a collaborative filtering algorithm to obtain the medical service information to be pushed for each user. The present invention improves the information quality and push effectiveness of medical service push using a collaborative filtering algorithm.

Description

Technical Field

[0001] The present invention relates to the field of big data technology. More specifically, the present invention relates to a method and system for behavior analysis and medical service delivery based on big data. Background Art

[0002] With technological advancements and a growing emphasis on health, medical service platforms are gradually developing. These platforms allow people to retrieve relevant medical information, thereby increasing their understanding of medical services related to their own illnesses or those of interest. However, simply accessing the information required through user search requires high levels of retrieval skills and the user must judge the quality of the information obtained. Therefore, combining big data with user behavior analysis and personalized medical service delivery can improve the efficiency of users' access to relevant medical services.

[0003] In order to accurately push relevant information to users, collaborative filtering algorithms are often used to obtain the reception information of users with similar behaviors to the target user and push it to the target user. In related technologies, for example, the Chinese patent document with authorization announcement number CN109582875B discloses a personalized recommendation method and system for online medical education resources, which discloses the use of a content-based collaborative filtering recommendation algorithm to establish a case recommendation model, generate recommendation results for target users, reduce the time spent on active search by target users, and reduce the learning cost of users. The Chinese patent document with authorization announcement number CN118277668B discloses an information push method and system for financial services, which discloses combining a collaborative filtering algorithm to obtain each user's predicted score for each financial service, obtain a financial service recommendation list corresponding to each user, and realize financial service information push.

[0004] In the process of using collaborative filtering algorithms to push medical services, there is a problem of unstable quality of medical service information. Information that can arouse people's emotions often has high popularity, but lacks necessity and professionalism. Therefore, collaborative filtering algorithms may recommend medical service information that does not meet the user's conditions to a large number of people who cannot distinguish medical information, affecting users' acquisition of effective medical service information and even affecting disease treatment. Summary of the Invention

[0005] In order to solve the above-mentioned technical problem of unstable quality of medical service information when using collaborative filtering algorithm to push medical service information, the present invention provides solutions in the following aspects.

[0006] In a first aspect, the present invention provides a method for behavior analysis and medical service delivery based on big data, comprising:

[0007] Establish a medical service dictionary, which contains several disease nouns, several symptom nouns and several medical service nouns; obtain several medical service information; obtain several users' medical service demand sets, each of which is a subset of the medical service dictionary; match each medical service information with the medical service dictionary to obtain characteristic vocabulary of each medical service information; establish an association network of the medical service dictionary based on the frequency of simultaneous appearance of different characteristic vocabulary of the medical service information; obtain the credibility of each medical service information based on the scope and clustering of the characteristic vocabulary of each medical service information in the association network of the medical service dictionary; obtain the positive sentiment index and negative sentiment index of each medical service information based on the emotional vocabulary expression of each medical service information; obtain the credibility of each medical service noun based on the positive sentiment index and negative sentiment index of the medical service information related to each medical service noun and the credibility of the medical service information related to each medical service noun; use a collaborative filtering algorithm to obtain the medical service information to be pushed for each user based on the user's medical service demand set and the credibility of each medical service noun.

[0008] The present invention filters medical service information pushed to users based on credibility, improving the quality and efficiency of medical service information available to users. The present invention uses sentiment vocabulary and medical service-related vocabulary to obtain the effectiveness of medical service information and medical service vocabulary, making the quality judgment of medical service information more accurate, thereby preventing low-quality information from being pushed to users in large quantities through collaborative filtering algorithms.

[0009] Preferably, the establishment of an association network of the medical service dictionary based on the frequency of simultaneous appearance of different characteristic words of the medical service information includes: performing a union operation on the characteristic words of all medical service information to obtain a characteristic word set and characteristic word types of the medical service information; obtaining the correlation between any two characteristic words based on the frequency of simultaneous appearance of different characteristic words of the medical service information; taking the inverse proportional normalization result of the correlation between any two characteristic words as the distance between the two characteristic words in the association network of the medical service dictionary, taking all characteristic words as nodes of the network, and connecting all characteristic words with a distance greater than 0 to obtain the association network of the medical service dictionary.

[0010] The present invention establishes an association network of the medical service dictionary so that the association of medical service-related words can be visually represented, thereby determining the association of each word in the medical service dictionary.

[0011] Preferably, the correlation between any two characteristic words satisfies the expression:

[0012] ;

[0013] Where, Indicates the correlation between the i-th feature vocabulary and the c-th feature vocabulary; 、 represents the number of medical service information containing the i-th characteristic vocabulary and the c-th characteristic vocabulary; represents the number of medical service information containing both the i-th characteristic vocabulary and the c-th characteristic vocabulary; represents the absolute value function; represents the normalization function; Represents an exponential function with a natural constant as its base.

[0014] The present invention obtains the relevance of different characteristic words by the co-occurrence of different characteristic words, thereby ensuring the accuracy of the analysis of the relevance of the characteristic words.

[0015] Preferably, obtaining the credibility of each medical service information includes:

[0016] Obtain the number of words in each medical service information, obtain the number of words in each characteristic word in each medical service information, and obtain the types of characteristic words included in each medical service information;

[0017] ;

[0018] Where, represents the credibility of the a-th medical service information; The word count set representing the characteristic vocabulary of the a-th medical service information; Indicates the number of words in the a-th medical service information; Indicates the type of characteristic words contained in the a-th medical service information; represents the distance between the bth characteristic word and the dth characteristic word contained in the ath medical service information in the association network of the medical service dictionary; Represents an exponential function with a natural constant as its base.

[0019] Preferably, the obtaining of the positive sentiment index and negative sentiment index of each medical service information includes: obtaining a set of sentiment words for each medical service information based on the sentiment word expression of each medical service information; obtaining the sentiment relative relationship of different sentiment words based on a voting mechanism; obtaining the final sentiment degree of each sentiment word based on the sentiment relative relationship of different sentiment words; adding up the final sentiment degrees of all sentiment words whose final sentiment degrees of the a-th medical service information are greater than 0, and recording it as the positive sentiment index of the a-th medical service information; adding up the final sentiment degrees of all sentiment words whose final sentiment degrees of the a-th medical service information are less than 0, and taking the absolute value, and recording it as the negative sentiment index of the a-th medical service information.

[0020] The present invention calculates the positive sentiment index and the negative sentiment index, providing a clear basis for analyzing the emotional expression of medical service information, thereby being able to more accurately obtain the credibility of medical service vocabulary.

[0021] Preferably, the emotional vocabulary set of each medical service information is obtained based on the emotional vocabulary expression of each medical service information, including: using jieba participles to mark the part of speech of each medical service information, obtaining the words with the part of speech of adjective or adverb in each medical service information, and recording them as the emotional vocabulary of each medical service information; performing a union operation on the emotional vocabulary of each medical service information to obtain the emotional vocabulary set of each medical service information.

[0022] Preferably, the voting mechanism is based on obtaining the emotional relative relationship of different emotional words, including: performing a union operation on the emotional words of each medical service information to obtain an emotional word set of each medical service information; setting up a voting mechanism involving several people, for any two emotional words, each person votes for the emotional word that he or she personally thinks is more positive among the two emotional words, and the emotional word with the highest number of votes among the two emotional words is recorded as the relatively positive emotional word among the two emotional words, and the emotional word with the lowest number of votes among the two emotional words is recorded as the relatively negative emotional word among the two emotional words.

[0023] The present invention determines the emotional levels of different emotional words through a voting mechanism, thereby improving the robustness of using emotional word sequences and the accuracy of emotional analysis of medical service information.

[0024] Preferably, the method of obtaining the final emotion degree of each emotion word according to the emotion relative relationship of different emotion words includes: constructing an emotion word degree tree according to the emotion relative relationship of different emotion words, wherein the emotion word degree tree is a binary sorted tree; performing an in-order traversal on the emotion word degree tree to obtain an in-order emotion word sequence; recording the emotion word corresponding to the ordinal median of the in-order emotion word sequence as a neutral emotion word, subtracting the ordinal number of the neutral emotion word from the ordinal number of the u-th emotion word in the in-order emotion word sequence, and then dividing it by the maximum ordinal number of the in-order emotion word sequence, recording it as the final emotion degree of the u-th emotion word.

[0025] Preferably, obtaining the credibility of each medical service noun includes:

[0026] Obtain all medical service information containing the s-th medical service noun, and record it as the relevant medical service information of the s-th medical service noun;

[0027] ;

[0028] Where, represents the credibility of the sth medical service noun; Indicates the number of related medical service information for the sth medical service noun; represents the credibility of the ath related medical service information of the sth medical service noun; 、 represents the positive sentiment index and negative sentiment index of the a-th related medical service information of the s-th medical service noun; represents the absolute value function; Represents an exponential function with a natural constant as its base.

[0029] In the second aspect, the present invention provides a behavior analysis and medical service push system based on big data, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned behavior analysis and medical service push method based on big data is implemented.

[0030] By adopting the above technical solution, the above-mentioned behavior analysis and medical service push method based on big data is generated into a computer program and stored in the memory to be loaded and executed by the processor, so that a terminal device is made based on the memory and the processor for easy use.

[0031] The beneficial effects of the present invention are:

[0032] (1) Based on big data technology, the present invention obtains the credibility of medical service vocabulary through medical service information related to medical service vocabulary, making the acquisition of medical service information quality more accurate, thereby providing a basis for using collaborative filtering algorithms to push accurate medical services to users;

[0033] (2) The final sentiment level of the sentiment vocabulary of the present invention provides a basis for analyzing medical service information from the sentiment aspect, avoiding the problem that the collaborative filtering algorithm may push low-quality medical service information to users. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 is a flow chart schematically illustrating a method for behavior analysis and medical service delivery based on big data in the present invention;

[0035] Figure 2 FIG. 1 is a diagram schematically showing a relational network of a medical service dictionary. DETAILED DESCRIPTION

[0036] The embodiment of the present invention discloses a behavior analysis and medical service push method based on big data, referring to Figure 1 , including steps S1 to S4:

[0037] S1: Establish a medical service dictionary, which includes a number of disease nouns, a number of symptom nouns, and a number of medical service nouns; obtain a number of medical service information; and obtain a set of medical service requirements of a number of users.

[0038] It should be noted that, taking social media platforms as an example, the platform will use a user-based collaborative filtering algorithm to find similar user groups and recommend relevant content based on the preferences of similar users, which can improve user usage of the platform and reduce user retrieval costs. In order to increase the number of visits to pushed content, users who send pushed content often add text that triggers people's emotional changes. However, when it comes to recommending medical service information, more attention needs to be paid to the information quality of medical service information. When low-quality medical service information is expanded by the collaborative filtering algorithm, it is easy to cause the spread of erroneous information. In order to ensure the information quality of medical service push, the present invention first obtains relevant push information of various medical services, and then analyzes the credibility of each medical service information, and finally pushes high-credibility medical service information related to the user to be pushed to the user to be pushed.

[0039] Specifically, a medical service dictionary is manually established, and the medical service dictionary includes a number of disease nouns, a number of symptom nouns, and a number of medical service nouns.

[0040] Obtain some medical service information from content platforms involving medical service push.

[0041] The search records of several users are obtained and segmented using a dictionary-based maximum matching word segmentation algorithm. The dictionary used is a medical service dictionary. Several medical service demand terms for each user are obtained to form each user's medical service demand set. It should be noted that a user's search records may include diseases, symptoms, and medical services, so the user's medical service demand set may include disease nouns, symptom nouns, and medical service nouns.

[0042] At this point, a medical service dictionary, some medical service information, and a set of medical service requirements of several users have been obtained.

[0043] S2: Match each medical service information with the medical service dictionary to obtain the characteristic vocabulary of each medical service information; establish an association network of the medical service dictionary based on the frequency of simultaneous appearance of different characteristic vocabulary of the medical service information; obtain the credibility of each medical service information based on the scope and clustering of the characteristic vocabulary of each medical service information in the association network of the medical service dictionary.

[0044] It should be noted that among all medical service information, due to differences in the medical capabilities of the senders, medical service information also shows differences in quality. In addition, in order to facilitate dissemination, some medical service information contains non-professional terms and non-true content. Therefore, it is necessary to judge the credibility of the obtained medical service information.

[0045] It should be further explained that a disease often has multiple symptoms and multiple medical services. Taking heart disease as an example, medical services include monitoring heartbeats through wearable devices, non-invasive screening, and bypass surgery for multi-vessel lesions. Different medical services respond to different symptoms and have different purposes. Therefore, symptoms and medical services are often correlated. When medical service information contains more descriptions of medical services and there is a correlation between the descriptions of these medical service information, it indicates that the medical service information reflects the correlation between symptoms and medical services and has higher credibility. Therefore, the present invention analyzes the credibility of each medical service information based on the correlation of medical service-related words contained in the medical service information.

[0046] Specifically, each medical service information is matched with a medical service dictionary to obtain characteristic words of each medical service information:

[0047] Each medical service information item is segmented using a dictionary-based maximum matching segmentation algorithm. The resulting vocabulary is recorded as the characteristic vocabulary of the target medical service information. The dictionary used is the medical service dictionary. It should be noted that since the medical service dictionary is used in the segmentation process, all characteristic vocabulary items are included in the medical service dictionary.

[0048] It should be noted that there is a correlation between diseases, symptoms and medical services. For example, antiplatelet drugs are used to prevent the formation of blood clots in heart disease. The characteristic words contained in a medical service information reflect the correlation between diseases, symptoms and medical services. The higher the frequency of two characteristic words appearing simultaneously in all medical service information, the higher the correlation between the two characteristic words. Based on the correlation between characteristic words, the irregular medical service dictionary can be transformed into a network that reflects the relationship between the words in the medical service dictionary.

[0049] Preferably, based on the frequencies of simultaneous occurrence of different characteristic words in medical service information, a correlation network of the medical service dictionary is established:

[0050] A union operation is performed on all characteristic words of the medical service information to obtain a characteristic word set and characteristic word types of the medical service information.

[0051] It should be noted that, the more frequently the i-th characteristic vocabulary and the c-th characteristic vocabulary appear at the same time, and the closer the number of medical service information containing the i-th characteristic vocabulary and the c-th characteristic vocabulary is, the stronger the correlation between the i-th characteristic vocabulary and the c-th characteristic vocabulary.

[0052] The correlation between any two feature words satisfies the expression:

[0053] ;

[0054] Where, Indicates the correlation between the i-th feature vocabulary and the c-th feature vocabulary; 、 represents the number of medical service information containing the i-th characteristic vocabulary and the c-th characteristic vocabulary; represents the number of medical service information containing both the i-th characteristic vocabulary and the c-th characteristic vocabulary; represents the absolute value function; represents the normalization function; Represents an exponential function with a natural constant as its base.

[0055] Where, represents the proportion of medical service information containing the cth type of characteristic vocabulary among the medical service information containing the ith type of characteristic vocabulary; represents the proportion of medical service information containing the i-th characteristic vocabulary among the medical service information containing the c-th characteristic vocabulary; It represents the product of the proportion of the i-th characteristic word and the c-th characteristic word in the medical service information containing the other characteristic word. The larger the value, the greater the proportion of the i-th characteristic word and the c-th characteristic word appearing at the same time. It indicates the difference in the number of medical service information containing the i-th characteristic vocabulary and the c-th characteristic vocabulary. The smaller the value, the closer the number of medical service information containing the i-th characteristic vocabulary and the c-th characteristic vocabulary. At the same time, the greater the proportion of the i-th characteristic vocabulary and the c-th characteristic vocabulary appearing at the same time, the greater the probability that the i-th characteristic vocabulary and the c-th characteristic vocabulary appear at the same time, and therefore the stronger the correlation between the i-th characteristic vocabulary and the c-th characteristic vocabulary.

[0056] The inverse proportional normalization result of the correlation between any two feature words is used as the distance between the two feature words in the association network of the medical service dictionary. All feature words are used as nodes of the network, and all feature words with a distance greater than 0 are connected to obtain the association network of the medical service dictionary.

[0057] At this point, the association network of the medical service dictionary is obtained.

[0058] It should be noted that if Figure 2This is a schematic diagram of the association network of the medical service dictionary. Due to different fields, the association network of the medical service dictionary is often manifested as multiple clustered areas. A clustered area represents medical service-related vocabulary for a disease or a field. Therefore, the more clustered the characteristic vocabulary contained in the medical service information in the association network of the medical service dictionary, and the higher the proportion of the number of characteristic vocabulary in the medical service information, the more professional the medical service information is, and thus the higher its credibility.

[0059] Preferably, the credibility of each medical service information is obtained based on the word count ratio of the characteristic words of each medical service information and the aggregation in the associated network of the medical service dictionary:

[0060] The number of characters in each piece of medical service information is obtained, the number of characters in each characteristic word in each piece of medical service information is obtained, and the types of characteristic words included in each piece of medical service information are obtained.

[0061] The credibility of any medical service information satisfies the expression:

[0062] ;

[0063] Where, represents the credibility of the a-th medical service information; The word count set representing the characteristic vocabulary of the a-th medical service information; Indicates the number of words in the a-th medical service information; Indicates the type of characteristic words contained in the a-th medical service information; represents the distance between the bth characteristic word and the dth characteristic word contained in the ath medical service information in the association network of the medical service dictionary; Represents an exponential function with a natural constant as its base.

[0064] Where, It represents the proportion of the number of characteristic words in the a-th medical service information. The larger the value, the more medical service information is related to medical services, the stronger the relevance, and thus the higher the credibility; It represents the average distance of all characteristic words contained in the a-th medical service information in the association network of the medical service dictionary. The larger the value, the lower the correlation of all characteristic words contained in the a-th medical service information, indicating that the a-th medical service information is not centered around a medical subject, and thus the credibility of the a-th medical service information is lower.

[0065] At this point, the credibility of each medical service information has been obtained.

[0066] S3: Based on the emotional vocabulary expression of each medical service information, obtain the positive emotional index and negative emotional index of each medical service information; according to the positive emotional index and negative emotional index of the medical service information related to each medical service noun, and the credibility of the medical service information related to each medical service noun, obtain the credibility of each medical service noun.

[0067] It's important to note that when conveying accurate medical information, for example, in papers, emotional words like "touched" are often avoided. However, in marketing and promotional contexts, such as advertising, emotional words are often used to increase the likelihood of successful promotion of medical services. Positive emotional words promote the use of medical services, while negative emotional words are used to discourage users from using other medical services. Therefore, the stronger the emotional words in medical information, and the greater the difference between positive and negative emotions, the lower the credibility of the medical information.

[0068] It should be further explained that sentiment words often appear as adjectives and adverbs. Therefore, by obtaining the adjectives and adverbs in the medical service information and performing sentiment tagging, the positive and negative sentiment analysis of the medical service information can be completed. Natural language processing technology can efficiently process text and perform part-of-speech tagging on the text. Therefore, the present invention uses natural language processing technology to extract adjectives and adverbs, and manually sorts the extracted adjectives and adverbs according to their sentiment level, thereby obtaining the positive and negative sentiment indexes of each medical service information based on the sentiment level of all adjectives and adverbs in each medical service information.

[0069] Specifically, based on the sentiment vocabulary representation of each medical service information, the positive sentiment index and negative sentiment index of each medical service information are obtained:

[0070] Jieba is used to perform part-of-speech tagging on each medical service information, and words with adjective or adverb parts of speech in each medical service information are obtained and recorded as sentiment words of each medical service information. It should be noted that Jieba is an existing Chinese word segmentation tool that can perform word segmentation and part-of-speech tagging on text.

[0071] A union operation is performed on the sentiment words of each medical service information to obtain the sentiment word set of each medical service information.

[0072] A voting mechanism involving several people is set up. For any two sentiment words, each person votes for the sentiment word that they personally consider to be more positive. The sentiment word with the highest number of votes among the two sentiment words is recorded as the relatively positive sentiment word among the two sentiment words, and the sentiment word with the lowest number of votes among the two sentiment words is recorded as the relatively negative sentiment word among the two sentiment words. It should be noted that since the emotional level of sentiment words may vary among different people, the voting mechanism can ensure a more accurate analysis of the emotional level of sentiment words.

[0073] Construct an emotional degree function that satisfies the expression:

[0074] ;

[0075] Where, Represents the sentiment degree function of the u-th sentiment word and the v-th sentiment word, f(u) and f(v) represent the relative sentiment degrees of the u-th sentiment word and the v-th sentiment word in the two sentiment words; when the u-th sentiment word is the relatively positive sentiment word between the u-th sentiment word and the v-th sentiment word, f(u) is 1 and f(v) is -1; when the u-th sentiment word is the relatively negative sentiment word between the two sentiment words, f(u) is -1 and f(v) is 1.

[0076] For the set of sentiment words, take the first sentiment word as the root node. If the sentiment degree function of the second sentiment word and the first sentiment word , then place the second sentiment word in the right subtree of the node corresponding to the first sentiment word; if the sentiment degree function of the second sentiment word and the first sentiment word , then place the second sentiment word in the left subtree of the node corresponding to the first sentiment word; and place all sentiment words in sequence to form a binary sorted tree, recorded as the sentiment word degree tree. It should be noted that in the sentiment word degree, the relative sentiment degree of all nodes in the left subtree is less than the value of the root node, and the relative sentiment degree of all nodes in the right subtree is greater than the value of the root node. The sentiment word degree tree is traversed in order, and the resulting in-order sentiment word sequence is a relational sequence with increasing sentiment degree.

[0077] Perform in-order traversal on the sentiment vocabulary degree tree to obtain the in-order sentiment vocabulary sequence.

[0078] The emotional word corresponding to the median of the ordinal number of the mid-order emotional word sequence is recorded as a neutral emotional word. The ordinal number of the u-th emotional word in the mid-order emotional word sequence is subtracted from the ordinal number of the neutral emotional word, and then divided by the maximum ordinal number of the mid-order emotional word sequence to record it as the final emotional degree of the u-th emotional word.

[0079] The final sentiment levels of all sentiment words in the a-th medical service information whose final sentiment levels are greater than 0 are added together, and recorded as the positive sentiment index of the a-th medical service information; the final sentiment levels of all sentiment words in the a-th medical service information whose final sentiment levels are less than 0 are added together, and the absolute value is taken, and recorded as the negative sentiment index of the a-th medical service information.

[0080] At this point, the positive sentiment index and negative sentiment index of each medical service information were obtained.

[0081] It should be noted that the greater the positive sentiment index and negative sentiment index of the medical service information related to the medical service noun, the lower the credibility of the medical service information related to the medical service noun, and thus the lower the credibility of the medical service noun; in addition, considering that the medical service sender will deal with the medical service push with a high negative sentiment index due to interest relations to avoid the spread of bad information, the greater the overall difference between the positive sentiment index and the negative sentiment index in the medical service information related to the medical service noun, the lower the credibility of the medical service noun; at the same time, the lower the overall credibility of the medical service information related to the medical service noun, the lower the credibility of the medical service noun.

[0082] Preferably, the credibility of each medical service noun is obtained based on the positive sentiment index and the negative sentiment index of the medical service information related to each medical service noun and the credibility of the medical service information related to each medical service noun:

[0083] Obtain all medical service information containing the s-th medical service noun, record it as the relevant medical service information of the s-th medical service noun, and obtain the positive sentiment index and negative sentiment index of all the relevant medical service information of the s-th medical service noun.

[0084] The credibility of any medical service noun satisfies the expression:

[0085] ;

[0086] Where, represents the credibility of the sth medical service noun; Indicates the number of related medical service information for the sth medical service noun; represents the credibility of the ath related medical service information of the sth medical service noun; 、 represents the positive sentiment index and negative sentiment index of the a-th related medical service information of the s-th medical service noun; represents the absolute value function; Represents an exponential function with a natural constant as its base.

[0087] Where, It represents the influence of the a-th related medical service information of the s-th medical service noun on the credibility of the s-th medical service noun. The greater the credibility of the a-th related medical service information of the s-th medical service noun, the smaller the positive sentiment index and the negative sentiment index, and the smaller the difference between the positive sentiment index and the negative sentiment index, the greater the influence on the credibility of the s-th medical service noun, making the credibility of the s-th medical service noun greater.

[0088] At this point, the credibility of each medical service term has been obtained.

[0089] S4: Based on the user's medical service demand set and the credibility of each medical service term, a collaborative filtering algorithm is used to obtain the medical service information to be pushed to each user.

[0090] Specifically, any user is designated as the target user. On the associated network of the medical service dictionary, all medical service nouns that can be reached by the vocabulary in the target user's medical service demand set are obtained and recorded as the target user's related medical service nouns. From the related medical service information of the target user's related medical service nouns, the Top-N algorithm is used to obtain the target user's related medical service nouns in descending order of credibility for all the target user's related medical service nouns to be pushed. The target user is then pushed in descending order of all the medical service information to be pushed. It should be noted that the number of medical service information to be pushed selected by the Top-N algorithm, i.e., the value N, is set by the implementer based on actual implementation circumstances. For example, the value N can be set to 3.

[0091] At this point, the medical service push for each user has been completed.

[0092] An embodiment of the present invention also discloses a behavior analysis and medical service push system based on big data, including a processor and a memory, wherein the memory stores computer program instructions. When the computer program instructions are executed by the processor, a behavior analysis and medical service push method based on big data according to the present invention is implemented.

[0093] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface. The configuration and functions of these components are known in the art and will not be described in detail here.

[0094] While several embodiments of the present invention have been shown and described herein, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Numerous modifications, variations, and alternatives will occur to those skilled in the art without departing from the concept and spirit of the present invention. It should be understood that various alternatives to the embodiments of the present invention described herein may be employed in practicing the present invention.

Claims

1. A behavior analysis and medical service push method based on big data, characterized in that: include: Establishing a medical service dictionary, wherein the medical service dictionary includes a number of disease nouns, a number of symptom nouns, and a number of medical service nouns; obtaining a number of medical service information; obtaining a number of user medical service demand sets, wherein the user medical service demand sets are all subsets of the medical service dictionary; Matching each medical service information with a medical service dictionary to obtain characteristic words of each medical service information; Based on the frequency of simultaneous appearance of different characteristic words in medical service information, an association network of a medical service dictionary is established, including: performing a union operation on the characteristic words of all medical service information to obtain a characteristic word set and characteristic word types of the medical service information; obtaining the association between any two characteristic words according to the frequency of simultaneous appearance of different characteristic words in medical service information; using the inverse proportional normalization result of the association between any two characteristic words as the distance between the two characteristic words in the association network of the medical service dictionary, using all characteristic words as nodes of the network, and connecting all characteristic words with a distance greater than 0 to obtain the association network of the medical service dictionary; obtaining the credibility of each medical service information based on the scope and clustering of the characteristic words of each medical service information in the association network of the medical service dictionary, the number of words in each medical service information, the number of words in each characteristic word of each medical service information, and the types of characteristic words contained in each medical service information; The calculation formula for the credibility of medical service information is: ； Where, represents the credibility of the a-th medical service information; The word count set representing the characteristic vocabulary of the a-th medical service information; Indicates the number of words in the a-th medical service information; Indicates the type of characteristic words contained in the a-th medical service information; represents the distance between the bth characteristic word and the dth characteristic word contained in the ath medical service information in the association network of the medical service dictionary; represents an exponential function with a natural constant as its base; Based on the emotional vocabulary expression of each medical service information, the positive emotional index and negative emotional index of each medical service information are obtained, including: according to the emotional vocabulary expression of each medical service information, the emotional vocabulary set of each medical service information is obtained; based on the voting mechanism, the emotional relative relationship of different emotional vocabulary is obtained; according to the emotional relative relationship of different emotional vocabulary, the final emotional degree of each emotional vocabulary is obtained; the final emotional degree of all emotional vocabulary with a final emotional degree greater than 0 of the a-th medical service information is added, and recorded as the positive emotional index of the a-th medical service information; the final emotional degree of all emotional vocabulary with a final emotional degree less than 0 of the a-th medical service information is added, and the absolute value is taken, and recorded as the negative emotional index of the a-th medical service information; according to the positive emotional index and negative emotional index of the medical service information related to each medical service noun, and the credibility of the medical service information related to each medical service noun, the credibility of each medical service noun is obtained, including: obtaining all medical service information containing the s-th medical service noun, and recording it as the relevant medical service information of the s-th medical service noun; ； Where, represents the credibility of the sth medical service noun; Indicates the number of related medical service information for the sth medical service noun; represents the credibility of the ath related medical service information of the sth medical service noun; 、 represents the positive sentiment index and negative sentiment index of the a-th related medical service information of the s-th medical service noun; represents the absolute value function; Based on the user's medical service demand set and the credibility of each medical service term, a collaborative filtering algorithm is used to obtain the medical service information to be pushed to each user.

2. A method for behavior analysis and medical service push based on big data according to claim 1, characterized in that: The correlation between any two feature words satisfies the expression: ； Where, Indicates the correlation between the i-th feature vocabulary and the c-th feature vocabulary; 、 represents the number of medical service information containing the i-th characteristic vocabulary and the c-th characteristic vocabulary; represents the number of medical service information containing both the i-th characteristic vocabulary and the c-th characteristic vocabulary; represents the absolute value function; represents the normalization function; Represents an exponential function with a natural constant as its base.

3. The method for behavior analysis and medical service push based on big data according to claim 1, characterized in that: The step of obtaining the emotional vocabulary set of each medical service information according to the emotional vocabulary expression of each medical service information includes: The medical service information was tagged with the part-of-speech tag using Jieba word segmentation, and the words with the part-of-speech of adjective or adverb in each medical service information were obtained and recorded as the sentiment words of each medical service information; the sentiment words of each medical service information were unioned to obtain the sentiment word set of each medical service information.

4. The method for behavior analysis and medical service push based on big data according to claim 1, characterized in that: The voting mechanism is used to obtain the relative sentiment relationship of different sentiment words, including: Performing a union operation on the sentiment words of each medical service information to obtain a sentiment word set of each medical service information; A voting mechanism involving several people is set up. For any two emotional words, each person votes for the emotional word that he or she thinks is more positive among the two emotional words. The emotional word with the highest number of votes among the two emotional words is recorded as the relatively positive emotional word among the two emotional words, and the emotional word with the lowest number of votes among the two emotional words is recorded as the relatively negative emotional word among the two emotional words.

5. The method for behavior analysis and medical service push based on big data according to claim 1, characterized in that: The method of obtaining the final emotion degree of each emotion word according to the emotion relative relationship of different emotion words includes: According to the relative relationship of emotions among different emotional words, an emotional word degree tree is constructed, wherein the emotional word degree tree is a binary sorted tree; an in-order traversal is performed on the emotional word degree tree to obtain an in-order emotional word sequence; The emotional word corresponding to the median of the ordinal number of the mid-order emotional word sequence is recorded as a neutral emotional word. The ordinal number of the u-th emotional word in the mid-order emotional word sequence is subtracted from the ordinal number of the neutral emotional word, and then divided by the maximum ordinal number of the mid-order emotional word sequence to record it as the final emotional degree of the u-th emotional word.

6. A behavior analysis and medical service push system based on big data, characterized by: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a behavior analysis and medical service push method based on big data according to any one of claims 1 to 5 is implemented.

Images