CN113297489A - Rehabilitation aid recommendation method and device, computer equipment and storage medium - Google Patents
Rehabilitation aid recommendation method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113297489A CN113297489A CN202110593386.1A CN202110593386A CN113297489A CN 113297489 A CN113297489 A CN 113297489A CN 202110593386 A CN202110593386 A CN 202110593386A CN 113297489 A CN113297489 A CN 113297489A
- Authority
- CN
- China
- Prior art keywords
- rehabilitation
- aid
- determining
- text
- rehabilitation aid
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 31
- 238000004364 calculation method Methods 0.000 claims abstract description 19
- 238000004590 computer program Methods 0.000 claims description 13
- 230000011218 segmentation Effects 0.000 claims description 12
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000007405 data analysis Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 10
- 238000000605 extraction Methods 0.000 description 5
- 238000003062 neural network model Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
Abstract
The application relates to the field of data analysis, and realizes automatic recommendation of a proper rehabilitation aid to a user, so that convenience of configuring the rehabilitation aid by the user is improved. A rehabilitation aid recommendation method, apparatus, computer device and storage medium are provided, the method comprising: when the search text is detected, determining keywords corresponding to the search text, and performing semantic expansion on the keywords to obtain a corresponding keyword set; calling a rehabilitation assistive device matching library, wherein the rehabilitation assistive device matching library comprises at least one rehabilitation assistive device and characteristic text information corresponding to each rehabilitation assistive device; performing relevance calculation on the keyword set and each feature text message based on a preset relevance scoring algorithm to obtain a relevance score corresponding to each feature text message; and determining the target rehabilitation assistant tool corresponding to the search text according to the relevance value corresponding to each piece of characteristic text information, and displaying the target rehabilitation assistant tool. In addition, the application also relates to a block chain technology, and a rehabilitation aid matching library can be stored in the block chain.
Description
Technical Field
The application relates to the field of data analysis, in particular to a rehabilitation assistant recommendation method and device, computer equipment and a storage medium.
Background
With the increasing severity of aging of the population, more and more disabled old people need to use various rehabilitation aids, so the rehabilitation aids have great effects on improving the life, the quality of life and the care level of the old people. In actual life, the way for configuring the rehabilitation assistive device by the user is mainly manual configuration; when a user needs to configure a rehabilitation aid, a rehabilitation aid mechanism is required to request a professional to configure a proper rehabilitation aid according to the actual condition of the user; for users who are inconvenient to travel, great inconvenience exists.
Therefore, how to improve the convenience of configuring the rehabilitation aid for the user becomes an urgent problem to be solved.
Disclosure of Invention
The application provides a rehabilitation assistive device recommending method and device, computer equipment and a storage medium.
In a first aspect, the present application provides a rehabilitation aid recommendation method, including:
when a search text is detected, determining keywords corresponding to the search text, and performing semantic expansion on the keywords to obtain a corresponding keyword set;
calling a rehabilitation assistive device matching library, wherein the rehabilitation assistive device matching library comprises at least one rehabilitation assistive device and characteristic text information corresponding to each rehabilitation assistive device;
performing relevance calculation on the keyword set and each feature text message based on a preset relevance scoring algorithm to obtain a relevance score corresponding to each feature text message;
and determining a target rehabilitation aid corresponding to the search text according to the relevance value corresponding to each piece of feature text information, and outputting the target rehabilitation aid for recommendation.
In a second aspect, the present application further provides a rehabilitation aid recommendation device, the device comprising:
the keyword determining module is used for determining keywords corresponding to a search text when the search text is detected, and performing semantic expansion on the keywords to obtain a corresponding keyword set;
the device comprises a matching library calling module, a matching library matching module and a matching library matching module, wherein the matching library matching module is used for calling a rehabilitation assistant tool, and the rehabilitation assistant tool matching library comprises at least one rehabilitation assistant tool and characteristic text information corresponding to each rehabilitation assistant tool;
the relevance calculating module is used for carrying out relevance calculation on the keyword set and each feature text message based on a preset relevance scoring algorithm to obtain a relevance score corresponding to each feature text message;
and the rehabilitation aid recommending module is used for determining a target rehabilitation aid corresponding to the search text according to the relevance value corresponding to each piece of characteristic text information and outputting the target rehabilitation aid for recommendation.
In a third aspect, the present application further provides a computer device comprising a memory and a processor;
the memory for storing a computer program;
the processor is used for executing the computer program and realizing the rehabilitation assistant recommendation method when the computer program is executed.
In a fourth aspect, the present application also provides a computer-readable storage medium storing a computer program which, when executed by a processor, causes the processor to implement the rehabilitation aid recommendation method as described above.
The application discloses a rehabilitation assistive device recommendation method and device, computer equipment and a storage medium, semantic expansion is carried out on keywords corresponding to a search text, synonyms and near synonyms are added, the matching range of the keywords can be expanded, and the probability of matching the keywords to a proper rehabilitation assistive device subsequently is improved; by calling a rehabilitation aid matching library comprising at least one rehabilitation aid and the characteristic text information corresponding to each rehabilitation aid, correlation calculation can be performed on the keyword set and each characteristic text information based on a preset correlation scoring algorithm, and then correlation scores corresponding to each characteristic text information can be obtained; according to the relevance score corresponding to each feature text message, the target rehabilitation assistant tool corresponding to the search text can be determined and output for recommendation, so that the appropriate rehabilitation assistant tool can be automatically recommended to the user, and convenience of the user in configuring the rehabilitation assistant tool is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a rehabilitation aid recommendation method provided in an embodiment of the present application;
FIG. 2 is a schematic flow chart diagram illustrating a sub-step of creating a rehabilitation aid matching library according to an embodiment of the present application;
fig. 3 is a schematic diagram illustrating a calculation of a relevance score corresponding to feature text information according to an embodiment of the present application;
fig. 4 is a schematic block diagram of a rehabilitation aid recommendation device provided in an embodiment of the present application;
fig. 5 is a schematic block diagram of a structure of a computer device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The flow diagrams depicted in the figures are merely illustrative and do not necessarily include all of the elements and operations/steps, nor do they necessarily have to be performed in the order depicted. For example, some operations/steps may be decomposed, combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
It is to be understood that the terminology used in the description of the present application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the specification of the present application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should also be understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
The embodiment of the application provides a rehabilitation assistant tool recommendation method and device, computer equipment and a storage medium. The rehabilitation assistive device recommendation method can be applied to a server or a terminal, the target rehabilitation assistive device is obtained by calling a rehabilitation assistive device matching library and matching according to the keyword set corresponding to the search text, the appropriate rehabilitation assistive device is automatically recommended to the user, and convenience of the user in configuring the rehabilitation assistive device is improved.
The server may be an independent server or a server cluster. The terminal can be an electronic device such as a smart phone, a tablet computer, a notebook computer, a desktop computer and the like.
Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments described below and the features of the embodiments can be combined with each other without conflict.
As shown in fig. 1, the rehabilitation aid recommendation method includes steps S10 to S40.
Step S10, when a search text is detected, determining keywords corresponding to the search text, and performing semantic expansion on the keywords to obtain a corresponding keyword set.
It should be noted that the rehabilitation aid recommendation method provided by the embodiment of the application can be applied to a rehabilitation aid search system, and a user can search a rehabilitation aid on a search page of the rehabilitation aid search system. The rehabilitation aid search system can be installed in a server or a terminal, and a user can enter a search page by logging in the rehabilitation aid search system. For example, the user can input information such as illness state, physical condition or rehabilitation requirement and the like in the search page according to the self requirement, and search the corresponding rehabilitation assistant tool.
Illustratively, when an input operation of a user on a search page is detected, a search text input by the user is detected and acquired according to the input operation. The text to be searched may include, but is not limited to, disease condition information, physical condition information, rehabilitation requirement information, and the like.
In the embodiment of the application, after the search text input by the user is obtained, keywords can be extracted from the search text to obtain keywords corresponding to the search text; and then performing semantic expansion on the keywords to obtain a corresponding keyword set.
In some embodiments, when extracting keywords from a search text, performing word segmentation processing on the search text to obtain a phrase set corresponding to the search text; and extracting keywords from the phrase set to obtain keywords corresponding to the search text.
Illustratively, word segmentation processing may be performed on the search text based on the word segmentation model to obtain a word group set corresponding to the search text. Wherein the phrase set comprises at least one phrase.
The word segmentation model may include a BI _ LSTM-CRF neural network model, and of course, other neural network models may be used, which are not limited herein. It should be noted that the BI _ LSTM-CRF neural network model combines the BI _ LSTM network and the CRF (conditional Random field) layer. The BI _ LSTM-CRF neural network model can not only use the features and statement label information input in the past, but also use the input features in the future, and can ensure the higher accuracy of Chinese word segmentation by considering the influence of long-distance context information on Chinese word segmentation.
Illustratively, the keyword extraction may be performed on the phrase set based on a keyword extraction algorithm to obtain corresponding keywords.
The keyword extraction algorithm may include, but is not limited to, a TF-IDF algorithm, a TextRank algorithm, and a Word2Vec Word clustering algorithm. In the embodiment of the application, a TF-IDF algorithm, a TextRank algorithm or a Word2Vec Word clustering algorithm can be adopted to extract keywords from the phrase set; and extracting keywords from the phrase set by adopting a plurality of algorithms of the TF-IDF algorithm, the TextRank algorithm and the Word2Vec Word clustering algorithm.
By carrying out word segmentation on the search text and carrying out keyword extraction on the phrase set obtained by word segmentation, the keywords corresponding to the search text can be obtained, so that the corresponding rehabilitation aids are matched according to the keywords, and the matching success rate is improved.
In some embodiments, semantically expanding the keywords to obtain a corresponding keyword set may include: determining a near synonym and a synonym corresponding to the keyword; and determining a keyword set according to the keywords and the similar synonyms and/or synonyms.
For example, the synonym forest or the Chinese synonym toolkit synnyms may be used to match the Synonyms and the keywords with each other, so as to obtain the corresponding Synonyms and the Synonyms of the keywords.
Illustratively, the keyword set may be generated according to keywords, synonyms or synonyms; and generating a keyword set according to the keywords, the synonyms and the synonyms.
By performing semantic expansion on the keywords, the matching range of the keywords can be expanded, the loss of matching results caused by different words is reduced, and the probability of matching to a proper rehabilitation aid is effectively improved.
Step S20, calling a rehabilitation aid matching library, wherein the rehabilitation aid matching library comprises at least one rehabilitation aid and characteristic text information corresponding to each rehabilitation aid.
The rehabilitation assistive device matching library is used for matching corresponding rehabilitation assistive devices according to the search texts; the rehabilitation assistant matching library is pre-established and stored in a local disk or a local database. In the embodiment of the present application, how to establish the rehabilitation assistant matching library will be described in detail. By establishing the rehabilitation assistive device matching library, the corresponding rehabilitation assistive devices can be matched according to the search texts input by the user, so that the user can conveniently obtain the appropriate rehabilitation assistive devices.
Referring to fig. 2, fig. 2 is a schematic flowchart illustrating sub-steps of establishing a rehabilitation assistant matching library according to an embodiment of the present application, which may specifically include the following steps S201 to S203.
Step S201, obtaining attribute information corresponding to each rehabilitation assistive device.
In the embodiment of the application, the attribute information corresponding to the rehabilitation assistive device can be collected through databases of medical institutions, residual union institutions and instrument manufacturers.
Illustratively, the attribute information may include at least one of basic data of the rehabilitation aid, applicable patient data, and basic characteristic data. The basic data can include dimensional characteristics such as names, brands and models of the assistive devices; applicable patient data may include dimensional characteristics of the patient's physical function, chief complaints, and the like; the basic characteristic data may include data on the environment in which the rehabilitation aid is used, the primary function, the achievable rehabilitation needs, comfort, price, etc.
Step S202, determining characteristic text information corresponding to each rehabilitation aid according to the attribute information corresponding to each rehabilitation aid.
For example, the attribute information corresponding to each rehabilitation assistive device can be determined as the characteristic text information corresponding to each rehabilitation assistive device; and key information in the attribute information can be extracted and stored in a key value pair form to obtain the characteristic text information.
For example, for the rehabilitation aid of an oxygen machine, the corresponding characteristic text information is shown in table 1.
TABLE 1
In some embodiments, before determining the characteristic text information corresponding to each rehabilitation assistive device according to the attribute information corresponding to each rehabilitation assistive device, the method may further include: when detecting that the attribute information has data loss, performing data matching on the attribute information to obtain corresponding filling data; and filling the attribute information according to the filling data to obtain the filled attribute information.
It should be noted that, since the basic data of the rehabilitation aid can be derived from the product specification, if some fields in the product specification are not complete or are not described in detail, the attribute information may be missing.
For example, the format and content of the attribute information may be detected, and when it is detected that there is data missing in the attribute information, the filling data corresponding to the missing data is determined.
For example, the data matching may be performed on the attribute information of the missing data according to the basic data of similar or similar rehabilitation aids, so as to obtain corresponding padding data. If there is no matching data, the padding data may be null. In order to ensure the reliability and the specificity of the filling data, the filling data can also be supplemented by a professional.
For example, after the attribute information is filled according to the filling data and the filled attribute information is obtained, the feature text information may be determined according to the filled attribute information.
By acquiring the filling data and filling the attribute information when the attribute information is detected to have data loss, the integrity and the reliability of the attribute information can be ensured, and the probability of matching the appropriate rehabilitation aid according to the search text in the follow-up process is effectively improved.
In some embodiments, when determining the characteristic text information corresponding to each rehabilitation aid according to the attribute information corresponding to each rehabilitation aid, the method may further include: performing expansion processing on the attribute information to obtain expanded attribute information; and determining the characteristic text information according to the attribute information after the expansion processing.
The expansion processing is data that does not affect the characteristics of the rehabilitation aid for the attribute information addition portion. For example, data of different volumes are added, where the volumes are large, medium and small.
Exemplarily, a parameter with a volume of 'middle' is added to the attribute information of the rehabilitation aid to obtain the extended attribute information; then, according to the attribute information after the expansion processing, it is determined as the characteristic text information, as shown in table 2.
TABLE 2
By expanding the attribute information, new parameters can be added to the attribute information, and the integrity of the attribute information is further improved.
And S203, generating the rehabilitation assistant tool matching library according to the characteristic text information.
For example, each rehabilitation aid can be associated with the feature text information corresponding to each rehabilitation aid, and the feature text information is stored in a preset database to obtain a rehabilitation aid matching library. Wherein, the rehabilitation assistant matching library can be loaded into the rehabilitation assistant searching system.
To further ensure the privacy and security of the rehabilitation aid matching library, the rehabilitation aid matching library may be stored in a node of a block chain. When the rehabilitation assistive device matching library is required to be used, the rehabilitation assistive device matching library can be called from the block link points.
Step S30, performing relevance calculation on the keyword set and each feature text information based on a preset relevance scoring algorithm, and obtaining a relevance score corresponding to each feature text information.
Illustratively, the preset relevance scoring algorithm may include the BM25 algorithm. It should be noted that the BM25 algorithm is used to calculate the correlation between sentences and documents. Among them, the principle of BM25 algorithm: performing morpheme analysis on the search content Query to generate morpheme qi; then, for each search result D, calculating a relevance score between each morpheme qi and the search content D; and finally, carrying out weighted summation on the relevance scores between each morpheme qi and the search result D, thereby obtaining the relevance score between the search content Query and the search content D.
Referring to fig. 3, fig. 3 is a schematic diagram illustrating a calculation of a relevance score corresponding to a feature text message according to an embodiment of the present application. As shown in fig. 3, relevance calculation may be performed on the keyword set and each feature text information through a BM25 algorithm, so as to obtain a relevance score corresponding to each feature text information. The specific calculation formula is as follows:
in the formula (II), RSVdRepresenting the corresponding relevance score of each characteristic text message;
representing the weight value of the keyword set t, N representing the total number of characteristic text messages, dftAnd the number corresponding to the characteristic text information of the phrases in the keyword set is shown. Wherein the content of the first and second substances,
representing a relevance score between the keyword set t and the characteristic text information d; tf istdRepresenting the frequency of occurrence of the keyword set t in the characteristic text information d; k is a radical of1And b is a regulatory factor; l isdIndicating the length, L, of the characteristic text informationaveRepresenting the average length of the characteristic text information. Wherein the content of the first and second substances,
representing a relevance score between the set of keywords and the search text; k is a radical of3Is a regulatory factor.
Illustratively, the factor k is adjusted1And the adjustment factor b can be set according to actual conditions, and specific values are not limited herein.
In some embodiments, since the search text is user-based, the user's own situationIf the search is carried out, the extracted keyword set has higher correlation with the search text, therefore, the adjustment factor k can be adjusted3Is set to 0.
It should be noted that, the BM25 algorithm effectively improves the accuracy of correlation calculation by introducing the weight values of the keyword sets in the feature text information, the weight values of the keyword sets in the search text, and some empirical parameters.
By carrying out relevance calculation on the keyword set and each characteristic text message based on a relevance scoring algorithm, the relevance score corresponding to each characteristic text message can be accurately calculated.
Step S40, determining a target rehabilitation aid corresponding to the search text according to the relevance score corresponding to each feature text message, and outputting the target rehabilitation aid for recommendation.
For example, after the relevance calculation is performed on the keyword set and each feature text information based on a preset relevance scoring algorithm to obtain the relevance score corresponding to each feature text information, the target rehabilitation aid corresponding to the search text may be determined according to the relevance score corresponding to each feature text information.
In some embodiments, determining the target rehabilitation assistant tool corresponding to the search text according to the relevance score corresponding to each feature text message may include: determining the corresponding characteristic text information with the relevance score larger than a preset relevance threshold value as target characteristic text information; and determining the target rehabilitation aid according to the target characteristic text information based on the corresponding relation between the preset characteristic text information and the rehabilitation aid.
For example, the preset correlation threshold may be set according to actual conditions, and the specific value is not limited herein.
For example, for feature text information A, B and C, if the relevance score corresponding to feature text information a is greater than the preset relevance threshold, feature text information a may be determined as the target feature text information.
It can be understood that, since the rehabilitation assistive devices stored in the rehabilitation assistive device matching library all have corresponding characteristic text information, the target rehabilitation assistive device can be determined according to the target characteristic text information based on the corresponding relationship between the preset characteristic text information and the rehabilitation assistive device. For example, the rehabilitation aid corresponding to the characteristic text information a is determined as the target rehabilitation aid.
In some embodiments, the targeted rehabilitation aid may be displayed in a search page when it is output for recommendation. For example, the attribute information of the target rehabilitation aid may be displayed, and a structure diagram or a product diagram corresponding to the target rehabilitation aid may be displayed.
It should be noted that, by displaying the target rehabilitation aid on the search page, the appropriate rehabilitation aid can be automatically recommended to the user, so that the user can conveniently obtain the appropriate rehabilitation aid. For some users who are inconvenient to go out, the configured rehabilitation assistive device can be obtained only by inputting the conditions such as the physical conditions, the rehabilitation requirements and the like of the users remotely, and the time and the trip cost are greatly saved.
In some embodiments, after the target rehabilitation assistive device corresponding to the search text is determined, geographic position information and/or link address information corresponding to the target rehabilitation assistive device can be acquired; outputting the geographical location information and/or the link address information.
It should be noted that the geographic location information refers to an address for purchasing a target rehabilitation aid offline; the link address information refers to a website for purchasing the target rehabilitation aid on line.
For example, the address location information or the link address information may be displayed on the search page, or the address location information and the link address information may be displayed at the same time.
When the geographical position information corresponding to the target rehabilitation assistive device is obtained, the actual address of the physical store corresponding to the target rehabilitation assistive device can be searched based on the navigation positioning system, and then the corresponding geographical position information is generated. When the link address information corresponding to the target rehabilitation aid is obtained, an online store corresponding to the target rehabilitation aid can be searched through a big data technology, and the link address information is generated according to the website of the online store.
The geographical position information or the link address information corresponding to the target rehabilitation aid is displayed on the search page, so that a user can conveniently purchase the rehabilitation aid, and the user experience is improved.
According to the rehabilitation assistive device recommendation method provided by the embodiment, the search text is subjected to word segmentation, the word group set obtained by the word segmentation is subjected to keyword extraction, and the keywords corresponding to the search text can be obtained, so that the corresponding rehabilitation assistive device is matched according to the keywords, and the matching success rate is improved; by performing semantic expansion on the keywords, the matching range of the keywords can be expanded, the loss of matching results caused by different words is reduced, and the probability of matching to a proper rehabilitation aid is effectively improved; when the attribute information is detected to have data loss, the filling data is acquired and the attribute information is filled, so that the integrity and reliability of the attribute information can be ensured, and the probability of matching proper rehabilitation aids according to the search text in the follow-up process is effectively improved; by expanding the attribute information, new parameters can be added to the attribute information, and the integrity of the attribute information is further improved; correlation calculation is carried out on the keyword set and each characteristic text message based on a correlation scoring algorithm, so that a correlation score corresponding to each characteristic text message can be accurately calculated; by displaying the target rehabilitation assistive device on the search page, the appropriate rehabilitation assistive device can be automatically recommended to the user, so that the user can conveniently obtain the appropriate rehabilitation assistive device; the geographical position information or the link address information corresponding to the target rehabilitation aid is displayed on the search page, so that a user can conveniently purchase the rehabilitation aid, and the user experience is improved.
Referring to fig. 4, fig. 4 is a schematic block diagram of a rehabilitation aid recommendation device 1000 for executing the aforementioned rehabilitation aid recommendation method according to an embodiment of the present application. The rehabilitation aid recommendation device can be configured in a server or a terminal.
As shown in fig. 4, the rehabilitation aid recommendation device 1000 includes: a keyword determination module 1001, a matching library calling module 1002, a correlation calculation module 1003 and a rehabilitation aid recommendation module 1004.
The keyword determining module 1001 is configured to determine, when a search text is detected, a keyword corresponding to the search text, perform semantic expansion on the keyword, and obtain a corresponding keyword set.
The matching library calling module 1002 is configured to call a rehabilitation assistant tool matching library, where the rehabilitation assistant tool matching library includes at least one rehabilitation assistant tool and feature text information corresponding to each rehabilitation assistant tool.
The relevance calculating module 1003 is configured to perform relevance calculation on the keyword set and each piece of feature text information based on a preset relevance scoring algorithm, and obtain a relevance score corresponding to each piece of feature text information.
And a rehabilitation aid recommending module 1004, configured to determine a target rehabilitation aid corresponding to the search text according to the relevance score corresponding to each piece of feature text information, and output the target rehabilitation aid for recommendation.
It should be noted that, as will be clear to those skilled in the art, for convenience and brevity of description, the specific working processes of the apparatus and the modules described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The apparatus described above may be implemented in the form of a computer program which is executable on a computer device as shown in fig. 5.
Referring to fig. 5, fig. 5 is a schematic block diagram of a computer device according to an embodiment of the present disclosure.
Referring to fig. 5, the computer device includes a processor and a memory connected by a system bus, wherein the memory may include a nonvolatile storage medium and an internal memory.
The processor is used for providing calculation and control capability and supporting the operation of the whole computer equipment.
The internal memory provides an environment for execution of a computer program on a non-volatile storage medium, which when executed by the processor, causes the processor to perform any of the rehabilitation aid recommendation methods.
It should be understood that the Processor may be a Central Processing Unit (CPU), and the Processor may be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, etc. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Wherein, in one embodiment, the processor is configured to execute a computer program stored in the memory to implement the steps of:
when a search text is detected, determining keywords corresponding to the search text, and performing semantic expansion on the keywords to obtain a corresponding keyword set; calling a rehabilitation assistive device matching library, wherein the rehabilitation assistive device matching library comprises at least one rehabilitation assistive device and characteristic text information corresponding to each rehabilitation assistive device; performing relevance calculation on the keyword set and each feature text message based on a preset relevance scoring algorithm to obtain a relevance score corresponding to each feature text message; and determining a target rehabilitation aid corresponding to the search text according to the relevance value corresponding to each piece of feature text information, and outputting the target rehabilitation aid for recommendation.
In one embodiment, the processor, prior to implementing the invoking of the rehabilitation aid matching library, is further to implement:
acquiring attribute information corresponding to each rehabilitation assistive device; determining characteristic text information corresponding to each rehabilitation aid according to the attribute information corresponding to each rehabilitation aid; and generating the rehabilitation assistive device matching library according to the characteristic text information.
In one embodiment, before the processor determines the characteristic text information corresponding to each of the rehabilitation aids according to the attribute information corresponding to each of the rehabilitation aids, the processor is further configured to:
when detecting that the attribute information has data loss, performing data matching on the attribute information to obtain corresponding filling data; and filling the attribute information according to the filling data to obtain the filled attribute information.
In one embodiment, the processor is configured to, when determining the feature text information corresponding to each of the rehabilitation aids according to the attribute information corresponding to each of the rehabilitation aids, implement:
and determining the characteristic text information according to the filled attribute information.
In one embodiment, the processor, in performing determining the keyword corresponding to the search text, is configured to perform:
performing word segmentation processing on the search text to obtain a word group set corresponding to the search text; and extracting keywords from the phrase set to obtain the keywords.
In one embodiment, the processor is configured to perform semantic expansion on the keywords to obtain a corresponding keyword set, and is configured to perform:
determining a similar meaning word and a synonym corresponding to the keyword; and determining the keyword set according to the keywords and the similar synonyms and/or the synonyms.
In one embodiment, when determining the target rehabilitation aid corresponding to the search text according to the relevance score corresponding to each piece of feature text information, the processor is configured to:
determining the corresponding characteristic text information with the relevance score larger than a preset relevance threshold value as target characteristic text information; and determining the target rehabilitation aid according to the target characteristic text information based on the corresponding relation between the preset characteristic text information and the rehabilitation aid.
In one embodiment, the processor, after implementing determining that the target rehabilitation aid corresponds to the search text, is further configured to implement:
acquiring geographic position information and/or link address information corresponding to the target rehabilitation assistive device; and outputting the geographical position information and/or the link address information.
The embodiment of the application further provides a computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, the computer program comprises program instructions, and the processor executes the program instructions to realize any rehabilitation assistant recommendation method provided by the embodiment of the application.
The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiment, for example, a hard disk or a memory of the computer device. The computer readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital Card (SD Card), a Flash memory Card (Flash Card), and the like provided on the computer device.
Further, the computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.
The block chain referred by the application is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
While the invention has been described with reference to specific embodiments, the scope of the invention is not limited thereto, and those skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the invention. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A rehabilitation aid recommendation method, comprising:
when a search text is detected, determining keywords corresponding to the search text, and performing semantic expansion on the keywords to obtain a corresponding keyword set;
calling a rehabilitation assistive device matching library, wherein the rehabilitation assistive device matching library comprises at least one rehabilitation assistive device and characteristic text information corresponding to each rehabilitation assistive device;
performing relevance calculation on the keyword set and each feature text message based on a preset relevance scoring algorithm to obtain a relevance score corresponding to each feature text message;
and determining a target rehabilitation aid corresponding to the search text according to the relevance value corresponding to each piece of feature text information, and outputting the target rehabilitation aid for recommendation.
2. The rehabilitation aid recommendation method according to claim 1, wherein before said invoking a rehabilitation aid matching library, further comprising:
acquiring attribute information corresponding to each rehabilitation assistive device;
determining characteristic text information corresponding to each rehabilitation aid according to the attribute information corresponding to each rehabilitation aid;
and generating the rehabilitation assistive device matching library according to the characteristic text information.
3. The method for recommending rehabilitation aids of claim 2, wherein before determining the characteristic text information corresponding to each of the rehabilitation aids according to the attribute information corresponding to each of the rehabilitation aids, the method further comprises:
when detecting that the attribute information has data loss, performing data matching on the attribute information to obtain corresponding filling data;
filling the attribute information according to the filling data to obtain the filled attribute information;
the determining, according to the attribute information corresponding to each rehabilitation aid, feature text information corresponding to each rehabilitation aid includes:
and determining the characteristic text information according to the filled attribute information.
4. The rehabilitation aid recommendation method according to claim 1, wherein the determining of the keyword corresponding to the search text comprises:
performing word segmentation processing on the search text to obtain a word group set corresponding to the search text;
and extracting keywords from the phrase set to obtain the keywords.
5. The rehabilitation aid recommendation method according to claim 1, wherein said semantically expanding said keywords to obtain a corresponding keyword set comprises:
determining a similar meaning word and a synonym corresponding to the keyword;
and determining the keyword set according to the keywords and the similar synonyms and/or the synonyms.
6. The method for recommending rehabilitation aids of claim 1, wherein the determining the target rehabilitation aids corresponding to the search text according to the relevance score corresponding to each piece of feature text information comprises:
determining the corresponding characteristic text information with the relevance score larger than a preset relevance threshold value as target characteristic text information;
and determining the target rehabilitation aid according to the target characteristic text information based on the corresponding relation between the preset characteristic text information and the rehabilitation aid.
7. The rehabilitation aid recommendation method according to any one of claims 1-6, wherein after determining the target rehabilitation aid corresponding to the search text, the method further comprises;
acquiring geographic position information and/or link address information corresponding to the target rehabilitation assistive device;
and outputting the geographical position information and/or the link address information.
8. A rehabilitation aid recommendation device, comprising:
the keyword determining module is used for determining keywords corresponding to a search text when the search text is detected, and performing semantic expansion on the keywords to obtain a corresponding keyword set;
the device comprises a matching library calling module, a matching library matching module and a matching library matching module, wherein the matching library matching module is used for calling a rehabilitation assistant tool, and the rehabilitation assistant tool matching library comprises at least one rehabilitation assistant tool and characteristic text information corresponding to each rehabilitation assistant tool;
the relevance calculating module is used for carrying out relevance calculation on the keyword set and each feature text message based on a preset relevance scoring algorithm to obtain a relevance score corresponding to each feature text message;
and the rehabilitation aid recommending module is used for determining a target rehabilitation aid corresponding to the search text according to the relevance value corresponding to each piece of characteristic text information and outputting the target rehabilitation aid for recommendation.
9. A computer device, wherein the computer device comprises a memory and a processor;
the memory for storing a computer program;
the processor for executing the computer program and implementing the rehabilitation aid recommendation method according to any one of claims 1 to 7 when the computer program is executed.
10. A computer-readable storage medium, characterized in that it stores a computer program which, when executed by a processor, causes the processor to implement the rehabilitation aid recommendation method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110593386.1A CN113297489A (en) | 2021-05-28 | 2021-05-28 | Rehabilitation aid recommendation method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110593386.1A CN113297489A (en) | 2021-05-28 | 2021-05-28 | Rehabilitation aid recommendation method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113297489A true CN113297489A (en) | 2021-08-24 |
Family
ID=77325973
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110593386.1A Pending CN113297489A (en) | 2021-05-28 | 2021-05-28 | Rehabilitation aid recommendation method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113297489A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103425687A (en) * | 2012-05-21 | 2013-12-04 | 阿里巴巴集团控股有限公司 | Retrieval method and system based on queries |
| US20150058309A1 (en) * | 2013-08-23 | 2015-02-26 | Naver Corporation | Keyword presenting system and method based on semantic depth structure |
| CN108776901A (en) * | 2018-04-27 | 2018-11-09 | 微梦创科网络科技（中国）有限公司 | Method and system for advertisement recommendation based on search term |
| CN111626813A (en) * | 2020-04-22 | 2020-09-04 | 北京健康之家科技有限公司 | Product recommendation method and system |
-
2021
- 2021-05-28 CN CN202110593386.1A patent/CN113297489A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103425687A (en) * | 2012-05-21 | 2013-12-04 | 阿里巴巴集团控股有限公司 | Retrieval method and system based on queries |
| US20150058309A1 (en) * | 2013-08-23 | 2015-02-26 | Naver Corporation | Keyword presenting system and method based on semantic depth structure |
| CN108776901A (en) * | 2018-04-27 | 2018-11-09 | 微梦创科网络科技（中国）有限公司 | Method and system for advertisement recommendation based on search term |
| CN111626813A (en) * | 2020-04-22 | 2020-09-04 | 北京健康之家科技有限公司 | Product recommendation method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11182564B2 (en) | Text recommendation method and apparatus, and electronic device | |
| US10997370B2 (en) | Hybrid classifier for assigning natural language processing (NLP) inputs to domains in real-time | |
| US10452694B2 (en) | Information extraction from question and answer websites | |
| US11227118B2 (en) | Methods, devices, and systems for constructing intelligent knowledge base | |
| US11544578B2 (en) | Method, device and equipment for fusing different instances describing same entity | |
| WO2019201098A1 (en) | Question and answer interactive method and apparatus, computer device and computer readable storage medium | |
| US10102191B2 (en) | Propagation of changes in master content to variant content | |
| US20190349320A1 (en) | System and method for automatically responding to user requests | |
| CN112215008B (en) | Entity identification method, device, computer equipment and medium based on semantic understanding | |
| WO2019037258A1 (en) | Information recommendation method, device and system, and computer-readable storage medium | |
| US20210365803A1 (en) | Machine-learning system and method for identifying same person in genealogical databases | |
| US11017002B2 (en) | Description matching for application program interface mashup generation | |
| CN109522397B (en) | Information processing method and device | |
| WO2012096388A1 (en) | Unexpectedness determination system, unexpectedness determination method, and program | |
| CN112395391A (en) | Concept graph construction method and device, computer equipment and storage medium | |
| CN113254588A (en) | Data searching method and system | |
| CN113177407A (en) | Data dictionary construction method and device, computer equipment and storage medium | |
| CN112527967A (en) | Text matching method, device, terminal and storage medium | |
| CN113297489A (en) | Rehabilitation aid recommendation method and device, computer equipment and storage medium | |
| CN112733492B (en) | Knowledge base-based aided design method and device, terminal and storage medium | |
| CN111709226B (en) | Text processing method and device | |
| WO2024098636A1 (en) | Text matching method and apparatus, computer-readable storage medium, and terminal | |
| JP6467678B1 (en) | Question answering system, apparatus, method, server apparatus and program | |
| CN116127367A (en) | Method and device for auditing service evaluation and computer readable storage medium | |
| CN117373698A (en) | Medical guidance information acquisition method, device and equipment based on session interaction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |