CN108874773B - Keyword newly-adding method and device, computer equipment and storage medium - Google Patents
Keyword newly-adding method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN108874773B CN108874773B CN201810551257.4A CN201810551257A CN108874773B CN 108874773 B CN108874773 B CN 108874773B CN 201810551257 A CN201810551257 A CN 201810551257A CN 108874773 B CN108874773 B CN 108874773B
- Authority
- CN
- China
- Prior art keywords
- word
- keyword
- words
- search
- keywords
- 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.)
- Active
Links
Images
Classifications
-
- 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
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/247—Thesauruses; Synonyms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Machine Translation (AREA)
Abstract
The application relates to a keyword newly-adding method, a keyword newly-adding device, computer equipment and a storage medium. The method comprises the following steps: inquiring search records without search results, and popping up a keyword mapping management interface; acquiring ontology words with different dimensions corresponding to the search records, and inputting the ontology words with different dimensions into attribute values with corresponding dimensions in a keyword mapping management interface; receiving input keywords through the keyword mapping management interface; and storing the attribute value and the keyword in an associated manner. By adopting the method, the recommendation success rate of departments can be improved.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method and an apparatus for adding a keyword, a computer device, and a storage medium.
Background
With the development of computer technology, a user can perform online inquiry through an application program installed on a mobile phone terminal to realize online diagnosis, and only when the problem which cannot be solved online is met, the user can go to an offline department for treatment. However, since the names of the hospital outpatient departments are different from the names of the on-line inquiry departments, the on-line and off-line referral needs to be translated.
Conventionally, since the amount of history data is small, a problem that a keyword cannot be calculated or a keyword search result cannot be obtained occurs, which leads to a failure in recommendation of a department, and thus the problem continues to be solved.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a keyword adding method, device, computer device and storage medium for improving the success rate of recommendation of departments.
A keyword adding method, the method comprising:
inquiring search records without search results, and acquiring the corresponding different-dimension local words of the search records;
popping up a keyword mapping management interface, and inputting the ontology words with different dimensions into attribute values of corresponding dimensions in the keyword mapping management interface;
receiving input keywords through the keyword mapping management interface;
and storing the attribute value and the keyword in an associated manner.
In one embodiment, the method further comprises:
receiving a state modification instruction for the attribute values and the keywords after associated storage;
according to the state modification instruction, modifying the state of the search record corresponding to the attribute value and the keyword after the associated storage into a search result;
and adding the attribute values and the keywords after the association storage to a keyword mapping management library.
In one embodiment, the method further comprises:
receiving input inquiry data acquired by a terminal;
performing word segmentation processing on the inquiry data to obtain word segmentation data;
deducing the word segmentation data through an escape word library to obtain body words with different dimensions;
matching the body words with different dimensions with the attribute values of the keywords in the keyword mapping management library;
and when the attribute values of the body words with different dimensions are matched with the attribute values of the keywords in the keyword mapping management library to obtain no target keyword, marking the search record corresponding to the inquiry data as a no-search result.
In one embodiment, the method further comprises:
when the body words with different dimensions are matched with the attribute values of the keywords in the keyword mapping management library to obtain target keywords, searching departments corresponding to the target keywords;
and when the department corresponding to the target keyword is not searched, marking the search record corresponding to the inquiry data as a non-search result.
In one embodiment, before the deriving the word segmentation data through an escape word library to obtain ontology words with different dimensions, the method further includes:
receiving a current scene acquired by the terminal;
and loading a corresponding escape word library according to the current scene.
In one embodiment, the deriving the word segmentation data through an escape word library to obtain ontology words with different dimensions includes:
searching whether the escape word library corresponds to the current word segmentation;
when the body words corresponding to the current word segmentation exist in the escape word stock, performing dimension processing on the body words to obtain body words with different dimensions, and outputting the body words with different dimensions;
when the body word corresponding to the current word segmentation does not exist in the escape word library, searching whether a near word corresponding to the current word segmentation exists in the escape word library or not;
and when the similar meaning word corresponding to the current word segmentation exists in the escape word library, updating the current word segmentation through the similar meaning word, and continuously searching whether the body word corresponding to the current word segmentation exists in the escape word library.
A keyword adding apparatus, the apparatus comprising:
the query module is used for querying search records without search results and acquiring the body words with different dimensionalities corresponding to the search records;
the first input module is used for popping up a keyword mapping management interface and inputting the ontology words with different dimensions into attribute values of corresponding dimensions in the keyword mapping management interface;
the first receiving module is used for receiving the input keywords through the keyword mapping management interface;
and the storage module is used for storing the attribute value and the keyword in an associated manner.
In one embodiment, the apparatus further comprises:
a second receiving module, configured to receive a state modification instruction for the attribute value and the keyword after the association storage;
the modification module is used for modifying the state of the search record corresponding to the attribute value and the keyword after the associated storage into a search result according to the state modification instruction;
and the adding module is used for adding the attribute values and the keywords which are stored in the associated manner to a keyword mapping management library.
A computer device comprising a memory storing a computer program and a processor implementing the steps of any of the above methods when the computer program is executed.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method of any of the above.
According to the method, the device, the computer equipment and the storage medium for adding the keywords, the search records without the search results are obtained firstly, then the body words with different dimensionalities corresponding to the search records are automatically popped up to form the keyword mapping management interface, the body words with different dimensionalities corresponding to the search records are automatically filled in the attribute values with the corresponding dimensionalities, then the corresponding keywords are input by the user, so that the matching relation between the keywords and the attribute values is established, the keyword records are added newly, therefore, when a department is searched next time, the corresponding department can be provided according to the attribute values, and the success rate of department recommendation is improved.
Drawings
FIG. 1 is a diagram illustrating an application scenario of a keyword adding method according to an embodiment;
FIG. 2 is a flowchart illustrating a keyword adding method according to an embodiment;
FIG. 3 is a diagram of a keyword mapping management interface in one embodiment;
FIG. 4 is a diagram of a search record without search results, in one embodiment;
FIG. 5 is a flow diagram of the steps of a search process in one embodiment;
FIG. 6 is a diagram of a prefix tree in one embodiment;
FIG. 7 is a schematic diagram of a directed acyclic graph in one embodiment;
FIG. 8 is a diagram of an escape library, under an embodiment;
FIG. 9 is a diagram of a keyword mapping management library in one embodiment;
FIG. 10 is a block diagram of an exemplary keyword adding apparatus;
FIG. 11 is a diagram illustrating an internal structure of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad application.
The keyword adding method provided by the application can be applied to the application environment shown in fig. 1. Wherein the terminal communicates with the server via a network. The method comprises the steps that a user inputs inquiry data through an application program installed on a terminal, the terminal obtains the inquiry data and uploads the inquiry data to a server, corresponding search results are obtained from the server, and department recommendation results are obtained. And the server acquires the body words with different dimensionalities corresponding to the search records and pops up a keyword mapping management interface. And inputting the ontology terms of different dimensions into the attribute values of the corresponding dimensions. And receiving the input keywords through the keyword mapping management interface. And associating the storage attribute values with the keywords to complete the addition of the keywords, so that corresponding departments can be provided according to the attribute values when the departments are searched next time, and the success rate of department recommendation is improved. The terminal can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers and portable wearable devices, and the server can be implemented by an independent server or a server cluster formed by a plurality of servers.
In an embodiment, as shown in fig. 2, a keyword adding method is provided, which is described by taking the application of the method to the server in fig. 1 as an example, and includes the following steps:
s202: and inquiring the search records without the search results, and acquiring the body words with different dimensionalities corresponding to the search records.
Specifically, the search record without the search result is that the server cannot obtain the corresponding keyword from the inquiry data of the user transmitted from the terminal, or even if the corresponding keyword is obtained, the server cannot search the corresponding department from the obtained keyword.
Specifically, the body words with different dimensions are generated according to the inquiry data input by the user corresponding to the search record, specifically, the user inputs the inquiry data through the terminal, the terminal sends the inquiry data input by the user to the server, and the server processes the inquiry data to obtain the body words with different dimensions. For example, the server may first perform word segmentation on the inquiry data to obtain word segmentation data, and then derive the word from the word segmentation data through a corresponding escape word bank to obtain a body word with different dimensions.
S204: and popping up a keyword mapping management interface, and inputting ontology words with different dimensions into attribute values of corresponding dimensions in the keyword mapping management interface.
For the search record without search result in this case, the server may pop up a keyword mapping management interface for mapping management of the keyword, specifically, referring to fig. 3, where fig. 3 is a schematic diagram of the keyword mapping management interface in an embodiment, where a plurality of fields exist in the keyword mapping management interface, including: department, CAT description, CAT classification, site, organ, population, symptom, disease species, cause, non-disease, specialty, clinical, exogenous, examination, treatment, medication, and directional weight, where keyword = search keyword; department = standard department name; CAT description = description of international disease classification criteria; CAT classification = international disease classification criteria code; part = part of the human body; visceral organs = human organs; people = classification of people, such as male, female, elderly, children; symptom = symptom of disease, such as "fever"; disease species = type of disease, such as "virus infection type"; etiology = cause of disease occurrence, such as "postoperative complications"; non-disease = non-disease expressions such as "fear of obesity"; special = other; clinical = clinical presentation; extrinsic causes = external causes of disease, such as "snake bite"; exam = clinical exam, such as "X-ray exam"; treatment = clinical treatment, such as "intravenous infusion"; drug = drug name; directional weight = numeric type, positive numbers indicating that the key is valid, and negative numbers indicating that the result of the key hit is to be excluded. The larger the positive number, the higher the ranking.
Optionally, the search record server without the search result may be marked, for example, as a "to-be-solved" state, specifically, as shown in fig. 4, fig. 4 is a schematic diagram of a search record without the search result in an embodiment, the server may query the search record without the search result from all search records according to the marked state, and display the search record without the search result on a display interface of the server, for example, the search record may be sorted according to a search time of the search record, so that a user may perform processing according to needs, for example, preferentially perform processing on a search record with a high frequency of occurrence, and the like. For example, the user may operate the search record without the search result as needed, the server may receive an entry instruction input by the user, pop up a corresponding keyword mapping management interface according to the entry instruction, and then continue the subsequent operation.
Specifically, referring to fig. 4, in fig. 4, two operation buttons "solve" and "rule entry" exist after each search record, where the "rule entry" button is a button for performing an addition entry operation on the search record without the search result, and when the "rule entry" button is clicked by the user, the server pops up a keyword mapping management interface, so that the user can modify and manage the search record without the search result.
When the keyword is mapped to the management interface, in order to reduce the re-analysis and input process of the user, the server may directly input the ontology terms of different dimensions queried in the search process, and then fill and write the ontology terms of different dimensions into the attribute values of corresponding dimensions, for example, a corresponding ontology term "abdomen" with a dimension of "part" is generated in the search process, and then the server may directly input the "abdomen" into the attribute value with a dimension of "part" when the keyword is mapped to the management interface, so that the user input may be reduced, and the situation of input errors caused by the user input may be avoided.
S206: and receiving the input keywords through the keyword mapping management interface.
Specifically, the server inputs the corresponding ontology word into the attribute value of the corresponding dimension, and then the user fills the corresponding keyword into the keyword mapping management interface according to the input attribute value.
Alternatively, for the above directional weights, the server may generate corresponding directional weights according to the filled-in corresponding attribute values and keywords, for example, based on a machine learning model, for example, inputting a training sample set, i.e., the keywords, the attribute values corresponding to the keywords, and the directional weights corresponding to the keywords, into an original machine learning model for training, so as to obtain a trained machine learning model. Optionally, the direction weight after passing through the machine learning model can be obtained by inputting the attribute value corresponding to the keyword in the verification sample set and the keyword into the trained machine learning model, and then the direction weight is compared with the direction weight corresponding to the verification sample set, if the two are the same or the error of the two is within an allowable range, the trained machine learning model is available, otherwise, the trained machine learning model is corrected according to the verification sample set after comparison, so that the accuracy of the machine learning model is improved.
After the machine learning model is obtained through training, the attribute values corresponding to the keywords and the keywords can be input into the machine learning model, so that the direction weights corresponding to the keywords can be directly obtained, and the generated direction weights are directly filled in fields corresponding to the direction weights.
S208: the storage attribute value and the keyword are associated.
Specifically, after the corresponding attribute values and the corresponding keywords are obtained, the server stores the attribute values and the keywords in an associated manner, so that when a department is searched next time, the corresponding department can be provided according to the attribute values, and the success rate of department recommendation is improved.
Alternatively, the user may click on a "save" button on the keyword mapping association interface, so that the server may store the entered keyword, the directional weight, and the automatically filled-in attribute value after retrieving an instruction for the user to click on the "save" button.
According to the keyword adding method, the search record without the search result is obtained firstly, then the search record without the search result is displayed, so that a user can input an input instruction aiming at the search record without the search result, a keyword mapping management interface is popped up according to the input instruction, ontology words with different dimensionalities corresponding to the search record are automatically filled in attribute values of corresponding dimensionalities, then the user inputs corresponding keywords, a matching relation between the keywords and the attribute values is established, the keyword record is added newly, therefore when a department is searched next time, corresponding departments can be given according to the attribute values, and the success rate of department recommendation is improved.
In one embodiment, the keyword adding method may further include: receiving a state modification instruction aiming at the attribute values and the keywords after the associated storage; according to the state modification instruction, modifying the state of the search record corresponding to the attribute value and the keyword after the associated storage into the search result; and adding the attribute values and the keywords which are stored in an associated manner to a keyword mapping management library.
Specifically, after the rule entry is finished, in order to provide corresponding departments for the attribute values when the departments are searched next time, the server receives a state modification instruction for the attribute values and the keywords which are stored in association, that is, a state of "to be solved" in fig. 4 is modified to a "to be solved" state, for example, the user may click a "to solve" button displayed on the interface, so that the server may modify the state of the search record corresponding to the attribute values and the keywords which are stored in association to have a search result, traverse the search records without the search results, and modify the state of the search records corresponding to other search results to a "to be solved" state if the attribute values corresponding to the search records without the search results are the same as the attribute values and the attribute values in the keywords which are stored in association, thereby reducing the number of manual operations.
Furthermore, the server adds the attribute values and the keywords which are stored in the associated mode to the keyword mapping management library, so that the corresponding attribute values can be matched after the server acquires the corresponding ontology words next time, the corresponding departments can be matched, and the success rate of matching of the offline departments is guaranteed.
In the above embodiment, after the keyword is added to the record, the user clicks a "solve" button on the interface to mark the state of the record as "solved", and then the server adds the entered rule to the keyword mapping management library, so that the next time the record is encountered, the record can be automatically applied without adding the record again, thereby improving the efficiency.
In one embodiment, the keyword adding method may further include: receiving input inquiry data acquired by a terminal; performing word segmentation processing on the inquiry data to obtain word segmentation data; deducing the word data through an escape word library to obtain the body words with different dimensions; matching the body words with different dimensions with the attribute values of the keywords in the keyword mapping management library; and when the attribute values of the body words with different dimensions are matched with the attribute values of the keywords in the keyword mapping management library to obtain no target keyword, marking the search record corresponding to the inquiry data as a non-search result.
In one embodiment, the keyword adding method may further include: when the body words with different dimensions are matched with the attribute values of the keywords in the keyword mapping management library to obtain target keywords, searching departments corresponding to the target keywords; and when the department corresponding to the target keyword is not searched, marking the search record corresponding to the inquiry data as a non-search result.
Specifically, referring to fig. 5, fig. 5 is a flowchart illustrating steps of a search process in an embodiment, where the search process mainly includes the following steps:
and S502, receiving input inquiry data acquired by the terminal.
Specifically, a user can input inquiry data through an application program in the terminal, then the terminal obtains the inquiry data input by the user, and the terminal sends the inquiry data input by the user to the server, that is, the server receives the inquiry data input by the user and obtained by the terminal.
The inquiry data input by the user can be a text input by the user through a virtual keyboard of the terminal or a voice input by the terminal, and the terminal converts the input voice into a corresponding text and sends the text to the server, so that the server receives the inquiry data input by the user and acquired by the terminal.
And S504, performing word segmentation processing on the inquiry data to obtain word segmentation data.
Specifically, the word segmentation processing is performed on the inquiry data to obtain words, and the obtained inquiry data, generally in the form of sentences, is subjected to word segmentation to obtain a plurality of words with independent meanings.
Performing word segmentation processing on the obtained inquiry data to obtain word segmentation data, which may include: loading a preset dictionary, and generating a prefix tree according to the loaded preset dictionary; generating a directed acyclic graph according to the prefix tree and the words in the inquiry data, wherein the directed acyclic graph is used for representing the condition that the words in the inquiry data can form words; searching a maximum probability path in the directed acyclic graph through the dynamic path, and acquiring word segmentation data corresponding to the maximum probability path. And optionally, the following processing can be carried out on the words which do not appear in the directed acyclic graph: selecting characters which do not appear in the directed acyclic graph from the inquiry data; acquiring a preset hidden Markov model; and performing word segmentation processing on the selected characters through a hidden Markov model to obtain word segmentation data.
Specifically, the server may first load a pre-stored dictionary, where the dictionary may be a dictionary downloaded from the internet, or a dictionary generated according to various medical websites and the like, or a user-defined dictionary, and the server generates a prefix tree according to the dictionaries, as shown in fig. 6, where the basic properties of the prefix tree include that a root node does not include a character, and each child node except the root node includes a character. And connecting the characters passing through the path from the root node to a certain node, and forming a character string corresponding to the node. All children of each node contain different characters. A character having successive repetitions starting from the first character occupies only one node, such as to and ten in fig. 6, and the repeated word t occupies only one node.
Secondly, the server generates a directed acyclic graph according to the prefix tree and the words in the inquiry data, where the directed acyclic graph is used to represent a situation that the words in the inquiry data can form words, and specifically, as shown in fig. 7, fig. 7 is a schematic diagram of the directed acyclic graph in an embodiment, where the directed acyclic graph is generated according to each root node of the prefix tree, and first obtains the prefix tree copied with the words in the text, and then generates a corresponding directed acyclic graph according to the root node of the prefix tree.
And thirdly, searching a maximum probability path in the directed acyclic graph through a dynamic path by the server, and acquiring word segmentation data corresponding to the maximum probability path, specifically, performing dynamic planning based on the directed acyclic graph, firstly searching words segmented in the data to be subjected to word segmentation inquiry, searching the frequency (times/total number, frequency and part of speech of each word is given in a dictionary) of the words, if the words do not exist in the dictionary, taking the frequency of the word with the minimum frequency as the frequency of the word, and then calculating the maximum probability path from right to left. I.e. the path with the highest probability by multiplication of the frequencies from right to left. As in fig. 7, the probability of having an opinion divergence is the greatest, and the resulting participles are "having", "opinion", and "divergence".
Fourthly, the server selects characters which do not appear in the directed acyclic graph from the inquiry data; acquiring a preset hidden Markov model; and performing word segmentation processing on the selected characters through a hidden Markov model to obtain word segmentation data. The Chinese words are marked according to four states of BEMS, B is a starting begin position, E is an end position, M is a middle position, S is a singgle, and the position of a single word is not before or after, namely, the Chinese words are marked by adopting four states of (B, E, M and S), for example, beijing can BE marked as BE, namely north/B Beijing/E, which indicates that north is a starting position, beijing is an end position, chinese nationality can BE marked as BMME, namely, beginning, middle and end, so that the server can obtain word segmentation data of characters which do not appear in the directed acyclic graph according to the starting and end positions.
S506, deducing the word data through an escape word library to obtain the body words with different dimensions.
Specifically, referring to fig. 8, the escape thesaurus is a thesaurus for converting the segmented word data into a plurality of different-dimensional ontology words, in which escape relationships between the segmented word data and the different-dimensional ontology words, such as segmented word "belly pain", which may be converted into { part: belly, symptom: pain } by the escape thesaurus, are stored. The dimension of the body word in the escape word library may include: population classification (male, female, child, elderly, etc.), department appeal, examination appeal, organs, sites, classification systems, symptoms, treatments (e.g., surgery, tooth extraction, etc.). Wherein: population classification (Population): male, female, children, the elderly, pregnant women, etc.; department appeal (Department): departments that the user intends to see a doctor, such as oral departments to be hung by the user; examination appeal (administration): items that the user should examine have been determined or indicated by the user during the interrogation process, such as a four-dimensional color ultrasound; organ (Organ): human organs and organs to which the user's disease or symptom belongs, such as intestines and stomach, heart, mammary gland, etc.; site (Body part): parts of the human body to which the user's diseases and symptoms belong, such as the chest, abdomen, limbs, head and face, etc.; classification system (Category system): medical classification systems to which the user's diseases and symptoms belong, such as the female reproductive system and mammary gland, urinary system, respiratory system, etc.; symptom (Symptom): user disease symptoms such as expectoration, lethargy, pain, etc.; disposal (Procedure): suggested treatment modalities, such as surgery, tooth extraction, etc.
And two types of escape relations exist in the escape word library, including an ontology escape relation and an approximate escape relation, wherein the ontology escape relation is a mapping relation in the escape word library which can be directly escaped to obtain ontology words with different dimensions, and the approximate escape relation is a mapping relation in the escape word library which converts word segmentation data into other word segmentation data. See in particular the escape word library shown in fig. 8.
After the server loads the corresponding escape word library, matching the word segmentation data obtained by word segmentation processing with the corresponding words in the escape word library, for example, matching the obtained word segmentation data with different words in the escape word library, so that the body words with different dimensionalities can be obtained, namely, the server matches the word segmentation data with different words in the escape word library, when the matching is successful, obtaining the dimensionality corresponding to the word and outputting the dimensionality and the word, for example, when the abdomen is matched, obtaining the dimensionality of the abdomen as a part, outputting 'the part, namely the abdomen', and when the abdomen is matched, obtaining the dimensionality as a symptom, outputting 'the symptom, namely pain'. The matching mode can adopt fuzzy matching, so that the matching success rate can be improved.
And S508, matching the body words with different dimensions with the attribute values of the keywords in the keyword mapping management library.
Specifically, the keyword mapping management library is a library for storing keywords and attribute values of the keywords, where each keyword corresponds to the following attribute values: department, CAT description, CAT classification, location, organ, population, symptom, disease species, cause, non-disease, specific, clinical, external cause, examination, treatment, medication, and directional weight. Wherein department = standard department name; CAT description = description of international disease classification criteria; CAT classification = international disease classification criteria code; site = a site of a human body; visceral organs = human organs; people = classification of people, such as male, female, elderly, children; symptom = symptom of disease, such as "fever"; disease species = type of disease, such as "virus infection type"; etiology = cause of disease occurrence, such as "postoperative complications"; non-disease = non-disease expressions such as "fear of obesity"; special = other; clinical = clinical presentation; extrinsic causes = external causes of disease, such as "snake bite"; exam = clinical exam, such as "X-ray exam"; treatment = clinical treatment, such as "intravenous infusion"; drug = drug name; directional weight = numeric type, positive numbers indicating that the key is valid, and negative numbers indicating that the result of a key hit is to be excluded. The larger the positive number, the closer the ranking is. Referring to fig. 9, fig. 9 is a keyword mapping management library in an embodiment. Wherein the user can match the corresponding keywords by clicking the "modify" button, the "delete" button, the "copy" button, and the like.
The matching process is mainly a process of matching the body words with the attribute values in the keywords, namely matching the body words and the keywords which are the same as the pair, and outputting the target keywords with the dimensions and the attribute values successfully matched, or optionally outputting the target keywords with the matching success rates of the dimensions and the attribute values reaching preset values.
And S510, when the attribute values of the body words with different dimensions are matched with the attribute values of the keywords in the keyword mapping management library to obtain no target keyword, marking the search record corresponding to the inquiry data as a no-search result.
Specifically, the server matches the body words with different dimensions with the attribute values of the keywords in the keyword mapping management library, and if the matching is not successful, that is, there is no keyword corresponding to the attribute value of the body word, marks the search record corresponding to the inquiry data as a no-search result, that is, as a "to-be-solved" state, which may be specifically shown in fig. 4.
Optionally, referring to the following table, in order to improve matching efficiency, when there is a combination manner of the dimensions of the attribute values in the following table, the target keyword may be matched by default, and therefore if the target keyword is not matched according to the dimension combination of the attribute values in the following table, an error may be reported so as to facilitate timely processing.
S512, when the body words with different dimensions are matched with the attribute values of the keywords in the keyword mapping management library to obtain target keywords, searching departments corresponding to the target keywords.
Specifically, when the server matches the body words with different dimensions with the attribute values of the keywords in the keyword mapping management library and obtains the corresponding target keywords, the corresponding departments are searched according to the target keywords, for example, when the search is performed according to the target keywords, the corresponding departments are matched through the directional weights.
The direction weight is one of the attribute values of the keywords, which is manually filled in when the keywords are generated, wherein the larger the value of the direction weight is, the higher the correlation degree between the corresponding attribute values and the keywords is. The direction weight can be set to be a positive value or a negative value, the positive value represents positive correlation, and the keyword should be contained when a department is obtained according to the keyword; a negative value indicates a negative correlation, and when a department is obtained from a keyword, an option including the keyword should be deleted from the obtained result.
The server obtains a corresponding department according to the direction weight, for example, whether a target keyword with a positive direction weight exists is inquired.
And S514, when the department corresponding to the target keyword is not searched, marking the search record corresponding to the inquiry data as a non-search result.
Specifically, when a department corresponding to the target keyword is not searched, specifically, when there is no target keyword with a positive direction weight, the server marks the search record corresponding to the inquiry data as a no search result, that is, as a "to-be-solved" state, which may be specifically shown in fig. 4.
And S516, when the department corresponding to the target keyword is searched, obtaining the corresponding department according to the target keyword, and recommending the obtained department to the terminal.
Specifically, after the server obtains the target keyword, the server obtains a direction weight corresponding to the target keyword, and then obtains a department corresponding to the target keyword of which the direction weight is a positive value as a final department.
For example: the method comprises the steps of obtaining a word of a user body, namely child anemia, hitting crowd, namely child anemia and symptom anemia, in keyword attributes, calculating two target keywords, namely 'pediatric' and 'otorhinolaryngology', wherein the direction weight of the 'pediatric' is 5, and the direction weight of the 'otorhinolaryngology' is-1, and therefore when departments under a search line are searched, departments with keywords comprising the 'pediatric' and not comprising the 'otorhinolaryngology' should be matched, namely, departments under the search line corresponding to the target keywords with positive matching direction weights.
Alternatively, when there are a plurality of target keywords whose directional weights are positive values, the processing may be performed as follows: firstly, target keywords are sorted according to the direction weight, for example, a positive value is arranged before a negative value, a large value is arranged before a small value, then departments corresponding to the keywords with the direction weight being the positive value are obtained, and the departments corresponding to the keywords with the maximum direction weight are used as final departments.
For example: if the user inputs inquiry data of 'baby cough and fever, nosebleed', and target keywords 'baby', 'cough and fever', and 'nosebleed', then 'baby' + 'cough and fever' is a pediatrics, but 'baby' + 'nosebleed' may possibly push out 'otorhinolaryngology', and in this case, the user is more suitable for 'pediatrics', wherein the weight of the pediatrics is +5, the weight of the otorhinolaryngology is +3, and the user excludes 'otorhinolaryngology' after sequencing by +5> + 3.
After the department is acquired, the server sends the department to the terminal, and the terminal displays the department for the user to refer to.
Optionally, after the departments are obtained and recommended to the user, the terminal can also receive a registration instruction input by the user, and the server can select the corresponding department of the hospital closest to the user for recommendation according to the registration instruction input by the user and the current position of the terminal, so that the user can register in time. The respective departments of the plurality of hospitals may optionally also be sorted by distance for selection by the user.
According to the department recommending method, after the server receives the inquiry data acquired by the terminal, word segmentation processing is firstly carried out on the inquiry data to obtain word segmentation data, then word segmentation data are deduced through an escape word library to obtain body words with different dimensions, the body words are matched with attribute values in a keyword mapping management library to obtain target keywords, and finally corresponding departments are obtained according to the target keywords, so that the departments can be recommended to the terminal, manual review is not needed, the recommending efficiency is improved, and search records without search results, such as search records without the target keywords or search records without the target keywords but without the corresponding search results according to the target keywords, can be automatically marked, and the problem that the manual marking efficiency is low is avoided.
In one embodiment, before the obtaining of the ontology words with different dimensions by deriving the word data through the escape word library, the method may further include: receiving a current scene acquired by a terminal; and loading a corresponding escape word library according to the current scene.
In one embodiment, deriving the word data by using the escape word library to obtain the body words with different dimensions may include: searching whether the word bank of the escape contains words corresponding to the current word segmentation; when the body words corresponding to the current participles exist in the escape word stock, performing dimension processing on the body words to obtain body words with different dimensions, and outputting the body words with different dimensions; when the body word corresponding to the current word does not exist in the escape word library, searching whether a similar word corresponding to the current word exists in the escape word library or not; and when the similar meaning word corresponding to the current word segmentation exists in the escape word library, updating the current word segmentation through the similar meaning word, and continuously searching whether the body word corresponding to the current word segmentation exists in the escape word library.
The current scene refers to a scene of a client where a user is located when the user uses the terminal to perform operation, where the scene is preset when the client is designed, and may include, for example, a department recommendation scene, a medicine recommendation scene, a doctor recommendation scene, and the like, and the terminal may acquire the corresponding current scene according to a position of the current client where the user operates, or acquire the corresponding current scene according to a flag bit manner.
In the server, different scenes correspond to different escape word libraries, because the same word segmentation may correspond to different body words in different scenes, for example, fever may correspond to internal medicine in a department recommendation scene, but fever may correspond to cold in a medicine recommendation scene, after the corresponding scene is obtained, the server loads the escape word library corresponding to the scene first to lay a foundation for the next derivation.
Specifically, the scene obtaining step includes that the terminal obtains a scene according to an operation position of a user, namely, the position of the operation of the user is obtained according to a preset embedded point, so that the operation position is sent to the server, the server can obtain a corresponding current operation position, and accordingly the scene where the operation position is located is judged.
Specifically, the escape word library may specifically refer to fig. 5, where the server first obtains the current participle, and then detects whether a body word corresponding to the current participle exists in the escape word library, that is, first detects whether a body word matching the current participle exists in the escape word library, where a matching manner may be performed through fuzzy matching. Optionally, in order to improve matching efficiency, threads may be subjected to synchronous matching, that is, multiple participles are distributed in different threads in a balanced manner for synchronous matching, so that matching efficiency can be improved.
When the body word corresponding to the current word segmentation exists in the escape word library, the dimension corresponding to the body word, such as the above-mentioned population, system division, part and organ, symptom, cause, examination, medicine, and clinical treatment, is obtained, for example: { part: abdomen, symptom: pain }, the server outputs the different dimension of the body word.
The synonym is a word having an approximate relationship with the current participle, when the server does not retrieve the noumenon word corresponding to the current participle, whether the synonym corresponding to the current participle exists in a retrieval word library is retrieved, wherein the retrieval can be performed according to the word library of the synonym and the synonym, the approximate relationship between the participle and the synonym is stored in the approximate relationship library, namely whether the pre-retrieval synonym corresponding to the current participle exists in the approximate relationship library is retrieved at first, and then the synonym corresponding to the pre-retrieval synonym is obtained from the translation relationship library.
When the escape relation library has the similar meaning word corresponding to the current word segmentation, the search is continuously carried out in the escape relation library through the similar meaning word, namely the body word corresponding to the similar meaning word is obtained, so that the body words with different dimensionalities corresponding to the similar meaning word can be output, and when the similar meaning word is not searched, the server returns a processing result without a search result to the terminal.
In practical application, a server firstly obtains the vocabulary after word segmentation, then carries out ontology relationship retrieval, and outputs the ontology word and the part of speech (corresponding dimensionality) of the ontology word when the ontology word exists, namely the ontology word corresponding to the vocabulary after word segmentation; when the ontology does not exist, namely the ontology word corresponding to the analyzed vocabulary does not exist, the near meaning word retrieval is continued, namely the retrieval is performed through the approximate relation, when the near meaning word is not retrieved, no result is output, when the near meaning word is retrieved, the near meaning word is continuously used as the vocabulary to be output, and the ontology relation retrieval is performed until the ontology word is output or other near meaning words do not exist.
In the above embodiment, the search is performed through the ontology relationship in the escape word library, and when the search fails, the search is performed through the approximate relationship in the escape word library, so that the accuracy of the search result is improved.
It should be understood that although the steps in the flowcharts of fig. 2 and 5 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2 and 5 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 10, there is provided a keyword adding apparatus, including: the query module 100, the input module 200, the first receiving module 300, and the storage module 400, wherein:
the query module 100 is configured to query a search record without a search result, and obtain a body word with different dimensions corresponding to the search record.
The input module 200 is configured to pop up a keyword mapping management interface, and input ontology words with different dimensions into attribute values of corresponding dimensions in the keyword mapping management interface.
The first receiving module 300 is configured to receive the entered keyword through the keyword mapping management interface.
The storage module 400 is used for associating and storing the attribute value and the keyword.
In one embodiment, the keyword adding apparatus may further include:
and the second receiving module is used for receiving a state modification instruction aiming at the attribute value and the keyword after the association storage.
And the modification module is used for modifying the state of the search record corresponding to the attribute value and the keyword after the associated storage into the search result according to the state modification instruction.
And the adding module is used for adding the attribute values and the keywords after the association storage to the keyword mapping management library.
In one embodiment, the keyword adding apparatus may further include:
and the third receiving module is used for receiving the input inquiry data acquired by the terminal.
And the word segmentation module is used for carrying out word segmentation processing on the inquiry data to obtain word segmentation data.
And the derivation module is used for deriving the word data through the escape word library to obtain the body words with different dimensions.
And the matching module is used for matching the body words with different dimensions with the attribute values of the keywords in the keyword mapping management library.
And the first marking module is used for marking the search records corresponding to the inquiry data as no search results when the attribute values of the body words with different dimensions are matched with the attribute values of the keywords in the keyword mapping management library to obtain no target keywords.
In one embodiment, the keyword adding apparatus may further include:
and the searching module is used for searching departments corresponding to the target keywords when the body words with different dimensions are matched with the attribute values of the keywords in the keyword mapping management library to obtain the target keywords.
And the second marking module is used for marking the search records corresponding to the inquiry data as no search results when departments corresponding to the target keywords are not searched.
In one embodiment, the keyword adding apparatus may further include:
and the fourth receiving module is used for receiving the current scene acquired by the terminal.
And the loading module is used for loading the corresponding escape word library according to the current scene.
In one embodiment, the derivation module may include:
and the retrieval unit is used for retrieving whether the word bank with the escape is corresponding to the current participle.
And the first derivation unit is used for performing dimension processing on the body words to obtain body words with different dimensions and outputting the body words with different dimensions when the body words corresponding to the current participle exist in the escape word bank.
And the second derivation unit is used for searching whether the similar meaning word corresponding to the current participle exists in the escape word library or not when the body word corresponding to the current participle does not exist in the escape word library.
And the third derivation unit is used for updating the current participle through the near-synonym when the near-synonym corresponding to the current participle exists in the escape word stock, and continuously searching whether the body word corresponding to the current participle exists in the escape word stock.
For the specific limitation of the keyword adding device, reference may be made to the above limitation on the keyword adding method, and details are not described herein again. All or part of the modules in the keyword newly-added device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 11. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing the data of the keyword mapping management library. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a keyword addition method.
Those skilled in the art will appreciate that the architecture shown in fig. 11 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, there is provided a computer device comprising a memory storing a computer program and a processor implementing the following steps when the processor executes the computer program: inquiring search records without search results, and acquiring body words with different dimensionalities corresponding to the search records; popping up a keyword mapping management interface, and inputting ontology words with different dimensions into attribute values of corresponding dimensions in the keyword mapping management interface; receiving input keywords through a keyword mapping management interface; the storage attribute value and the keyword are associated.
In one embodiment, the processor, when executing the computer program, further performs the steps of: receiving a state modification instruction aiming at the attribute values and the keywords which are stored in an associated mode; according to the state modification instruction, modifying the state of the search record corresponding to the attribute value and the keyword after the associated storage into the search result; and adding the attribute values and the keywords which are stored in an associated manner to a keyword mapping management library.
In one embodiment, the processor, when executing the computer program, further performs the steps of: receiving input inquiry data acquired by a terminal; performing word segmentation processing on the inquiry data to obtain word segmentation data; deducing the word data through an escape word library to obtain the body words with different dimensions; matching the body words with different dimensions with the attribute values of the keywords in the keyword mapping management library; and when the attribute values of the body words with different dimensions are matched with the attribute values of the keywords in the keyword mapping management library to obtain no target keyword, marking the search record corresponding to the inquiry data as a non-search result.
In one embodiment, the processor, when executing the computer program, further performs the steps of: when the body words with different dimensions are matched with the attribute values of the keywords in the keyword mapping management library to obtain target keywords, searching departments corresponding to the target keywords; and when the department corresponding to the target keyword is not searched, marking the search record corresponding to the inquiry data as a non-search result.
In an embodiment, before deriving the ontology words with different dimensions from the word data obtained by the processor executing the computer program through the escape word library, the method may further include: receiving a current scene acquired by a terminal; and loading a corresponding escape word library according to the current scene.
In one embodiment, the derivation of the word data by the escape lexicon to obtain the body words with different dimensions, which is implemented when the processor executes the computer program, may include: searching whether the word bank of the escape words is corresponding to the current word segmentation; when the body words corresponding to the current participles exist in the escape word stock, performing dimension processing on the body words to obtain body words with different dimensions, and outputting the body words with different dimensions; when the body word corresponding to the current word does not exist in the escape word library, searching whether a similar word corresponding to the current word exists in the escape word library or not; and when the similar meaning word corresponding to the current word segmentation exists in the escape word library, updating the current word segmentation through the similar meaning word, and continuously searching whether the body word corresponding to the current word segmentation exists in the escape word library.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of: inquiring search records without search results, and acquiring body words with different dimensionalities corresponding to the search records; popping up a keyword mapping management interface, and inputting ontology words with different dimensions into attribute values of corresponding dimensions in the keyword mapping management interface; receiving input keywords through a keyword mapping management interface; the storage attribute value and the keyword are associated.
In one embodiment, the computer program when executed by the processor further performs the steps of: receiving a state modification instruction aiming at the attribute values and the keywords which are stored in an associated mode; according to the state modification instruction, modifying the state of the search record corresponding to the attribute value and the keyword after the associated storage into the search result; and adding the attribute values and the keywords which are stored in an associated manner to a keyword mapping management library.
In one embodiment, the computer program when executed by the processor further performs the steps of: receiving input inquiry data acquired by a terminal; performing word segmentation processing on the inquiry data to obtain word segmentation data; deducing the word data through an escape word library to obtain the body words with different dimensions; matching the body words with different dimensions with the attribute values of the keywords in the keyword mapping management library; and when the attribute values of the body words with different dimensions are matched with the attribute values of the keywords in the keyword mapping management library to obtain no target keyword, marking the search record corresponding to the inquiry data as a non-search result.
In one embodiment, the computer program when executed by the processor further performs the steps of: when the body words with different dimensions are matched with the attribute values of the keywords in the keyword mapping management library to obtain target keywords, searching departments corresponding to the target keywords; and when the department corresponding to the target keyword is not searched, marking the search record corresponding to the inquiry data as a non-search result.
In one embodiment, before the derivation of ontology words with different dimensions from the word data derived from the escape word library, when the computer program is executed by the processor, the method may further include: receiving a current scene acquired by a terminal; and loading a corresponding escape word library according to the current scene.
In one embodiment, the derivation of the body words with different dimensions from the word data derived from the escape word library, which is implemented when the computer program is executed by the processor, may include: searching whether the word bank of the escape contains words corresponding to the current word segmentation; when the body words corresponding to the current participles exist in the escape word stock, performing dimension processing on the body words to obtain body words with different dimensions, and outputting the body words with different dimensions; when the body word corresponding to the current word segmentation does not exist in the escape word library, searching whether a near word corresponding to the current word segmentation exists in the escape word library or not; and when the similar meaning word corresponding to the current word segmentation exists in the escape word library, updating the current word segmentation through the similar meaning word, and continuously searching whether the body word corresponding to the current word segmentation exists in the escape word library.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A keyword adding method, the method comprising:
inquiring search records without search results, and acquiring the corresponding different-dimension local words of the search records; the search records comprise rule entry buttons, wherein the rule entry buttons are buttons used for performing addition entry operation on the search records without the search results;
popping up a keyword mapping management interface, and inputting the ontology words with different dimensions into attribute values of corresponding dimensions in the keyword mapping management interface;
receiving input keywords through the keyword mapping management interface;
storing the attribute value and the keyword in an associated manner;
the obtaining of ontology terms with different dimensions corresponding to the search records includes:
receiving input inquiry data acquired by a terminal; performing word segmentation processing on the inquiry data to obtain word segmentation data; and deducing the word segmentation data through an escape word library to obtain the body words with different dimensions.
2. The method of claim 1, further comprising:
receiving a state modification instruction for the attribute values and the keywords after associated storage;
according to the state modification instruction, modifying the state of the search record corresponding to the attribute value and the keyword after the associated storage into a search result;
and adding the attribute values and the keywords after the association storage to a keyword mapping management library.
3. The method according to claim 1 or 2, characterized in that the method further comprises:
receiving input inquiry data acquired by a terminal;
performing word segmentation processing on the inquiry data to obtain word segmentation data;
deducing the word segmentation data through an escape word library to obtain body words with different dimensions;
matching the body words with different dimensions with the attribute values of the keywords in the keyword mapping management library;
and when the attribute values of the body words with different dimensions are matched with the attribute values of the keywords in the keyword mapping management library to obtain no target keyword, marking the search record corresponding to the inquiry data as a search result.
4. The method of claim 3, further comprising:
when the body words with different dimensions are matched with the attribute values of the keywords in the keyword mapping management library to obtain target keywords, searching departments corresponding to the target keywords;
and when the department corresponding to the target keyword is not searched, marking the search record corresponding to the inquiry data as a non-search result.
5. The method of claim 3, wherein before deriving the participle data by the escape thesaurus to obtain ontology words with different dimensions, the method further comprises:
receiving a current scene acquired by the terminal;
and loading a corresponding escape word library according to the current scene.
6. The method of claim 5, wherein the deriving the participle data through an escape thesaurus to obtain ontology words with different dimensions comprises:
searching whether a body word corresponding to the current word segmentation exists in the escape word library;
when the body words corresponding to the current participles exist in the escape word stock, carrying out dimension processing on the body words to obtain body words with different dimensions, and outputting the body words with different dimensions;
when the body word corresponding to the current word segmentation does not exist in the escape word library, searching whether a near word corresponding to the current word segmentation exists in the escape word library or not;
and when the similar meaning word corresponding to the current word segmentation exists in the escape word library, updating the current word segmentation through the similar meaning word, and continuously searching whether the body word corresponding to the current word segmentation exists in the escape word library.
7. A keyword adding apparatus, the apparatus comprising:
the query module is used for querying search records without search results and acquiring the corresponding different-dimension local words of the search records; the search records comprise rule entry buttons, wherein the rule entry buttons are buttons used for performing addition entry operation on the search records without the search results;
the first input module is used for popping up a keyword mapping management interface and inputting the ontology words with different dimensions into attribute values of corresponding dimensions in the keyword mapping management interface;
the first receiving module is used for receiving input keywords through the keyword mapping management interface;
the storage module is used for storing the attribute value and the keyword in an associated manner;
the query module is also used for receiving input inquiry data acquired by the terminal; performing word segmentation processing on the inquiry data to obtain word segmentation data; and deducing the word segmentation data through an escape word library to obtain the body words with different dimensions.
8. The apparatus of claim 7, further comprising:
the second receiving module is used for receiving a state modification instruction aiming at the attribute value and the keyword after the associated storage;
the modification module is used for modifying the state of the search record corresponding to the attribute value and the keyword after the associated storage into a search result according to the state modification instruction;
and the adding module is used for adding the attribute values and the keywords after the association storage to a keyword mapping management library.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor when executing the computer program performs the steps of the method according to any of claims 1 to 6.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810551257.4A CN108874773B (en) | 2018-05-31 | 2018-05-31 | Keyword newly-adding method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810551257.4A CN108874773B (en) | 2018-05-31 | 2018-05-31 | Keyword newly-adding method and device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108874773A CN108874773A (en) | 2018-11-23 |
| CN108874773B true CN108874773B (en) | 2023-04-18 |
Family
ID=64336126
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810551257.4A Active CN108874773B (en) | 2018-05-31 | 2018-05-31 | Keyword newly-adding method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108874773B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109871380B (en) * | 2019-01-14 | 2022-11-11 | 深圳市东信时代信息技术有限公司 | Crowd pack application method and system based on Redis |
| WO2021012222A1 (en) * | 2019-07-24 | 2021-01-28 | Beijing Didi Infinity Technology And Development Co., Ltd. | Artificial intelligence system for processing patient descriptions |
| CN111125344B (en) * | 2019-12-23 | 2023-09-05 | 新方正控股发展有限责任公司 | Related word recommendation method and device |
| CN113793193B (en) * | 2021-08-13 | 2024-02-02 | 唯品会(广州)软件有限公司 | Data search accuracy verification method, device, equipment and computer readable medium |
| CN113656556B (en) * | 2021-08-20 | 2023-08-15 | 广州天宸健康科技有限公司 | Text feature extraction method and knowledge graph construction method |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103744956A (en) * | 2014-01-06 | 2014-04-23 | 同济大学 | Diversified expansion method of keyword |
| CN103744866A (en) * | 2013-12-18 | 2014-04-23 | 北京百度网讯科技有限公司 | Searching method and device |
| CN105574310A (en) * | 2014-10-13 | 2016-05-11 | 潘一琦 | Remote diagnosis and treatment service system with medical history information management function |
| CN105913846A (en) * | 2016-05-25 | 2016-08-31 | 北京云知声信息技术有限公司 | Method, device and system for realizing voice registration |
| CN106227880A (en) * | 2016-08-01 | 2016-12-14 | 挂号网（杭州）科技有限公司 | Doctor searches for the implementation method of recommendation |
| CN106610972A (en) * | 2015-10-21 | 2017-05-03 | 阿里巴巴集团控股有限公司 | Query rewriting method and apparatus |
| CN107526932A (en) * | 2017-08-30 | 2017-12-29 | 河北健康侍卫网络科技有限公司 | Section office register guidance method and terminal device |
| CN107680660A (en) * | 2016-07-27 | 2018-02-09 | 百度在线网络技术（北京）有限公司 | Recommend the method and apparatus of doctor |
| CN107767963A (en) * | 2016-08-15 | 2018-03-06 | 腾讯科技（深圳）有限公司 | The method and apparatus that health and fitness information obtains |
-
2018
- 2018-05-31 CN CN201810551257.4A patent/CN108874773B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103744866A (en) * | 2013-12-18 | 2014-04-23 | 北京百度网讯科技有限公司 | Searching method and device |
| CN103744956A (en) * | 2014-01-06 | 2014-04-23 | 同济大学 | Diversified expansion method of keyword |
| CN105574310A (en) * | 2014-10-13 | 2016-05-11 | 潘一琦 | Remote diagnosis and treatment service system with medical history information management function |
| CN106610972A (en) * | 2015-10-21 | 2017-05-03 | 阿里巴巴集团控股有限公司 | Query rewriting method and apparatus |
| CN105913846A (en) * | 2016-05-25 | 2016-08-31 | 北京云知声信息技术有限公司 | Method, device and system for realizing voice registration |
| CN107680660A (en) * | 2016-07-27 | 2018-02-09 | 百度在线网络技术（北京）有限公司 | Recommend the method and apparatus of doctor |
| CN106227880A (en) * | 2016-08-01 | 2016-12-14 | 挂号网（杭州）科技有限公司 | Doctor searches for the implementation method of recommendation |
| CN107767963A (en) * | 2016-08-15 | 2018-03-06 | 腾讯科技（深圳）有限公司 | The method and apparatus that health and fitness information obtains |
| CN107526932A (en) * | 2017-08-30 | 2017-12-29 | 河北健康侍卫网络科技有限公司 | Section office register guidance method and terminal device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108874773A (en) | 2018-11-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108874773B (en) | Keyword newly-adding method and device, computer equipment and storage medium | |
| US11694297B2 (en) | Determining appropriate medical image processing pipeline based on machine learning | |
| CN109215754A (en) | Medical record data processing method, device, computer equipment and storage medium | |
| WO2021184567A1 (en) | Electronic health record query method and apparatus, computer device, and storage medium | |
| EP3895178A1 (en) | System and method for providing health information | |
| CN108986910B (en) | On-line question and answer method, device, computer equipment and storage medium | |
| WO2021139232A1 (en) | Medical knowledge graph-based triage method and apparatus, device, and storage medium | |
| CN109065172B (en) | Disease information acquisition method and device, computer equipment and storage medium | |
| CN109933785A (en) | Method, apparatus, equipment and medium for entity associated | |
| WO2023029506A1 (en) | Illness state analysis method and apparatus, electronic device, and storage medium | |
| CN109887596A (en) | Chronic obstructive disease of lung diagnostic method, device and the computer equipment of knowledge based map | |
| CN109065129A (en) | Department's recommended method, device, computer equipment and storage medium | |
| CN111627512A (en) | Recommendation method and device for similar medical records, electronic equipment and storage medium | |
| WO2023029513A1 (en) | Artificial intelligence-based search intention recognition method and apparatus, device, and medium | |
| WO2020052162A1 (en) | Disease data mapping method and device, computer device and storage medium | |
| CN110413751B (en) | Medicine searching method, device, terminal equipment and storage medium | |
| CN112037904A (en) | Online diagnosis and treatment data processing method and device, computer equipment and storage medium | |
| JP2023514023A (en) | Question retrieval device, question retrieval method, device, and storage medium | |
| WO2020034808A1 (en) | Decision data acquisition method and apparatus, computer device, and storage medium | |
| Kirchhoff et al. | Unsupervised resolution of acronyms and abbreviations in nursing notes using document-level context models | |
| CN111986759A (en) | Method and system for analyzing electronic medical record, computer equipment and readable storage medium | |
| CN111444686A (en) | Medical data labeling method, device, storage medium and computer equipment | |
| WO2023178970A1 (en) | Medical data processing method, apparatus and device, and storage medium | |
| CN113657109A (en) | Method, apparatus and computer device for standardization of model-based clinical terminology | |
| Magnini et al. | Comparing machine learning and deep learning approaches on NLP tasks for the Italian language |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |