CN110232071A - Search method, device and storage medium, the electronic device of drug data - Google Patents
Search method, device and storage medium, the electronic device of drug data Download PDFInfo
- Publication number
- CN110232071A CN110232071A CN201910345736.5A CN201910345736A CN110232071A CN 110232071 A CN110232071 A CN 110232071A CN 201910345736 A CN201910345736 A CN 201910345736A CN 110232071 A CN110232071 A CN 110232071A
- Authority
- CN
- China
- Prior art keywords
- drug
- entry
- search key
- attribute information
- drug entry
- 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
- 239000003814 drug Substances 0.000 title claims abstract description 295
- 229940079593 drug Drugs 0.000 title claims abstract description 241
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000004590 computer program Methods 0.000 claims description 11
- 230000011218 segmentation Effects 0.000 claims description 7
- 230000000694 effects Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 3
- 206010067484 Adverse reaction Diseases 0.000 description 2
- 208000036071 Rhinorrhea Diseases 0.000 description 2
- 206010039101 Rhinorrhoea Diseases 0.000 description 2
- 230000006838 adverse reaction Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 206010047700 Vomiting Diseases 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 208000002173 dizziness Diseases 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000009415 formwork Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000008673 vomiting Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Probability & Statistics with Applications (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of search method of drug data, device and storage mediums, electronic device, wherein the search method of drug data includes: the medicine types label for obtaining input；According to medicine types label, the drug item list of medicine types tag match is retrieved in drug data bank；Obtain the search key of input；Search key is split, multiple search keys are obtained；For the attribute information of each drug entry in drug item list, gap character number that the frequency of occurrence and the adjacent keyword of every two for counting each search key occur in attribute information；It is determined according to statistical result and recommends drug entry.Through the invention, search result inaccuracy when solving the retrieval in the prior art for drug data.
Description
Technical field
The present invention relates to searching fields, are situated between in particular to a kind of search method of drug data, device and storage
Matter, electronic device.
Background technique
Medical drugs are many kinds of, to each attributes of each medical drugs (for example, effect, indication, taboo crowd,
Adverse reaction etc.) word content that is introduced is also more, it is examined in the database of medical drugs based on keyword
The time cost of rope is higher, also, due to the specific properties of medical domain, it is not exactly the same to be frequently present of the identical vocabulary of meaning
The case where, if still scanned for using keyword, it will lead to the case where can not searching related drug.
For the above problem present in the relevant technologies, at present it is not yet found that the solution of effect.
Summary of the invention
The embodiment of the invention provides a kind of search method of drug data, device and storage mediums, electronic device, so that
Search result inaccuracy when the retrieval in the prior art for drug data is solved the problems, such as less.
According to one embodiment of present invention, a kind of search method of drug data is provided, this method comprises: obtaining defeated
The medicine types label entered；According to medicine types label, the drug item of medicine types tag match is retrieved in drug data bank
Mesh list；Obtain the search key of input；Search key is split, multiple search keys are obtained；For drug entry column
The attribute information of each drug entry in table counts the frequency of occurrence and the adjacent key of every two of each search key
The gap character number that word occurs in attribute information；It is determined according to statistical result and recommends drug entry.
Further, it is determined according to statistical result and recommends drug entry, comprising: according to each search key of statistics
Frequency of occurrence determines the total degree n that multiple search keys occur in the attribute information of each drug entry；According to statistics
The gap character number that the adjacent keyword of every two occurs in attribute information determines in the attribute information of each drug entry
The sum of the gap character number that the adjacent search key of any two occurs in multiple search keys t；Based on numerical value n and numerical value
T determines recommendation, wherein in the case where numerical value n is bigger, in the case that recommendation is bigger, and numerical value t is smaller, recommendation is got over
Greatly；The higher preceding m drug entry of recommendation is obtained, obtains recommending drug entry.
Further, for the attribute information of each drug entry in drug item list, the adjacent pass of every two is counted
The gap character number that key word occurs in attribute information, comprising: determine the adjacent retrieval of any two in multiple search keys
Crucial combinatorics on words；For two adjacent search key a and b in each combination, in the attribute information of each drug entry
Sequentially there is the character pitch number between a and b every time in middle retrieval.
Further, the character pitch sequentially occurred between a and b every time is retrieved in the attribute information of each drug entry
Number, comprising: word for word retrieve a from the front to the back in the attribute information of each drug entry；After being matched to a, word for word examine backward
Rope a and b, and present interval number of characters is counted；If a is matched to again when word for word retrieving a and b backward, to current
Gap character number counts again；If being matched to b when word for word retrieving a and b backward, present interval number of characters is recorded；From current
Character rises, and returns to the step of word for word retrieving a from the front to the back, until the attribute information retrieval to drug entry finishes.
Further, adjacent in statistics every two for the attribute information of each drug entry in drug item list
Before the gap character number that keyword occurs in attribute information, the frequency of occurrence and record of each search key are counted,
In determining multiple search keys after the combination of the adjacent search key of any two, this method further include: for each
Drug entry, according to the record of the frequency of occurrence of each search key as a result, determining in the attribute information of corresponding drug entry
The search key not occurred；Among the combination of the adjacent search key of any two, deletes the retrieval for including do not occur and close
Key combinatorics on words.
Further, according to medicine types label, the drug of medicine types tag match is retrieved in drug data bank
Before item list, this method further include: word segmentation processing is executed to the attribute information of each drug entry in drug data bank,
Obtain the corresponding multiple participles of each drug entry；For each drug entry, multiple keys are extracted in the multiple participles of correspondence
Word；Respectively by multiple keywords input topic model that training obtains in advance of each drug entry, the defeated of topic model is obtained
Result out, wherein topic model is used for the theme label according to the output prediction of multiple words of input；By topic model for each
Medicine types label of the theme label of multiple keywords output of drug entry as corresponding drug entry.
Further, using topic model for each drug entry multiple keywords export theme label as pair
After the medicine types label for answering drug entry, this method further include: newly-increased to each drug entry in drug data bank to belong to
Property, wherein the value of the newly-increased attribute of each drug entry is the medicine types label of corresponding drug entry；Based on newly-increased attribute
Index is established to the drug entry in drug data bank.
According to another embodiment of the invention, a kind of retrieval device of drug data is provided, which includes: first
Module is obtained, for obtaining the medicine types label of input；Retrieval module is used for according to medicine types label, in drug data
The drug item list of medicine types tag match is retrieved in library；Second obtains module, for obtaining the search key of input；
It splits module and obtains multiple search keys for splitting search key；Statistical module, for being directed to drug item list
In each drug entry attribute information, count the frequency of occurrence and the adjacent keyword of every two of each search key
The gap character number occurred in attribute information；Determining module recommends drug entry for determining according to statistical result.
Further, it is determined that module includes: the first determination unit, for the appearance according to each search key of statistics
Number determines the total degree n that multiple search keys occur in the attribute information of each drug entry；Second determination unit,
For the gap character number that the adjacent keyword of every two according to statistics occurs in attribute information, determine in each drug item
The sum of the gap character number that the adjacent search key of any two occurs in multiple search keys in purpose attribute information t；
Third determination unit, for determining recommendation based on numerical value n and numerical value t, wherein in the case where numerical value n is bigger, recommendation is got over
Greatly, and in the case that numerical value t is smaller, recommendation is bigger；Acquiring unit, for obtaining the higher preceding m drug entry of recommendation,
It obtains recommending drug entry.
Further, statistical module includes: the 4th determination unit, for determining any two phase in multiple search keys
The combination of adjacent search key；First retrieval unit, two adjacent search key a and b for being directed in each combination,
The character pitch number sequentially occurred between a and b every time is retrieved in the attribute information of each drug entry.
Further, retrieval unit includes: the second retrieval unit, in the attribute information of each drug entry by preceding
A is word for word retrieved backward；First execution unit, for word for word retrieving a and b backward, and to present interval word after being matched to a
Symbol number is counted；Second execution unit, if for being matched to a again when word for word retrieving a and b backward, to present interval
Number of characters counts again；Third execution unit, if recording present interval for being matched to b when word for word retrieving a and b backward
Number of characters；4th execution unit, for from current character, returning to the step of word for word retrieving a from the front to the back, until to drug item
The retrieval of purpose attribute information finishes.
Further, statistical module is used to unite for the attribute information of each drug entry in drug item list
Before the gap character number that the adjacent keyword of meter every two occurs in attribute information, the appearance of each search key is counted
Number simultaneously records, the device further include: the 5th determination unit, for the adjacent inspection of any two in determining multiple search keys
After Suo Guanjian combinatorics on words, for each drug entry, according to the record of the frequency of occurrence of each search key as a result, really
Surely the search key not occurred in the attribute information of drug entry is corresponded to；Unit is deleted, in the adjacent retrieval of any two
Among crucial combinatorics on words, the combination of the search key including not occurring is deleted.
Further, the device further include: word segmentation module, for according to medicine types label, in drug data bank
Before the drug item list for retrieving medicine types tag match, to the attribute information of each drug entry in drug data bank
Word segmentation processing is executed, the corresponding multiple participles of each drug entry are obtained；Extraction module, for being directed to each drug entry,
Multiple keywords are extracted in corresponding multiple participles；Execution module, for respectively inputting multiple keywords of each drug entry
The topic model that training obtains in advance, obtains the output result of topic model, wherein topic model is used for according to the multiple of input
The theme label of word output prediction；Logic module is exported for multiple keywords by topic model for each drug entry
Medicine types label of the theme label as corresponding drug entry.
Further, the device further include: newly-increased module, for topic model to be directed to the multiple of each drug entry
After medicine types label of the theme label of keyword output as corresponding drug entry, to each medicine in drug data bank
Product entry increases attribute newly, wherein the value of the newly-increased attribute of each drug entry is the medicine types label of corresponding drug entry；It builds
Formwork erection block, for establishing index to the drug entry in drug data bank based on newly-increased attribute.
According to still another embodiment of the invention, a kind of storage medium is additionally provided, meter is stored in the storage medium
Calculation machine program, wherein the computer program is arranged to execute the step in any of the above-described embodiment of the method when operation.
According to still another embodiment of the invention, a kind of electronic device, including memory and processor are additionally provided, it is described
Computer program is stored in memory, the processor is arranged to run the computer program to execute any of the above-described
Step in embodiment of the method.
Through the invention, by obtaining the medicine types label inputted；According to medicine types label, in drug data bank
Retrieve the drug item list of medicine types tag match；Obtain the search key of input；Search key is split, is obtained more
A search key；For the attribute information of each drug entry in drug item list, each search key is counted
The gap character number that frequency of occurrence and the adjacent keyword of every two occur in attribute information；It is determined according to statistical result
Recommend drug entry, search result inaccuracy when solving the retrieval in the prior art for drug data, by obtaining simultaneously
The retrieval for taking medicine types label and search key to obtain user with carrying out various dimensions is intended to, and for search key, performs
The processing method for splitting search key, is accurate to the frequency of occurrence of each search key and two neighboring search key,
The case where user search keyword and the retrieval of medical drugs term difference are less than hitting target is prevented, has been reached more accurately
For the technical effect of user search purpose feedback searching result.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes part of this application, this hair
Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.In the accompanying drawings:
Fig. 1 is the flow chart of the search method of drug data according to an embodiment of the present invention；
Fig. 2 is the schematic diagram of the retrieval device of drug data according to an embodiment of the present invention.
Specific embodiment
In order to make those skilled in the art more fully understand application scheme, below in conjunction in the embodiment of the present application
Attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is only
The embodiment of the application a part, instead of all the embodiments, in the absence of conflict, embodiment and reality in the application
The feature applied in example can be combined with each other.Based on the embodiment in the application, those of ordinary skill in the art are not making wound
Every other embodiment obtained under the premise of the property made labour, shall fall within the protection scope of the present application.
It should be noted that the description and claims of this application and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so as to embodiments herein described herein can in addition to illustrating herein or
Sequence other than those of description is implemented.In addition, term " includes " and " having " and their any deformation, it is intended that cover
Cover it is non-exclusive include, for example, the process, method, system, product or equipment for containing a series of steps or units are not necessarily limited to
Step or unit those of is clearly listed, but may include be not clearly listed or for these process, methods, product
Or other step or units that equipment is intrinsic.
Embodiment 1
The search method for present embodiments providing a kind of drug data, can be applied to client-side, for example, can run
Among the middle terminal device such as similar arithmetic facility of PC, work station, mobile terminal, specifically, client-side can be with
It is the function that retrieval is realized by browser or client application.Operating in different arithmetic facilities only is scheme in executing subject
On difference, those skilled in the art are contemplated that in nonidentity operation equipment, operation can generate identical technical effect.
The search method of drug data provided in this embodiment, by obtaining medicine types label and search key simultaneously
Obtain user retrieval with carrying out various dimensions is intended to, and for search key, performs the processing method for splitting search key, essence
The frequency of occurrence for really arriving each search key and two neighboring search key prevents user search keyword and medicine
The case where retrieval of drug term difference is less than hitting target has reached more accurately for user search purpose feedback searching result
Technical effect.
As shown in Figure 1, the search method of drug data provided in this embodiment includes the following steps:
Step 101, the medicine types label of input is obtained；
Step 102, according to medicine types label, the drug entry of medicine types tag match is retrieved in drug data bank
List；
Step 103, the search key of input is obtained；
Step 104, search key is split, multiple search keys are obtained；
Step 105, for the attribute information of each drug entry in drug item list, each search key is counted
Frequency of occurrence and the gap character number that occurs in attribute information of the adjacent keyword of every two；
Step 106, it is determined according to statistical result and recommends drug entry.
Drug data bank in the present embodiment is relevant database, for storing multiple drug entries, each drug item
Mesh includes multiple attributes, and the attribute value of each attribute is the information of corresponding attribute, for example, for drug A, the category of " effect " attribute
Property value be " treatment xxx class disease ", the attribute value of " adverse reaction " attribute is " occasionally having vomiting, dizziness ".It can in drug data bank
Multiple drug entries are saved in the form of through table, every data line corresponds to a drug entry, and each column data is corresponding
In an attribute.
Drug entry in drug data bank can be indexed by medicine types label.Medicine types label can be
One attribute is indexed as inside, can also additionally set up an external index.Based on the index of medicine types label, if
The execution side of one or more medicine types labels of user input selection, the present embodiment can be according to the subject classification mark of input
Label, retrieve the multiple drug entries (drug item list) being matched in drug data bank.
In addition to needing user to input medicine types label, it is also necessary to which user inputs search key.In order to increase search
Keyword is split as multiple keywords, counts drug entry by range, the search key non-medical term for preventing user from inputting
There is the number of each keyword in each drug entry in list and the adjacent keyword of every two occurs in drug entry
Gap character number, thus based on statistical result determine recommend drug entry.
Recommend drug entry specifically, determining according to statistical result, may include:
Step 11, it according to the frequency of occurrence of each search key of statistics, determines and believes in the attribute of each drug entry
The total degree n that multiple search keys occur in breath；
Step 12, the gap character number occurred in attribute information according to the adjacent keyword of the every two of statistics determines
The interval word that the adjacent search key of any two occurs in multiple search keys in the attribute information of each drug entry
Accord with the sum of number t；
Step 13, recommendation is determined based on numerical value n and numerical value t, wherein in the case where numerical value n is bigger, recommendation is got over
Greatly, and in the case that numerical value t is smaller, recommendation is bigger；
Step 14, the higher preceding m drug entry of recommendation is obtained, obtains recommending drug entry.
For example, being split as search key " stream ", " nose " and " tears ", such as if search key includes " rhinorrhea "
There are sentence " stuffy nose with watery discharge " in fruit drug entry, then " flowing " the gap character number between " nose " is 1, " nose " and " tears "
Between gap character number be 1, for sentence " stuffy nose with watery discharge ", the sum of gap character number is 2.
The function for calculating recommendation can be f (n/t), and recommendation is directly proportional to the size of numerical value n, the size with numerical value t
It is inversely proportional, that is, recommendation is directly proportional to the total degree for all keywords occur, with two neighboring keyword in drug entry
The sum of gap character number of appearance is inversely proportional, thus, recommendation can show that degree relevant to keyword, drug entry
Recommendation is higher, illustrates that the keyword degree of correlation of drug entry and input is higher.
Optionally, in the attribute information for each drug entry in drug item list, the adjacent pass of statistics every two
When the gap character number that key word occurs in attribute information, following steps can be used:
Step 21, the combination of the adjacent search key of any two in multiple search keys is determined；
For example, it is split as multiple search keys " stream ", " nose " and " tears " if search key is " rhinorrhea ",
Obtain the combination of the adjacent search key of any two: " stream " and " nose " and " nose " and " tears ".
Step 22, for two adjacent search key a and b in each combination, believe in the attribute of each drug entry
The character pitch number sequentially occurred between a and b every time is retrieved in breath, that is, being counted for each combination.
Specifically, retrieving the character pitch number sequentially occurred between a and b every time in the attribute information of each drug entry
When, include the following steps:
Step 31, a is word for word retrieved from the front to the back in the attribute information of each drug entry；
Step 32, after being matched to a, a and b is word for word retrieved backward, and count to present interval number of characters；
Step 33, if being matched to a again when word for word retrieving a and b backward, present interval number of characters is counted again；
Step 34, if being matched to b when word for word retrieving a and b backward, present interval number of characters is recorded；
Step 35, from current character, the step of word for word retrieving a from the front to the back is returned to, until to the attribute of drug entry
Information retrieval finishes.
Optionally, in step 105, it for the attribute information of each drug entry in drug item list, is counting
Before the gap character number that the adjacent keyword of every two occurs in attribute information, executes and count going out for each search key
Occurrence number simultaneously records.In turn, in determining multiple search keys after the combination of the adjacent search key of any two, for
Each drug entry, according to the record of the frequency of occurrence of each search key as a result, determining that the attribute of corresponding drug entry is believed
The search key not occurred in breath, among the combination of the adjacent search key of any two, deleting includes the inspection not occurred
Suo Guanjian combinatorics on words.
For example, if statistics search key abcd in search key b frequency of occurrence be 0, without count a and b,
The sum of combined gap character number of b and c.
Further, according to medicine types label, the drug of medicine types tag match is retrieved in drug data bank
Before item list, this method further include: word segmentation processing is executed to the attribute information of each drug entry in drug data bank,
Obtain the corresponding multiple participles of each drug entry；For each drug entry, multiple keys are extracted in the multiple participles of correspondence
Word；Respectively by multiple keywords input topic model that training obtains in advance of each drug entry, the defeated of topic model is obtained
Result out, wherein topic model is used for the theme label according to the output prediction of multiple words of input；By topic model for each
Medicine types label of the theme label of multiple keywords output of drug entry as corresponding drug entry.
Optionally, in the theme label for multiple keywords output that topic model is directed to each drug entry as correspondence
After the medicine types label of drug entry, in drug data bank newly attribute is increased to each drug entry, wherein each drug
The value of the newly-increased attribute of entry is the medicine types label of corresponding drug entry, in turn, based on newly-increased attribute to drug data
Drug entry in library establishes index.
It should be noted that step shown in the flowchart of the accompanying drawings can be in such as a group of computer-executable instructions
It is executed in computer system, although also, logical order is shown in flow charts, and it in some cases, can be with not
The sequence being same as herein executes shown or described step.
Through the above description of the embodiments, those skilled in the art can be understood that according to above-mentioned implementation
The method of example can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but it is very much
In the case of the former be more preferably embodiment.Based on this understanding, technical solution of the present invention is substantially in other words to existing
The part that technology contributes can be embodied in the form of software products, which is stored in a storage
In medium (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that a terminal device (can be mobile phone, calculate
Machine, server or network equipment etc.) execute method described in each embodiment of the present invention.
Embodiment 2
A kind of retrieval device of drug data is additionally provided in the present embodiment, and the device is for realizing above-described embodiment 1
And its preferred embodiment, to the term or implementation not being described in detail in this present embodiment, reference can be made to mutually speaking on somebody's behalf in embodiment 1
Bright, the descriptions that have already been made will not be repeated.
Term " module " as used below, can be achieved on the combination of the software and/or hardware of predetermined function.Although
Device described in following embodiment is preferably realized with software, but the combined realization of hardware or software and hardware
And can be contemplated.
Fig. 2 is the schematic diagram of the retrieval device of drug data according to an embodiment of the present invention, as shown in Fig. 2, the device packet
The first acquisition module 10 is included, retrieval module 20, second obtains module 30, splits module 40, statistical module 50 and determining module 60.
First acquisition module 10 is used to obtain the medicine types label of input；Retrieval module 20 is used for according to medicine types mark
Label retrieve the drug item list of medicine types tag match in drug data bank；Second acquisition module 30 is defeated for obtaining
The search key entered；Module 40 is split for splitting search key, obtains multiple search keys；Statistical module 50 is used for
For the attribute information of each drug entry in drug item list, count each search key frequency of occurrence and
The gap character number that the adjacent keyword of every two occurs in attribute information；Determining module 60 is used to be determined according to statistical result
Recommend drug entry.
Optionally, determining module includes: the first determination unit, for going out occurrence according to each search key of statistics
Number determines the total degree n that multiple search keys occur in the attribute information of each drug entry；Second determination unit is used
In the gap character number that the adjacent keyword of every two according to statistics occurs in attribute information, determine in each drug entry
Attribute information in the sum of the adjacent search key of any two occurs in multiple search keys gap character number t；The
Three determination units, for determining recommendation based on numerical value n and numerical value t, wherein in the case where numerical value n is bigger, recommendation is got over
Greatly, and in the case that numerical value t is smaller, recommendation is bigger；Acquiring unit, for obtaining the higher preceding m drug entry of recommendation,
It obtains recommending drug entry.
Optionally, statistical module includes: the 4th determination unit, and for determining, any two are adjacent in multiple search keys
The combination of search key；First retrieval unit, two adjacent search key a and b for being directed in each combination, every
The character pitch number sequentially occurred between a and b every time is retrieved in the attribute information of a drug entry.
Optionally, retrieval unit includes: the second retrieval unit, in the attribute information of each drug entry by forward direction
A is word for word retrieved afterwards；First execution unit, for word for word retrieving a and b backward, and to present interval character after being matched to a
Number is counted；Second execution unit, if for being matched to a again when word for word retrieving a and b backward, to present interval word
Symbol number counts again；Third execution unit, if recording present interval word for being matched to b when word for word retrieving a and b backward
Accord with number；4th execution unit, for from current character, returning to the step of word for word retrieving a from the front to the back, until to drug entry
Attribute information retrieval finish.
Optionally, statistical module is used to count for the attribute information of each drug entry in drug item list
Before the gap character number that the adjacent keyword of every two occurs in attribute information, count each search key goes out occurrence
It counts and records, the device further include: the 5th determination unit, for the adjacent retrieval of any two in determining multiple search keys
After crucial combinatorics on words, for each drug entry, according to the record of the frequency of occurrence of each search key as a result, determining
The search key not occurred in the attribute information of corresponding drug entry；Unit is deleted, for closing in the adjacent retrieval of any two
Among key combinatorics on words, the combination of the search key including not occurring is deleted.
Optionally, the device further include: word segmentation module, for being examined in drug data bank according to medicine types label
Before the drug item list of rope medicine types tag match, the attribute information of each drug entry in drug data bank is held
Row word segmentation processing obtains the corresponding multiple participles of each drug entry；Extraction module, for being directed to each drug entry, right
It answers and extracts multiple keywords in multiple participles；Execution module inputs multiple keywords of each drug entry for respectively pre-
The first topic model that training obtains, obtains the output result of topic model, wherein topic model is used for multiple words according to input
Export the theme label of prediction；Logic module, for export topic model for multiple keywords of each drug entry
Medicine types label of the theme label as corresponding drug entry.
Optionally, the device further include: newly-increased module, in multiple passes that topic model is directed to each drug entry
After medicine types label of the theme label of keyword output as corresponding drug entry, to each drug in drug data bank
Entry increases attribute newly, wherein the value of the newly-increased attribute of each drug entry is the medicine types label of corresponding drug entry；It establishes
Module, for establishing index to the drug entry in drug data bank based on newly-increased attribute.
It should be noted that above-mentioned modules can be realized by software or hardware, for the latter, Ke Yitong
Following manner realization is crossed, but not limited to this: above-mentioned module is respectively positioned in same processor；Alternatively, above-mentioned modules are with any
Combined form is located in different processors.
Obviously, those skilled in the art should be understood that each module of the above invention or each step can be with general
Computing device realize that they can be concentrated on a single computing device, or be distributed in multiple computing devices and formed
Network on, optionally, they can be realized with the program code that computing device can perform, it is thus possible to which they are stored
It is performed by computing device in the storage device, and in some cases, it can be to be different from shown in sequence execution herein
Out or description the step of, perhaps they are fabricated to each integrated circuit modules or by them multiple modules or
Step is fabricated to single integrated circuit module to realize.In this way, the present invention is not limited to any specific hardware and softwares to combine.
Embodiment 3
The embodiments of the present invention also provide a kind of storage medium, computer program is stored in the storage medium, wherein
The computer program is arranged to execute the step in any of the above-described embodiment of the method when operation.
Optionally, in the present embodiment, above-mentioned storage medium can include but is not limited to: USB flash disk, read-only memory (Read-
OnlyMemory, referred to as ROM), random access memory (Random AccessMemory, referred to as RAM), mobile hard disk,
The various media that can store computer program such as magnetic or disk.
Embodiment 4
The embodiments of the present invention also provide a kind of electronic device, including memory and processor, stored in the memory
There is computer program, which is arranged to run computer program to execute the step in any of the above-described embodiment of the method
Suddenly.
Optionally, above-mentioned electronic device can also include transmission device and input-output equipment, wherein the transmission device
It is connected with above-mentioned processor, which connects with above-mentioned processor.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.It is all within principle of the invention, it is made it is any modification, etc.
With replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of search method of drug data, which is characterized in that the described method includes:
Obtain the medicine types label of input；
According to the medicine types label, the drug entry column of the medicine types tag match is retrieved in drug data bank
Table；
Obtain the search key of input；
The search key is split, multiple search keys are obtained；
For the attribute information of each drug entry in the drug item list, going out for each search key is counted
The gap character number that occurrence number and the adjacent keyword of every two occur in the attribute information；
It is determined according to statistical result and recommends drug entry.
2. being wrapped the method according to claim 1, wherein described determined according to statistical result recommends drug entry
It includes:
According to the frequency of occurrence of each of statistics search key, determine in the attribute information of each drug entry
The total degree n that the multiple search key occurs；
According to the gap character number that the adjacent keyword of the every two of statistics occurs in the attribute information, determine in each institute
State the interval word that the adjacent search key of any two in multiple search keys described in the attribute information of drug entry occurs
Accord with the sum of number t；
Recommendation is determined based on numerical value n and numerical value t, wherein in the case where the numerical value n is bigger, the recommendation is bigger, and
In the case that the numerical value t is smaller, the recommendation is bigger；
The higher preceding m drug entry of the recommendation is obtained, the recommendation drug entry is obtained.
3. according to the method described in claim 2, it is characterized in that, each drug in the drug item list
The attribute information of entry, the gap character number that the adjacent keyword of statistics every two occurs in the attribute information, comprising:
Determine the combination of the adjacent search key of any two in the multiple search key；
For two adjacent search key a and b in each combination, in the attribute information of each drug entry
Sequentially there is the character pitch number between a and b every time in retrieval.
4. according to the method described in claim 3, it is characterized in that, described examine in the attribute information of each drug entry
Sequentially there is the character pitch number between a and b every time in rope, comprising:
A is word for word retrieved from the front to the back in the attribute information of each drug entry；
After being matched to a, a and b is word for word retrieved backward, and count to present interval number of characters；
If being matched to a again when word for word retrieving a and b backward, the present interval number of characters is counted again；
If being matched to b when word for word retrieving a and b backward, the present interval number of characters is recorded；
From current character, the step of word for word retrieving a from the front to the back is returned to, until the attribute information to the drug entry is retrieved
It finishes.
5. according to the method described in claim 3, it is characterized in that, for each drug entry in the drug item list
Attribute information, before the gap character number that the adjacent keyword of statistics every two occurs in the attribute information, statistics
The frequency of occurrence and record of each search key, the adjacent retrieval of any two in determining the multiple search key
After crucial combinatorics on words, the method also includes:
For each drug entry, corresponded to according to the record of the frequency of occurrence of each search key as a result, determining
The search key not occurred in the attribute information of drug entry；
Among the combination of the adjacent search key of any two, the group for the search key not occurred described in including is deleted
It closes.
6. the method according to claim 1, wherein according to the medicine types label, in drug data bank
Before the drug item list of the middle retrieval medicine types tag match, the method also includes:
Word segmentation processing is executed to the attribute information of each of the drug data bank drug entry, obtains each medicine
The corresponding multiple participles of product entry；
For each drug entry, multiple keywords are extracted in the multiple participle of correspondence；
Respectively by multiple keywords input topic model that training obtains in advance of each drug entry, the theme is obtained
The output result of model, wherein the topic model is used for the theme label according to the output prediction of multiple words of input；
The theme label that multiple keywords that the topic model is directed to each drug entry are exported is as corresponding drug
The medicine types label of entry.
7. according to the method described in claim 6, it is characterized in that, the topic model is directed to each drug entry
Multiple keywords output theme label as correspondence drug entry medicine types label after, the method also includes:
In the drug data bank newly attribute is increased to each drug entry, wherein what each drug entry increased newly
The value of attribute is the medicine types label of corresponding drug entry；
Index is established to the drug entry in the drug data bank based on the newly-increased attribute.
8. a kind of retrieval device of drug data, which is characterized in that described device includes:
First obtains module, for obtaining the medicine types label of input；
Retrieval module, for retrieving the medicine types tag match in drug data bank according to the medicine types label
Drug item list；
Second obtains module, for obtaining the search key of input；
It splits module and obtains multiple search keys for splitting the search key；
Statistical module counts each described for the attribute information for each drug entry in the drug item list
The gap character number that the adjacent keyword of frequency of occurrence and every two of search key occurs in the attribute information；
Determining module recommends drug entry for determining according to statistical result.
9. a kind of storage medium, which is characterized in that be stored with computer program in the storage medium, wherein the computer
Program is arranged to perform claim when operation and requires method described in 1 to 7 any one.
10. a kind of electronic device, including memory and processor, which is characterized in that be stored with computer journey in the memory
Sequence, the processor are arranged to run the computer program in method described in perform claim 1 to 7 any one of requirement.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910345736.5A CN110232071A (en) | 2019-04-26 | 2019-04-26 | Search method, device and storage medium, the electronic device of drug data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910345736.5A CN110232071A (en) | 2019-04-26 | 2019-04-26 | Search method, device and storage medium, the electronic device of drug data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110232071A true CN110232071A (en) | 2019-09-13 |
Family
ID=67860369
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910345736.5A Pending CN110232071A (en) | 2019-04-26 | 2019-04-26 | Search method, device and storage medium, the electronic device of drug data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110232071A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111198887A (en) * | 2019-12-31 | 2020-05-26 | 北京左医健康技术有限公司 | Medicine indexing method, medicine retrieval method and system |
| CN112307180A (en) * | 2020-10-22 | 2021-02-02 | 上海芯翌智能科技有限公司 | Rapid retrieval method and device based on label object |
| CN115359924A (en) * | 2022-08-11 | 2022-11-18 | 浙江迪谱诊断技术有限公司 | Cardiovascular and cerebrovascular medicine scoring method and device, storage medium and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010282480A (en) * | 2009-06-05 | 2010-12-16 | Nippon Telegr & Teleph Corp <Ntt> | Retrieval result ranking method, device and program, and computer-readable recording medium |
| CN102043812A (en) * | 2009-10-13 | 2011-05-04 | 北京大学 | Method and system for retrieving medical information |
| CN106024013A (en) * | 2016-04-29 | 2016-10-12 | 努比亚技术有限公司 | Voice data searching method and system |
| CN106776741A (en) * | 2016-11-18 | 2017-05-31 | 北京奇虎科技有限公司 | A kind of searching method and device |
-
2019
- 2019-04-26 CN CN201910345736.5A patent/CN110232071A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010282480A (en) * | 2009-06-05 | 2010-12-16 | Nippon Telegr & Teleph Corp <Ntt> | Retrieval result ranking method, device and program, and computer-readable recording medium |
| CN102043812A (en) * | 2009-10-13 | 2011-05-04 | 北京大学 | Method and system for retrieving medical information |
| CN106024013A (en) * | 2016-04-29 | 2016-10-12 | 努比亚技术有限公司 | Voice data searching method and system |
| CN106776741A (en) * | 2016-11-18 | 2017-05-31 | 北京奇虎科技有限公司 | A kind of searching method and device |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111198887A (en) * | 2019-12-31 | 2020-05-26 | 北京左医健康技术有限公司 | Medicine indexing method, medicine retrieval method and system |
| CN112307180A (en) * | 2020-10-22 | 2021-02-02 | 上海芯翌智能科技有限公司 | Rapid retrieval method and device based on label object |
| CN115359924A (en) * | 2022-08-11 | 2022-11-18 | 浙江迪谱诊断技术有限公司 | Cardiovascular and cerebrovascular medicine scoring method and device, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11328128B2 (en) | System and method for analysis and navigation of data | |
| US20180336193A1 (en) | Artificial Intelligence Based Method and Apparatus for Generating Article | |
| CN109062994A (en) | Recommended method, device, computer equipment and storage medium | |
| CN110209805B (en) | Text classification method, apparatus, storage medium and computer device | |
| US8725717B2 (en) | System and method for identifying topics for short text communications | |
| CN110532451A (en) | Search method and device for policy text, storage medium, electronic device | |
| CA3153598A1 (en) | Method of and device for predicting video playback integrity | |
| CN109614550A (en) | Public sentiment monitoring method, device, computer equipment and storage medium | |
| CN108595494A (en) | The acquisition methods and device of reply message | |
| CN108073568A (en) | keyword extracting method and device | |
| CN108304375A (en) | A kind of information identifying method and its equipment, storage medium, terminal | |
| CN109325146B (en) | Video recommendation method and device, storage medium and server | |
| CN107844533A (en) | A kind of intelligent Answer System and analysis method | |
| CN108959559A (en) | Question and answer are to generation method and device | |
| CN110232071A (en) | Search method, device and storage medium, the electronic device of drug data | |
| CN105843796A (en) | Microblog emotional tendency analysis method and device | |
| CN107688616A (en) | Show unique fact of entity | |
| CN112036187A (en) | Context-based video barrage text auditing method and system | |
| CN110955659A (en) | Method and system for processing data table | |
| CN113204953A (en) | Text matching method and device based on semantic recognition and device readable storage medium | |
| CN110162752A (en) | Article sentences weight processing method, device and electronic equipment | |
| CN112989824A (en) | Information pushing method and device, electronic equipment and storage medium | |
| CN112948664A (en) | Method and system for automatically processing sensitive words | |
| CA3046474A1 (en) | Portfolio-based text analytics tool | |
| CN115310436A (en) | Document outline extraction method and device, electronic equipment and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190913 |
|
| RJ01 | Rejection of invention patent application after publication |