CN113314207A - Object recommendation method and device, storage medium and electronic equipment - Google Patents
Object recommendation method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN113314207A CN113314207A CN202110718416.7A CN202110718416A CN113314207A CN 113314207 A CN113314207 A CN 113314207A CN 202110718416 A CN202110718416 A CN 202110718416A CN 113314207 A CN113314207 A CN 113314207A
- Authority
- CN
- China
- Prior art keywords
- recommendation
- index
- determining
- matching degree
- tasks
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 61
- 230000000875 corresponding effect Effects 0.000 claims description 61
- 239000013598 vector Substances 0.000 claims description 42
- 238000012545 processing Methods 0.000 claims description 25
- 238000011156 evaluation Methods 0.000 claims description 24
- 238000004364 calculation method Methods 0.000 claims description 18
- 238000013507 mapping Methods 0.000 claims description 4
- 230000002596 correlated effect Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 239000000047 product Substances 0.000 description 5
- 230000003068 static effect Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 208000004371 toothache Diseases 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 3
- 230000008961 swelling Effects 0.000 description 3
- 208000002193 Pain Diseases 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000013585 weight reducing agent Substances 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000006227 byproduct Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000000746 purification Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 230000003313 weakening effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
- G16H40/67—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Biomedical Technology (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Public Health (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Primary Health Care (AREA)
- Medical Informatics (AREA)
- Epidemiology (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses an object recommendation method, an object recommendation device, a storage medium and electronic equipment. The method comprises the following steps: acquiring search keywords, and determining the recommendation matching degree of each object based on the search keywords and the description information of each object; acquiring a quality index and a current dynamic recommendation index of each object, wherein the current dynamic recommendation index is determined based on the current accepted tasks and the accepted tasks of the objects; respectively determining a comprehensive recommendation index of each object based on the recommendation matching degree, the quality index and the current dynamic recommendation index of each object; and determining the object recommendation sequence corresponding to the search keyword based on the comprehensive recommendation index of each object. According to the technical scheme, when object recommendation is carried out, the matching relation between the search keyword and the description information of each object can be effectively captured by means of the recommendation matching degree, the quality index and the current dynamic recommendation index, the description information of each object is analyzed in real time, and the effectiveness and the accuracy of a recommendation result are improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of data processing, in particular to an object recommendation method, an object recommendation device, a storage medium and electronic equipment.
Background
With the continuous development of internet technology, more and more users choose to perform registration inquiry through the internet, so that the users can make diagnosis and treatment without going out, and great convenience is provided for the users.
In the prior art, a recommendation method based on keywords is mainly used for recommending a proper doctor for a user, the recommendation method comprises the steps of extracting the keywords from input contents, calculating the similarity between the keywords and a text to be matched, and recommending the doctor based on the calculated similarity.
However, according to the recommendation method based on the keywords, only the doctor with the highest similarity to the keywords is recommended, and the recommendation accuracy is low and the effectiveness is poor.
Disclosure of Invention
The embodiment of the invention provides an object recommendation method, an object recommendation device, a storage medium and electronic equipment, and aims to improve object recommendation accuracy and effectiveness.
In a first aspect, an embodiment of the present invention provides an object recommendation method, including:
acquiring search keywords, and determining the recommendation matching degree of each object based on the search keywords and the description information of each object;
acquiring a quality index and a current dynamic recommendation index of each object, wherein the current dynamic recommendation index is determined based on the current accepted tasks and the accepted tasks of the objects;
respectively determining a comprehensive recommendation index of each object based on the recommendation matching degree, the quality index and the current dynamic recommendation index of each object;
and determining the object recommendation sequence corresponding to the search keyword based on the comprehensive recommendation index of each object.
In a second aspect, an embodiment of the present invention further provides an object recommendation apparatus, including:
the matching degree generating module is used for acquiring search keywords and determining the recommended matching degree of each object based on the search keywords and the description information of each object;
the index acquisition module is used for acquiring the quality index and the current dynamic recommendation index of each object, wherein the current dynamic recommendation index is determined based on the current accepted tasks and the accepted tasks of the objects;
the comprehensive recommendation index determining module is used for respectively determining the comprehensive recommendation index of each object based on the recommendation matching degree, the quality index and the current dynamic recommendation index of each object;
and the recommendation sequence determining module is used for determining the object recommendation sequence corresponding to the search keyword based on the comprehensive recommendation index of each object.
In a third aspect, an embodiment of the present invention further provides an electronic device, where the electronic device includes:
one or more processors;
a storage device for storing one or more programs,
when the one or more programs are executed by the one or more processors, the one or more processors implement the object recommendation method according to any one of the embodiments of the present invention.
In a fourth aspect, the present invention further provides a storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform the object recommendation method according to any one of the embodiments of the present invention.
According to the method, the search keywords are obtained, and the recommendation matching degree of each object is determined based on the search keywords and the description information of each object, so that the object can be automatically recommended according to the search keywords; furthermore, by obtaining the quality index and the current dynamic recommendation index of each object, respectively determining the comprehensive recommendation index of each object based on the recommendation matching degree, the quality index and the current dynamic recommendation index of each object, and determining the object recommendation sequence corresponding to the search keyword based on the comprehensive recommendation index of each object, the static quality index and the current dynamic recommendation index which changes in real time are increased on the basis of the recommendation method based on the keyword, so that the analyzed data are more comprehensive, and the effectiveness and the accuracy of object recommendation are improved.
Drawings
In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, a brief description is given below of the drawings used in describing the embodiments. It should be clear that the described figures are only views of some of the embodiments of the invention to be described, not all, and that for a person skilled in the art, other figures can be derived from these figures without inventive effort.
Fig. 1 is a schematic flowchart of an object recommendation method according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating an object recommendation method according to a second embodiment of the present invention;
fig. 3 is a flowchart illustrating an object recommendation method according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of an object recommendation apparatus according to a fourth embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention.
It should be further noted that, for the convenience of description, only some but not all of the relevant aspects of the present invention are shown in the drawings. Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the operations (or steps) as a sequential process, many of the operations can be performed in parallel, concurrently or simultaneously. In addition, the order of the operations may be re-arranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, and the like.
Example one
Fig. 1 is a flowchart of an object recommendation method according to an embodiment of the present invention, where the embodiment is applicable to a case where an object related to a keyword in an input content is automatically recommended when searching for the input content, and the method may be executed by an object recommendation apparatus according to an embodiment of the present invention, where the apparatus may be implemented by software and/or hardware, and the apparatus may be configured on an electronic computing device, such as a desktop computer or a server.
The method specifically comprises the following steps:
s110, obtaining search keywords, and determining the recommendation matching degree of each object based on the search keywords and the description information of each object.
The search keywords can be obtained by preprocessing the text or voice information of the content input by the user, the preprocessing method can include but is not limited to document purification, word segmentation processing, word removal and other methods, and one or more search keywords in the content input by the user can be obtained after preprocessing.
In this embodiment, the type of the keyword may be determined according to a recommendation scenario, and different recommendation scenarios are used for recommending different types of objects, which is not limited herein. Illustratively, the recommendation scene includes, but is not limited to, a medical recommendation scene, a task recommendation scene, and the like, wherein in the medical recommendation scene, an object is recommended according to a medical keyword input by a user, and the object may be a hospital, a department, a doctor, or the like; in a task recommendation scene, an object is recommended according to a task keyword input by a user, and the object can be a task execution mechanism, a task executive and the like.
In some embodiments, where the embodiments are medical scenarios, the keywords may include the following types: disease, symptom, doctor, hospital, department or region. Accordingly, the recommended object may be a doctor, and the description information of the object may be information related to the doctor. Illustratively, the description information of the object may include, but is not limited to, the name of the doctor, the doctor's specialty disease, the doctor's expertise, the doctor's hospital and the doctor's hospital department, etc.
Specifically, the obtained search keywords are matched with the description information of each object to obtain one or more objects matched with one or more search keywords in the content input by the user, each object has a recommendation matching degree corresponding to the search keywords, the objects with higher matching degrees with the search keywords can be obviously found through the recommendation matching degrees, and the recommendation efficiency is improved.
And S120, acquiring the quality index and the current dynamic recommendation index of each object, wherein the current dynamic recommendation index is determined based on the current accepted tasks and the accepted tasks of the objects.
The quality index of the object can be understood as a quality score of the object, and is a static score. The better the quality of the object, the higher the score, and vice versa the lower the score. The current dynamic recommendation index can be understood as the real-time change information score of the object, and is a dynamic score. The real-time change information may include the current accepted task and the accepted task for the object. For example, the taken task may be the number of inquiry orders that the physician has completed the day, and the taken task may be the number of inquiry orders remaining for the day.
According to the method and the device for recommending the object, the task which is accepted by the current object and the task which can be accepted by the current object are analyzed in real time, the current dynamic recommendation index is generated, the object recommendation method is enabled to have timeliness, and the reliability of the recommended object is improved.
On the basis of the above embodiment, the obtaining the quality index of each object includes: calling a corresponding quality index based on the identification of each object, wherein the quality index is updated based on a preset period; or acquiring basic information, a task opening state and historical traffic corresponding to each object, and performing weighting processing based on weights corresponding to the basic information, the task opening state and the historical traffic respectively to obtain a corresponding quality index.
The identification of each object has uniqueness, the corresponding storage position of the quality index of each object in the server or the database can be identified by checking the identification of each object, and the quality index corresponding to the identification of each object is called. The quality index is updated based on a preset period, where the preset period may be one or more days, which is not limited in this embodiment. The basic information may include, but is not limited to, sub-item information such as national hospital ranking, city ranking of the hospital, hospital level and national department ranking; the task opening state can include but is not limited to sub-item information such as a number source, an opening consultation, an opening service package and an opening health number; historical traffic may include, but is not limited to, sub-item information such as registration good scores, inquiry good scores, and service package order quantities.
For example, if the weight of the basic information is 0.54, the weight of the task-on state is 0.16, and the weight of the historical traffic is 0.30, the quality index is 0.54 × basic information +0.16 × task-on state +0.30 × historical traffic. The following shows an example of a calculation method of the sub-item information, and not all the sub-item information in the embodiment is shown. Referring to table 1, table 1 is a calculation method of each sub-item information in the quality index, it should be noted that table 1 is an example of a medical recommendation often shown below and a recommendation object is a doctor, in other embodiments, the sub-item information and the calculation method for determining the quality index may be set according to needs, and the weight of each sub-item information may also be adjusted according to needs:
TABLE 1
According to the embodiment, the basic information, the task opening state and the historical traffic are weighted, and the corresponding formula calculation is also performed on the sub-item information, so that the multi-aspect evaluation of each object is realized, and the reliability of the quality index is improved.
And S130, respectively determining the comprehensive recommendation index of each object based on the recommendation matching degree, the quality index and the current dynamic recommendation index of each object.
The comprehensive recommendation index is a standard of comprehensive quality of an evaluation object and has timeliness.
Optionally, the comprehensive recommendation index is determined by at least one of the following methods: determining a comprehensive recommendation index corresponding to the recommendation matching degree, the quality index and the current dynamic recommendation index according to a pre-established mapping relation table; inputting the recommendation matching degree, the quality index and the current dynamic recommendation index of each object into a pre-trained comprehensive recommendation index determination model to obtain the comprehensive recommendation index; and inputting the recommendation matching degree, the quality index and the current dynamic recommendation index into the objective function according to a preset objective function, and determining a comprehensive recommendation index.
On the basis of the above embodiment, the determining the comprehensive recommendation index of each object based on the recommendation matching degree, the quality index and the current dynamic recommendation index of each object includes: for any object, weighting processing is carried out on the basis of weights respectively corresponding to the recommendation matching degree, the quality index and the current dynamic recommendation index, and a comprehensive recommendation index of the object is obtained; or for any object, determining the comprehensive recommendation index of the object based on the product of the recommendation matching degree, the quality index and the current dynamic recommendation index.
For example, if the comprehensive recommendation index is determined by performing weighting processing on the weights corresponding to the recommendation matching degree, the quality index and the current dynamic recommendation index, the calculation formula of the comprehensive recommendation index may be: the comprehensive recommendation index is 0.4 × recommendation matching degree +0.3 × quality index +0.3 × current dynamic recommendation index. If the comprehensive recommendation index is determined by the product of the recommendation matching degree, the quality index and the current dynamic recommendation index, the calculation formula of the comprehensive recommendation index may be: and the comprehensive recommendation index is the recommended matching degree multiplied by the quality index multiplied by the current dynamic recommendation index.
S140, determining the object recommendation sequence corresponding to the search keyword based on the comprehensive recommendation index of each object.
Specifically, the comprehensive recommendation indexes of the objects are sorted from large to small, and correspondingly, the recommendation sequence of the objects is the same as the comprehensive recommendation index sorting of the objects.
The embodiment of the invention provides an object recommendation method, which is characterized in that the recommendation matching degree of each object is determined based on a search keyword and description information of each object by acquiring the search keyword, so that the object is automatically recommended according to the search keyword; furthermore, by obtaining the quality index and the current dynamic recommendation index of each object, respectively determining the comprehensive recommendation index of each object based on the recommendation matching degree, the quality index and the current dynamic recommendation index of each object, and determining the object recommendation sequence corresponding to the search keyword based on the comprehensive recommendation index of each object, the static quality index and the current dynamic recommendation index which changes in real time are increased on the basis of the recommendation method based on the keyword, so that the analyzed data are more comprehensive, and the timeliness and the accuracy of object recommendation are improved.
Example two
Fig. 2 is a flow chart illustrating an object recommendation method provided in a second embodiment of the present invention, and based on the foregoing embodiment, the "obtaining a current dynamic recommendation index of each object" in the foregoing embodiment may be further refined, and a specific implementation manner of the method may refer to detailed descriptions of the technical solution. The technical terms that are the same as or corresponding to the above embodiments are not repeated herein. As shown in fig. 2, the method of the embodiment of the present invention specifically includes the following steps:
s210, obtaining search keywords, and determining the recommendation matching degree of each object based on the search keywords and the description information of each object.
S220, obtaining the quality index and the current dynamic recommendation index of each object, wherein for any object, the type of the task which can be accepted by the object, whether the accepted task exists currently or not and the current number of the accepted tasks are determined.
In this embodiment, the types of tasks that a subject can undertake may include, but are not limited to, a physician's registration source, an expert interrogation service, or an interrogation order quantity.
For any object, the type of the object that can support the task, such as the A type task, the B type task or the C type task, can be determined in real time. It may also be determined whether there are currently committed tasks, e.g., whether the object has committed an A-type task, and may also be determined the current number of committed tasks, e.g., the current number of objects that have completed an A-type task.
S230, determining the current dynamic recommendation index based on the types of the receivable tasks, whether the receivable tasks exist at present or not and evaluation values corresponding to the current number of the receivable tasks respectively.
The evaluation value is preset, may be a fixed value, or may be a value that changes within a certain range.
Illustratively, the score value of the object already carrying the a-type task is 1, the score value of the object not carrying the a-type task is 1.5, if the current number of the carried a-type tasks is less than a predetermined threshold, it indicates that the object can also carry the a-type task, the corresponding object needs to be weighted, the score correspondingly rises, the score value is 1.2, and if the current number of the carried a-type tasks is greater than or equal to the predetermined threshold, the score value is 0.9; if the current number of the borne B-type tasks reaches the maximum value of the borne tasks of the object, which indicates that the object can not bear the B-type tasks, the corresponding object needs to be weighted down, and the score correspondingly decreases.
According to the method and the device, the change condition of the object data can be analyzed in real time by determining the type of the task which can be accepted by the object, whether the accepted task exists at present or not and the current number of the accepted tasks, so that the weighting or weight reduction processing of each object is realized, the recommendation accuracy is improved, and the timeliness of the recommendation result is ensured.
On the basis of the embodiment, each type of the bearable tasks respectively corresponds to different evaluation values; the existing and non-existing accepted tasks respectively correspond to different evaluation values; the current number of the accepted tasks is negatively correlated with the corresponding evaluation value, or different number ranges to which the current number of the accepted tasks belongs respectively correspond to different evaluation values.
For example, when the present embodiment is a medical scenario, the recommended physician may register the number source (i.e. there is a performed task), the non-registered general evaluation value is 1 point, and the non-number source (i.e. there is no performed task) is 0.9 point. The recommended types of doctor receivable tasks include 1 point of providing expert inquiry service, and the recommended types of receivable tasks do not include 0.9 point of providing expert inquiry service. If the recommended doctor has asked for an order number (namely the current number of accepted tasks) of [0,3] on the day, the score is 1; if the number of orders asked by the expert on the day is (3, 10), the grade is determined according to the calculation formula that y is-0.0286 x +1.0857, and the grade range is [0.8, 1); if the number of orders asked by the experts on the same day is (10, 20), the grade is determined according to the calculation formula that y is 0.02x +1, and the grade range is [0.6,0.8 ]; if the recommended physician has asked an order quantity of (20, + ∞) units on the day, the score is 0.6.
On the basis of the above embodiment, the current dynamic recommendation index is determined by a preset processing rule based on evaluation values respectively corresponding to the type of the sustainable tasks, whether the sustainable tasks currently exist, and the current number of the sustainable tasks, where the preset processing rule includes product operation and weighting processing.
For example, if the current dynamic recommendation index is determined by performing weighting processing on the type of the adoptable tasks, whether the adoptable tasks currently exist, and the current number of the adoptable tasks, the calculation formula of the current dynamic recommendation index may be: the current dynamic recommendation index is 0.4 × a type task +0.3 × B type task +0.3 × C type task. If the current dynamic recommendation index is determined by product operation, the calculation formula of the comprehensive recommendation index may be: the current dynamic recommendation index is A type task multiplied by B type task multiplied by C type task.
And S240, respectively determining the comprehensive recommendation index of each object based on the recommendation matching degree, the quality index and the current dynamic recommendation index of each object.
And S250, determining the object recommendation sequence corresponding to the search keyword based on the comprehensive recommendation index of each object.
The embodiment of the invention provides an object recommendation method, which comprises the steps of determining the type of tasks which can be accepted by any object, whether the accepted tasks exist currently or not and the current number of the accepted tasks; and determining the current dynamic recommendation index based on the evaluation values respectively corresponding to the types of the supportable tasks, the existence of the supportable tasks at present and the current number of the supportable tasks. By the technical scheme, the change condition of the object data can be analyzed in real time, weighting or weight reduction processing of each object is realized, the recommendation accuracy is improved, and the timeliness of the recommendation result is ensured.
EXAMPLE III
Fig. 3 is a flowchart of an object recommendation method provided in a third embodiment of the present invention, and based on the foregoing embodiment, further refinement may be performed on "determining a recommendation matching degree of each object based on the search keyword and description information of each object" in the foregoing embodiment, and a specific implementation manner of the method may be described in detail with reference to information in the technical solution. The technical terms that are the same as or corresponding to the above embodiments are not repeated herein. As shown in fig. 3, the method of the embodiment of the present invention specifically includes the following steps:
s310, obtaining search keywords, and mapping the search keywords into a first vector.
The first vector comprises a first keyword vector and a first weight vector corresponding to the first keyword vector. The first keyword vector may be a vector of one or more numerical values, and each dimension in the first keyword vector may be used to characterize semantic features of the corresponding keyword.
For example, the keywords with similar semantics may have similar values, for example, the keyword "toothache" may correspond to a word vector of 0.12, and the keyword "swelling and aching gum" with similar semantics to "toothache" may correspond to a word vector of 0.14.
The first weight vector corresponding to the search keyword may be a vector composed of weights occupied by the search keywords in the input content, or may be a vector composed of weights occupied by all keywords extracted from the input content by the search keywords in the input content.
And S320, respectively carrying out similarity calculation with the first vector based on the second vector corresponding to the description information of each object, and determining the recommendation matching degree of the search keyword and the description information of each object.
The second vector comprises a second keyword vector and a second weight vector corresponding to the second keyword vector; specifically, a keyword is extracted from the description information of each object, and the extracted keyword is determined as the second keyword. The second keyword vector may be a vector of one or more numerical values, and each dimension in the second keyword vector may be used to characterize semantic features of the corresponding keyword. The second weight vector corresponding to the second keyword may be a vector composed of weights occupied by the second keywords in the description information of each object, or may be a vector composed of weights occupied by all keywords extracted by each search keyword in the description information of each object.
Specifically, after a first vector of the search keyword and a second vector corresponding to the description information of each object are obtained, cosine similarity calculation is performed, and the calculation formula is as follows:
wherein similarity is cosine similarity, q represents a first keyword vector in the input content, and d represents a second keyword vector in the description information of each object. coord denotes a co-ordination factor. queryNorm is a normalized indicator of similarity. tf represents the occurrence frequency of a search keyword in the description information of each object, idf represents the popularity of the keyword in the whole inverted index, and norm represents the normalization factor of the keyword in the description information of each object, and is used for weakening the influence of the file length in the description information on the similarity. Getboost () represents the weight of each search keyword in the input content, and the weight of the search keyword can be set in advance, so that a certain word is set to be more important.
It should be noted that, when the semantics of the search keyword in the input content and the second keyword in the description information of each object are relatively close, the word vectors of the two keywords are also relatively close, and thus the cosine similarity of the two words calculated in this way is also relatively high, for example, the semantics of the search keyword "toothache" in the input content and the second keyword "tooth swelling and pain" in the description information of each object are relatively close, and the cosine similarity of the word vector corresponding to "toothache" and "tooth swelling and pain" is also relatively high. When the search keyword in the input content has more keywords with the same or closer semantics with the second keyword in the description information of each object, the cosine similarity of the calculated first vector and the second vector is higher.
The embodiment maps the search keyword into a first vector; similarity calculation is carried out on the second vectors corresponding to the description information of each object and the first vectors respectively, and the recommendation matching degree of the search keywords and the description information of each object is determined, so that the recommendation matching degree is automatically generated according to the keywords, and a basic evaluation score is provided for object recommendation; furthermore, the relation between the search keyword and the description information of each object can be effectively obtained through the cosine similarity calculation, and the similarity calculation precision is improved.
S330, acquiring the quality index and the current dynamic recommendation index of each object, wherein the current dynamic recommendation index is determined based on the current accepted tasks and the accepted tasks of the objects.
S340, respectively determining the comprehensive recommendation index of each object based on the recommendation matching degree, the quality index and the current dynamic recommendation index of each object.
And S350, determining the object recommendation sequence corresponding to the search keyword based on the comprehensive recommendation index of each object.
The embodiment of the invention provides an object recommendation method, which is characterized in that the recommendation matching degree of each object is determined based on a search keyword and description information of each object by acquiring the search keyword, so that the object is automatically recommended according to the search keyword; furthermore, by obtaining the quality index and the current dynamic recommendation index of each object, respectively determining the comprehensive recommendation index of each object based on the recommendation matching degree, the quality index and the current dynamic recommendation index of each object, and determining the object recommendation sequence corresponding to the search keyword based on the comprehensive recommendation index of each object, the static quality index and the current dynamic recommendation index which changes in real time are increased on the basis of the recommendation method based on the keyword, so that the analyzed data are more comprehensive, and the timeliness and the accuracy of object recommendation are improved.
Example four
Fig. 4 is a schematic structural diagram of an object recommendation device according to a fourth embodiment of the present invention, where the object recommendation device provided in this embodiment may be implemented by software and/or hardware, and may be configured in a terminal and/or a server to implement the object recommendation method according to the fourth embodiment of the present invention. The device may specifically include: a matching degree generating module 410, an index obtaining module 420, a comprehensive recommendation index determining module 430 and a recommendation order determining module 440.
The matching degree generating module 410 is configured to obtain a search keyword, and determine a recommended matching degree of each object based on the search keyword and description information of each object; an index obtaining module 420, configured to obtain a quality index and a current dynamic recommendation index of each object, where the current dynamic recommendation index is determined based on a current accepted task and a current accepted task of the object; a comprehensive recommendation index determining module 430, configured to determine a comprehensive recommendation index of each object based on the recommendation matching degree, the quality index, and the current dynamic recommendation index of each object; and a recommendation order determining module 440, configured to determine, based on the comprehensive recommendation index of each object, an object recommendation order corresponding to the search keyword.
The embodiment of the invention provides an object recommendation device, which is used for determining the recommendation matching degree of each object based on a search keyword and description information of each object by acquiring the search keyword, so that the object can be automatically recommended according to the search keyword; furthermore, by obtaining the quality index and the current dynamic recommendation index of each object, respectively determining the comprehensive recommendation index of each object based on the recommendation matching degree, the quality index and the current dynamic recommendation index of each object, and determining the object recommendation sequence corresponding to the search keyword based on the comprehensive recommendation index of each object, the static quality index and the current dynamic recommendation index which changes in real time are increased on the basis of the recommendation method based on the keyword, so that the analyzed data are more comprehensive, and the timeliness and the accuracy of object recommendation are improved.
On the basis of any optional technical solution in the embodiment of the present invention, optionally, the index obtaining module 420 may include:
the task accepting determination unit is used for determining the type of the task which can be accepted by any object, whether the accepted task exists currently or not and the current number of the accepted tasks;
and the dynamic recommendation index generating unit is used for determining the current dynamic recommendation index based on the evaluation values respectively corresponding to the types of the supportable tasks, the existence of the supportable tasks at present and the current number of the supportable tasks.
On the basis of any optional technical scheme in the embodiment of the invention, optionally, each type of the supportable task corresponds to different evaluation values respectively; the existing and non-existing accepted tasks respectively correspond to different evaluation values; the current number of the accepted tasks is negatively correlated with the corresponding evaluation value, or different number ranges to which the current number of the accepted tasks belongs respectively correspond to different evaluation values.
On the basis of any optional technical solution in the embodiment of the present invention, optionally, the current dynamic recommendation index is determined by a preset processing rule based on the type of the adoptable task, whether the adoptable task exists currently, and evaluation values corresponding to the current number of the adoptable task, respectively, where the preset processing rule includes product operation and weighting processing.
On the basis of any optional technical solution in the embodiment of the present invention, optionally, the index obtaining module 420 may further be configured to:
calling a corresponding quality index based on the identification of each object, wherein the quality index is updated based on a preset period; alternatively, the first and second electrodes may be,
acquiring basic information, a task opening state and historical traffic corresponding to each object, and performing weighting processing based on weights corresponding to the basic information, the task opening state and the historical traffic respectively to obtain corresponding quality indexes.
On the basis of any optional technical solution in the embodiment of the present invention, optionally, the matching degree generating module 410 may be further configured to:
mapping the search keyword to a first vector;
and respectively carrying out similarity calculation with the first vector based on the second vector corresponding to the description information of each object, and determining the recommendation matching degree of the search keyword and the description information of each object.
On the basis of any optional technical solution in the embodiment of the present invention, optionally, the comprehensive recommendation index determining module 430 may be further configured to:
for any object, weighting processing is carried out on the basis of weights respectively corresponding to the recommendation matching degree, the quality index and the current dynamic recommendation index, and a comprehensive recommendation index of the object is obtained; alternatively, the first and second electrodes may be,
for any object, determining a comprehensive recommendation index of the object based on the product of the recommendation matching degree, the quality index and the current dynamic recommendation index.
The object recommendation device provided by the embodiment of the invention can execute the object recommendation method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
EXAMPLE five
Fig. 5 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present invention. FIG. 5 illustrates a block diagram of an exemplary electronic device 12 suitable for use in implementing embodiments of the present invention. The electronic device 12 shown in fig. 5 is only an example and should not bring any limitation to the function and the scope of use of the embodiment of the present invention.
As shown in FIG. 5, electronic device 12 is embodied in the form of a general purpose computing device. The components of electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.
The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)30 and/or cache memory 32. The electronic device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 5, and commonly referred to as a "hard drive"). Although not shown in FIG. 5, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. System memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.
A program/utility 36 having a set (at least one) of program modules 26 may be stored, for example, in system memory 28, such program modules 26 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 26 generally perform the functions and/or methodologies of the described embodiments of the invention.
The processing unit 16 executes various functional applications and data processing by executing programs stored in the system memory 28, for example, to implement an object recommendation method provided by the present embodiment.
EXAMPLE six
An embodiment of the present invention further provides a storage medium containing computer-executable instructions, which when executed by a computer processor, perform a method for object recommendation, the method including:
acquiring search keywords, and determining the recommendation matching degree of each object based on the search keywords and the description information of each object;
acquiring a quality index and a current dynamic recommendation index of each object, wherein the current dynamic recommendation index is determined based on the current accepted tasks and the accepted tasks of the objects;
respectively determining a comprehensive recommendation index of each object based on the recommendation matching degree, the quality index and the current dynamic recommendation index of each object;
and determining the object recommendation sequence corresponding to the search keyword based on the comprehensive recommendation index of each object.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for embodiments of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. An object recommendation method, comprising:
acquiring search keywords, and determining the recommendation matching degree of each object based on the search keywords and the description information of each object;
acquiring a quality index and a current dynamic recommendation index of each object, wherein the current dynamic recommendation index is determined based on the current accepted tasks and the accepted tasks of the objects;
respectively determining a comprehensive recommendation index of each object based on the recommendation matching degree, the quality index and the current dynamic recommendation index of each object;
and determining the object recommendation sequence corresponding to the search keyword based on the comprehensive recommendation index of each object.
2. The method of claim 1, wherein obtaining a current dynamic recommendation index for each object comprises:
for any object, determining the type of the task which can be accepted by the object, whether the accepted task exists currently or not and the current number of the accepted tasks;
and determining the current dynamic recommendation index based on the evaluation values respectively corresponding to the types of the supportable tasks, the existence of the supportable tasks at present and the current number of the supportable tasks.
3. The method of claim 2, wherein each type of bearable task corresponds to a different evaluation value;
the existing and non-existing accepted tasks respectively correspond to different evaluation values;
the current number of the accepted tasks is negatively correlated with the corresponding evaluation value, or different number ranges to which the current number of the accepted tasks belongs respectively correspond to different evaluation values.
4. The method according to claim 2, wherein the current dynamic recommendation index is determined by a preset processing rule based on evaluation values respectively corresponding to the type of the adoptable task, whether the adoptable task exists currently and the current number of the adoptable tasks, wherein the preset processing rule comprises multiplication and weighting.
5. The method of claim 1, wherein the obtaining the quality index of each object comprises:
calling a corresponding quality index based on the identification of each object, wherein the quality index is updated based on a preset period; alternatively, the first and second electrodes may be,
acquiring basic information, a task opening state and historical traffic corresponding to each object, and performing weighting processing based on weights corresponding to the basic information, the task opening state and the historical traffic respectively to obtain corresponding quality indexes.
6. The method of claim 1, wherein determining the recommended matching degree of each object based on the search keyword and the description information of each object comprises:
mapping the search keyword to a first vector;
and respectively carrying out similarity calculation with the first vector based on the second vector corresponding to the description information of each object, and determining the recommendation matching degree of the search keyword and the description information of each object.
7. The method according to claim 1, wherein the determining the comprehensive recommendation index of each object based on the recommendation matching degree, the quality index and the current dynamic recommendation index of each object respectively comprises:
for any object, weighting processing is carried out on the basis of weights respectively corresponding to the recommendation matching degree, the quality index and the current dynamic recommendation index, and a comprehensive recommendation index of the object is obtained; alternatively, the first and second electrodes may be,
for any object, determining a comprehensive recommendation index of the object based on the product of the recommendation matching degree, the quality index and the current dynamic recommendation index.
8. An object recommendation apparatus, comprising:
the matching degree generating module is used for acquiring search keywords and determining the recommended matching degree of each object based on the search keywords and the description information of each object;
the index acquisition module is used for acquiring the quality index and the current dynamic recommendation index of each object, wherein the current dynamic recommendation index is determined based on the current accepted tasks and the accepted tasks of the objects;
the comprehensive recommendation index determining module is used for respectively determining the comprehensive recommendation index of each object based on the recommendation matching degree, the quality index and the current dynamic recommendation index of each object;
and the recommendation sequence determining module is used for determining the object recommendation sequence corresponding to the search keyword based on the comprehensive recommendation index of each object.
9. An electronic device, characterized in that the electronic device comprises:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the object recommendation method of any of claims 1-7.
10. A storage medium containing computer-executable instructions for performing the object recommendation method of any one of claims 1-7 when executed by a computer processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110718416.7A CN113314207A (en) | 2021-06-28 | 2021-06-28 | Object recommendation method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110718416.7A CN113314207A (en) | 2021-06-28 | 2021-06-28 | Object recommendation method and device, storage medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113314207A true CN113314207A (en) | 2021-08-27 |
Family
ID=77380582
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110718416.7A Pending CN113314207A (en) | 2021-06-28 | 2021-06-28 | Object recommendation method and device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113314207A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113707335A (en) * | 2021-09-06 | 2021-11-26 | 挂号网（杭州）科技有限公司 | Method, device, electronic equipment and storage medium for determining target reception user |
| CN115269989A (en) * | 2022-08-03 | 2022-11-01 | 百度在线网络技术（北京）有限公司 | Object recommendation method and device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN106503119A (en) * | 2016-10-17 | 2017-03-15 | 广州薏生网络科技有限公司 | A kind of sort method of mobile interrogation platform vertical search result |
| CN110993084A (en) * | 2019-12-18 | 2020-04-10 | 腾讯科技（深圳）有限公司 | Object sorting method, device and equipment and readable storage medium |
| CN111476029A (en) * | 2020-04-13 | 2020-07-31 | 武汉联影医疗科技有限公司 | Resource recommendation method and device |
| CN112069413A (en) * | 2020-09-11 | 2020-12-11 | 腾讯科技（深圳）有限公司 | Doctor recommendation method, device, server and storage medium |
-
2021
- 2021-06-28 CN CN202110718416.7A patent/CN113314207A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN106503119A (en) * | 2016-10-17 | 2017-03-15 | 广州薏生网络科技有限公司 | A kind of sort method of mobile interrogation platform vertical search result |
| CN110993084A (en) * | 2019-12-18 | 2020-04-10 | 腾讯科技（深圳）有限公司 | Object sorting method, device and equipment and readable storage medium |
| CN111476029A (en) * | 2020-04-13 | 2020-07-31 | 武汉联影医疗科技有限公司 | Resource recommendation method and device |
| CN112069413A (en) * | 2020-09-11 | 2020-12-11 | 腾讯科技（深圳）有限公司 | Doctor recommendation method, device, server and storage medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113707335A (en) * | 2021-09-06 | 2021-11-26 | 挂号网（杭州）科技有限公司 | Method, device, electronic equipment and storage medium for determining target reception user |
| CN115269989A (en) * | 2022-08-03 | 2022-11-01 | 百度在线网络技术（北京）有限公司 | Object recommendation method and device, electronic equipment and storage medium |
| WO2024027125A1 (en) * | 2022-08-03 | 2024-02-08 | 百度在线网络技术（北京）有限公司 | Object recommendation method and apparatus, electronic device, and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| De Vine et al. | Medical semantic similarity with a neural language model | |
| CN110737774B (en) | Book knowledge graph construction method, book recommendation method, device, equipment and medium | |
| CN109325108B (en) | Query processing method, device, server and storage medium | |
| CN111832290B (en) | Model training method and device for determining text relevance, electronic equipment and readable storage medium | |
| CN112541056B (en) | Medical term standardization method, device, electronic equipment and storage medium | |
| CN112329460B (en) | Text topic clustering method, device, equipment and storage medium | |
| CN112883157B (en) | Method and device for standardizing multi-source heterogeneous medical data | |
| US10431337B2 (en) | System and method for weighting manageable patient attributes during criteria evaluations for treatment | |
| CN109299227B (en) | Information query method and device based on voice recognition | |
| CN113314207A (en) | Object recommendation method and device, storage medium and electronic equipment | |
| CN110276009B (en) | Association word recommendation method and device, electronic equipment and storage medium | |
| US20150227714A1 (en) | Medical information analysis apparatus and medical information analysis method | |
| CN113345577A (en) | Diagnosis and treatment auxiliary information generation method, model training method, device, equipment and storage medium | |
| CN112966181A (en) | Service recommendation method and device, electronic equipment and storage medium | |
| CN116127001A (en) | Sensitive word detection method, device, computer equipment and storage medium | |
| CN111755090A (en) | Medical record searching method, medical record searching device, storage medium and electronic equipment | |
| CN117473057A (en) | Question-answering processing method, system, equipment and storage medium | |
| CN115620886B (en) | Data auditing method and device | |
| CN115762704A (en) | Prescription auditing method, device, equipment and storage medium | |
| EP3964980A1 (en) | Automatically recommending an existing machine learning project as adaptable for use in a new machine learning project | |
| CN111858899B (en) | Statement processing method, device, system and medium | |
| CN113849618A (en) | Strategy determination method and device based on knowledge graph, electronic equipment and medium | |
| CN115048487A (en) | Artificial intelligence-based public opinion analysis method, device, computer equipment and medium | |
| CN114625960A (en) | On-line evaluation method and device, electronic equipment and storage medium | |
| CN114020774A (en) | Method, device and equipment for processing multiple rounds of question-answering sentences 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210827 |