CN116049326A - Medical instrument knowledge base construction method, electronic equipment and storage medium - Google Patents
Medical instrument knowledge base construction method, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116049326A CN116049326A CN202211653814.6A CN202211653814A CN116049326A CN 116049326 A CN116049326 A CN 116049326A CN 202211653814 A CN202211653814 A CN 202211653814A CN 116049326 A CN116049326 A CN 116049326A
- Authority
- CN
- China
- Prior art keywords
- entity
- contact
- event
- level
- behavior
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000009411 base construction Methods 0.000 title claims abstract description 31
- 230000004044 response Effects 0.000 claims abstract description 4
- 230000006399 behavior Effects 0.000 claims description 127
- 238000004590 computer program Methods 0.000 claims description 13
- 230000001788 irregular Effects 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 230000001737 promoting effect Effects 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 abstract description 8
- 230000008901 benefit Effects 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 5
- 230000001960 triggered effect Effects 0.000 description 5
- 238000010276 construction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000009193 crawling Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/288—Entity relationship models
-
- 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
- G06F16/23—Updating
Abstract
The embodiment of the invention discloses a medical instrument knowledge base construction method, electronic equipment and a storage medium, and relates to the technical field of information push, wherein the method comprises the following steps: constructing an E-R model based on a first operation behavior of a first entity; triggering a second operation behavior of the first entity based on the level of the event and the contact between the first entity and the second entity in response to the event corresponding to the second entity; and updating the E-R model according to the second operation behavior. According to the embodiment of the invention, the contact type of the first entity and the second entity in the E-R model is constructed based on the first operation behavior of the first entity, and whether the event corresponding to the second entity is sent to the first entity is further determined based on the event level and the corresponding pushing mechanism, so that the user experience is improved, the viscosity between the user and the platform is increased, and the benefit is maximized.
Description
Technical Field
The embodiment of the invention relates to the technical field of information pushing, in particular to a medical instrument knowledge base construction method, electronic equipment and a storage medium.
Background
The medical instrument platform is used for establishing a communication channel for the connection of the demander and the supplier. Firstly, a medical instrument platform provides data support, namely, a demander can search for a medical instrument product required by the demander through the platform, and further, after relevant knowledge is carried out on the product, whether to purchase or when to purchase is determined.
The database of the medical instrument platform is formed in two ways, the first is that the platform building party obtains medical instrument products and related information thereof in various channels by self through a crawler mode, such as production merchant information, market circulation conditions, treatment effects and the like, in the way, the business mode of the medical instrument can provide technical support, or the medical instrument is used as an intermediate party to carry out related inquiry according to the requirements of a demander to the production merchant, and in the way, the viscosity relation between the platform and the demander is mainly expressed, namely whether the technical requirements of the demander can be met; the second is that the production merchant enters the platform and interfaces the product data with the platform, and the platform side only serves as a bridge for communication between the production merchant and the platform, and the viscosity relationship between the demand side and the supplier side is mainly expressed in the situation.
The existing various internet platforms all have own information recommendation mechanisms so as to maximize flow or/and income, in the existing information recommendation mechanisms, the users are mostly portrait, personalized information is pushed to the users based on portrait results, and the following problems exist in the mode:
1. Under the condition of less data, the accurate portrait result is difficult to obtain, so that a great amount of junk information is received by a user, and the use of relevant data of the user can be penalized under the promotion of the existing various policies for protecting personal privacy;
2. the information recommendation mechanism is not intelligent, after the portrait is finished, even if the result of the subsequent portrait is adjusted, the information is continuously sent to the user, and the user can only cancel the harassment of big data by himself.
Therefore, the existing medical instrument platform continues to be an intelligent knowledge base to express the connection between the user and the medical instrument product and between the user and the production merchant, and the connection mainly aims at user experience, can be continuously adjusted according to the operation behaviors of the user, and further improves the dependence of the user on the platform from the side.
Disclosure of Invention
In order to overcome the defects of the prior art, the embodiment of the invention aims to provide a medical instrument knowledge base construction method, electronic equipment and a storage medium, which can adjust an E-R model according to the operation behaviors of a user and improve the user experience.
In order to solve the above problems, a first aspect of the embodiments of the present invention discloses a medical apparatus knowledge base construction method, which includes the following steps:
Based on a first operation behavior of a first entity, an E-R model is constructed, wherein the E-R model comprises the first entity, a second entity, events corresponding to the second entity and the contact between the first entity and the second entity, the contact comprises three types of dominant contact, implicit contact and potential contact, and the three types of priority levels are dominant contact, implicit contact and potential contact in sequence from high to low;
responding to an event corresponding to a second entity, and triggering a second operation behavior of the first entity based on the level of the event and the contact between the first entity and the second entity;
and updating the E-R model according to the second operation behavior, wherein the updating is to adjust the contact type between the first entity and the second entity.
Alternatively, in a first aspect of the embodiment of the present invention, constructing the E-R model based on the first operation behavior of the first entity includes:
acquiring retrieval behaviors or/and attention behaviors of the first entity on a medical instrument platform;
determining that the contact of the first entity and the second entity is a hidden contact or a potential contact based on the retrieval behavior;
determining that the contact of the first entity and the second entity is an explicit contact based on the behavior of interest;
When the first entity simultaneously retrieves and pays attention to the medical instrument platform, the contact of the first entity and the second entity is determined to be an explicit contact.
Alternatively, in the first aspect of the embodiment of the present invention, determining that the contact between the first entity and the second entity is a implicit contact or a potential contact based on the search behavior includes:
judging whether the search behavior is accurate search or fuzzy search;
when the search behavior is accurate search, determining that the contact between the first entity and the target second entity is an implicit contact;
when the search behavior is fuzzy search, determining that the contact between the first entity and the second entity group is potential contact;
the target second entity is a second entity determined by accurate retrieval; the second entity group is all second entities determined for fuzzy retrieval.
Alternatively, in a first aspect of the embodiment of the present invention, in response to an event corresponding to a second entity, triggering a second operation behavior of the first entity based on a level of the event and a contact between the first entity and the second entity includes:
acquiring an event corresponding to the second entity at regular or irregular time or in real time;
grading the event based on a preset grading rule;
Transmitting the event to the first entity based on the event level, the contact type and a preset transmission rule;
a second operational behavior of the first entity on the event is received, the second operational behavior being read or not read.
Alternatively, in a first aspect of the embodiment of the present invention, updating the E-R model according to the second operation behavior, where the updating adjusts a contact type between the first entity and the second entity, includes:
when the second operation behavior is reading, the contact type between the first entity and the second entity is promoted;
and when the second operation behavior is not read, reducing the contact type between the first entity and the second entity.
Alternatively, in the first aspect of the embodiment of the present invention, when the second operation behavior is reading, promoting a contact type between the first entity and the second entity includes:
when the contact type between the first entity and the second entity is potential contact and the second operation behavior is reading, adjusting the contact between the first entity and the target second entity to be implicit contact;
when the contact type between the first entity and the second entity is a hidden contact and the second operation behavior is reading, adjusting the contact type between the first entity and the second entity to be a dominant contact;
And when the contact type between the first entity and the second entity is an explicit contact and the second operation behavior is reading, reducing the event level of sending the event to the first entity until the event level is reduced to the minimum.
Alternatively, in the first aspect of the embodiment of the present invention, when the second operation behavior is not read, reducing a contact type between the first entity and the second entity includes:
when the contact type between the first entity and the second entity group owner is potential contact, the second operation behavior is unread, and the unread operation times reach a first preset threshold value, deleting the contact of the first entity and the second entity;
when the contact type between the first entity and the second entity is a hidden contact, the second operation behavior is unread, and the unread operation times reach a second preset threshold value, the contact type between the first entity and the second entity is adjusted to be a potential contact;
when the contact type between the first entity and the second entity is explicit contact, the second operation behavior is unread, and the unread operation times reach a third preset threshold, the event grade of sending the event to the first entity is improved until the event grade is improved to the preset grade, and the contact type between the first entity and the second entity is adjusted to be implicit contact;
The first preset threshold value is smaller than a second preset threshold value, and the second preset threshold value is smaller than a third preset threshold value.
As an alternative, in the first aspect of the embodiment of the present invention, the preset sending rule is a level threshold of an event sent to the first entity when the first entity and the second entity establish an initial contact state; the event level is five levels, wherein the level of the first-level event is lowest, and the level of the fifth-level event is highest;
when the contact between the first entity and the second entity is potential contact, sending an event to the first entity, wherein the event level threshold of the event is five levels;
when the contact between the first entity and the second entity is a hidden contact, sending an event to the first entity, wherein the event level threshold of the event is four levels;
and when the contact between the first entity and the second entity is the explicit contact, sending an event to the first entity, wherein the event level threshold of the event is two-level.
The second aspect of the embodiment of the invention discloses a medical instrument knowledge base construction device, which comprises:
the system comprises a model construction unit, a model generation unit and a model generation unit, wherein the model construction unit is used for constructing an E-R model based on a first operation behavior of a first entity, the E-R model comprises the first entity, a second entity, events corresponding to the second entity and a connection between the first entity and the second entity, the connection comprises three types of dominant connection, implicit connection and potential connection, and the three types of priority levels are dominant connection, implicit connection and potential connection in sequence from high to low;
The triggering unit is used for responding to an event corresponding to the second entity and triggering a second operation behavior of the first entity based on the level of the event and the connection between the first entity and the second entity;
and the updating unit is used for updating the E-R model according to the second operation behavior, and the updating is used for adjusting the contact type between the first entity and the second entity.
A third aspect of an embodiment of the present invention discloses an electronic device, including: a memory storing executable program code; a processor coupled to the memory; the processor invokes the executable program code stored in the memory to perform a medical instrument knowledge base construction method disclosed in the first aspect of the embodiment of the present invention.
A fourth aspect of the embodiment of the present invention discloses a computer-readable storage medium storing a computer program, where the computer program causes a computer to execute a medical instrument knowledge base construction method disclosed in the first aspect of the embodiment of the present invention.
A fifth aspect of the embodiments of the present invention discloses a computer program product, which when run on a computer causes the computer to perform a medical instrument knowledge base construction method disclosed in the first aspect of the embodiments of the present invention.
A sixth aspect of the embodiment of the present invention discloses an application publishing platform, which is configured to publish a computer program product, where the computer program product when run on the computer causes the computer to execute a medical apparatus and instrument knowledge base construction method disclosed in the first aspect of the embodiment of the present invention.
Compared with the prior art, the embodiment of the invention has the beneficial effects that:
according to the embodiment of the invention, the contact type of the first entity and the second entity in the E-R model is constructed based on the first operation behavior of the first entity, whether the event corresponding to the second entity is sent to the first entity is further determined based on the event level and the corresponding pushing mechanism, and the E-R model is updated based on the second operation behavior of the first entity on the event, so that wider data are provided when the demand of the first entity is increased, more focused data are provided or data are not provided for the first entity when the demand of the first entity is reduced, the user experience is improved, the viscosity between the user and the platform is increased, and the benefit is maximized.
Drawings
FIG. 1 is a schematic flow chart of a method for constructing a knowledge base of medical devices according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a medical device platform retrieval interface provided by an embodiment of the present invention;
FIG. 3 is a schematic diagram of an E-R model provided by an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a knowledge base construction device for medical devices according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
This detailed description is merely illustrative of the embodiments of the invention and is not intended to limit the embodiments of the invention, since modifications of the embodiments can be made by those skilled in the art without creative contribution as required after reading the specification, but are protected by the patent laws within the scope of the claims of the embodiments of the invention.
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are intended to be within the scope of the embodiments of the present invention.
The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.
In embodiments of the invention, words such as "exemplary" or "such as" are used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary" or "e.g." in an embodiment should not be taken as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete fashion.
The invention constructs the contact type of the first entity and the second entity in the E-R model based on the first operation behavior of the first entity, further determines whether to send the event corresponding to the second entity to the first entity based on the event level and the corresponding pushing mechanism, and updates the E-R model based on the second operation behavior of the first entity on the event, thereby providing wider data of the first entity when the demand of the first entity is increased, and providing more focused data or not providing data to the first entity when the demand of the first entity is reduced, thereby improving user experience, increasing viscosity between the user and the platform, and further maximizing benefits.
Example 1
Referring to fig. 1, fig. 1 is a schematic flow chart of a medical apparatus knowledge base construction method according to an embodiment of the present invention. The implementation main body of the embodiment of the invention is a medical instrument platform, is realized based on a database and a software/hardware structure of the medical instrument platform, wherein the knowledge base is used for constructing the connection between a user and a supplier or between the user and a medical instrument product through the medical instrument platform, and further realizing the aim of personalized information pushing according to a related pushing mechanism.
As shown in fig. 1, the medical instrument knowledge base construction method includes the following steps:
s110, constructing an E-R model based on the first operation behavior of the first entity.
In a preferred embodiment of the present invention, the E-R model is an ordered graph of the association between a first entity and a second entity, and mainly includes the first entity, the second entity, events corresponding to the second entity, and associations between the first entity and the second entity.
The first entity is a demand party, and the demand party automatically forms the first entity after registering the medical instrument platform; the second entity is a medical appliance product or a supplier (such as a merchant or a seller) of the medical appliance product, and the supplier registers on the platform and adds the corresponding medical appliance product to form the second entity, or the platform climbs the related medical appliance product information and the supplier information of the medical appliance product from the Internet to form the second entity.
The event is news, movement, etc. information related to the second entity, which may include crawling content from the internet, such as the national food and drug administration, etc. by the crawler technology, and may also include information related to the release of the second entity (here, the supplier) on the platform, such as price reduction, etc.
In a preferred embodiment of the present invention, the events are classified into five levels, wherein one level of event is the lowest level and five levels of event is the highest level, wherein:
the fifth-level event is significant information of the second entity itself, such as recall of the medical instrument product, inspection result of the medical instrument product in a regular inspection or a flight inspection, and price reduction notification, supplier accident, etc.;
the fourth-level event is relatively important information of the second entity, such as software update of medical equipment products, and business change information of suppliers;
the third-level event is conventional information of the second entity, such as the use hearts of medical instrument products, information of suppliers and the like;
the second event is significant information of a third entity associated with the second entity, where when the second entity is a medical instrument product, the third entity is other medical instrument products in the "medical instrument standard catalogue assembly" where the medical instrument product is located (issued by the national administration management center), and the third entity may or may not be in the database of the platform, and is not limited herein. When the second entity is a supplier, the third entity is an associated party of the supplier, such as a controlling company, or a subsidiary, a branch company, etc.;
A primary event is relatively important or routine information for a third entity associated with a second entity.
The significant information, the relatively important information, and the general information corresponding to the primary event and the secondary event are similar to those of the tertiary to the five-stage events.
Of course, the event classification method and the number of classification can be performed according to other needs, which is only an example and does not limit the protection of the event classification method.
The association between the first entity and the second entity is used for sending the event corresponding to the second entity to the first entity according to the event level and the association type, and the association between the first entity and the second entity is dynamically adjusted according to the operation behavior of the first entity, which is described in step S130.
The first operation behavior refers to the operation behavior of the first entity on the medical instrument platform after registration is completed, and the first operation behavior can comprise a retrieval behavior and an attention behavior according to specific situations, wherein the retrieval behavior is used for inquiring a corresponding medical instrument product or supplier in a medical instrument database, the attention behavior refers to the operation on the medical instrument product or supplier after the retrieval behavior occurs, and the attention behavior on the medical instrument product mainly comprises the steps of collecting the medical instrument product, inquiring the medical instrument product or purchasing the medical instrument product; the operation of the supplier mainly comprises collecting the supplier page, communicating with the supplier customer service for not less than a first preset time, sending a short message to the supplier, and the like.
The search behavior can be further classified into accurate search or fuzzy search according to the search results, wherein the accurate search means that there is one search result and only one search result, the correlation between the search result and the search keyword is greater than a similarity threshold, for example, 90%, the search result obtained by the accurate search is marked as a target second entity, the fuzzy search means that the search result obtained by the search is greater than 1, and the search result obtained by the fuzzy search is marked as a second entity group.
The analysis of the search behavior and the method and strategy for determining the search result can be implemented by adopting the existing conventional search technology. Fig. 2 illustrates a search interface and a search mechanism of the medical device platform, and for example, for accurate search of medical device products, the name (sometimes including a model) of the medical device product, or registration of a license number, etc. may be input.
The E-R model is built, namely, the process of establishing the connection between the first entity and the second entity is completely based on the operation behavior of the first entity, and the platform or the second entity does not portray the first entity in various modes such as data analysis, so that the personal privacy of the first entity can be protected from being violated.
For the medical device platform, each time a first entity is registered, an ordered directed graph is constructed according to the first operation behavior of the first entity when the first entity performs the first operation behavior, so as to form an entire E-R model, and the ordered directed graph is called herein because in the model, only messages are sent to the first entity according to events, and no messages are sent to a second entity by the first entity.
And the first entity also establishes an E-R relationship between the first entity and the other second entity when the subsequent first operational behaviour involves the other second entity.
In the preferred embodiment of the invention, the contacts comprise three types of explicit contacts, implicit contacts and potential contacts, and the three types of contacts are in order of priority from high to low.
When the retrieval behavior of the first entity is fuzzy retrieval, determining that the contact between the first entity and the second entity group is potential contact; when the retrieval behavior of the first entity is accurate retrieval, determining that the contact between the first entity and the target second entity is a hidden contact; when the operational behavior of the first entity is a behavior of interest, then the contact of the first entity and the second entity is determined to be an explicit contact.
Of course, in some other embodiments, if the first entity performs the first operation for the same second entity multiple times, the contact between the first entity and the second entity is the one with the highest priority of contact types of the first entity and the second entity. For example, when the first entity is simultaneously searching for and paying attention, it is determined that the contact of the first entity and the second entity is an explicit contact.
And S120, responding to an event corresponding to the second entity, and triggering a second operation behavior of the first entity based on the level of the event and the contact between the first entity and the second entity.
The event may be that the platform obtains the event corresponding to the second entity (including the associated third entity) from the internet at regular or irregular time or in real time through the crawler technology, and after crawling the event, ranks the event based on the preset rule.
And sending the event to the first entity based on the event grade, the contact type and a preset sending rule.
For example, when the contact type is a potential contact, to avoid that frequently sent or sent information is not an event of interest to the first entity, a situation occurs that affects the experience of the first entity, and it may be set to send only five-level events to the first entity. For a contact type of implicit contact, it may be set to send a four-level event to the first entity, while for a contact type of explicit contact, it may be set to send more event types, for example, initially set to send a two-level event to the first entity, and then the event level may also be used as a sending condition of the explicit contact.
It can be understood that, the preset sending rule is a sending threshold, and an event above the sending threshold is also sent to the corresponding first entity, for example, when the first entity and the second entity are in a hidden contact, the event obtained from the second entity is a five-level event, and the event is also sent to the first entity.
Referring to fig. 3, when the level of the event 1 is four, the event 1 is simultaneously sent to the entity C1 (the entity C1 and the entity A1 are in implicit connection, the sending of the four-level event 1 to the entity C1 is triggered), the entity C2 (the sending of the four-level event 1 to the entity C2 is triggered ), and the event C3 (the potential connection between the entity C2 and the entity a is not triggered, when the event 1 or the event 2 or the event 3 is five, the sending of the event to the entity C3 is triggered, the event 3 is other events of the entity a related to the entity A1 and the entity A2, and the entity a is a second entity group corresponding to the entity C3 to establish the potential connection); similarly, when the event 2 is five-level, the event is sent to both the entity C2 and the entity C3.
And on the other hand, the event sent to the first entity can trigger a second operation behavior of the first entity, so that the E-R model is updated according to the second operation behavior, and the user experience is improved.
The second operation behavior refers to an action of the first entity after receiving the event, and may be reading the event or not reading the event.
And S130, updating the E-R model according to the second operation behavior.
Updating the E-R model is primarily to adjust the type of contact between the first entity and the second entity. In a preferred embodiment of the present invention, the contact type between the first entity and the second entity is adjusted based on the second operation behavior, and in general, the contact type (the contact type adjusted to a higher priority) between the first entity and the second entity is promoted when the read second operation behavior is operated; reducing the contact type between the first entity and the second entity (adjusting to a lower priority contact type) when the second behavior is not read; in some other scenarios, the event level threshold sent to the first entity may also be adjusted.
It can be understood that the second operation behavior can be that the first entity operates on the platform, or can be that the operation is based on a short message or the like at the mobile phone end; either operation is associated with the platform, and the platform is ascertained for this operation.
The second operation behavior also needs a time threshold, which is recorded as an operation time threshold, and corresponds to a time difference of reading by the first entity after the event is sent to the first entity, the time threshold cannot be too short, otherwise, the contact type between the first entity and the second entity cannot be frequently adjusted, the time threshold cannot be too long, otherwise, the updating of the E-R model is also affected, for example, the operation time threshold can be set to 2 days, and likewise, the event sending frequency of different contact types can be set, generally, the event sending frequency of the implicit contact can be set to be close to the operation data threshold, the event sending frequency of the explicit contact is higher than the sending frequency of the implicit contact event, and the potential contact sends the event only once.
In order to avoid misjudgment, the duration of the second operation behavior may be set, that is, some first entities may read the event and turn off directly, so that the minimum duration of the second operation behavior may be set to be not less than 30S, and when the duration of the second operation behavior is less than 30S, the second operation behavior is regarded as unread.
The situation of promoting the contact type between the first entity and the second entity includes the following:
when the contact type between the first entity and the second entity is potential contact and the second operation behavior is reading, adjusting the contact between the first entity and the target second entity to be implicit contact;
when the contact type between the first entity and the second entity is implicit contact and the second operation behavior is reading, the contact type between the first entity and the second entity is adjusted to be explicit contact, the first entity initially adjusted to be explicit contact is performed according to the event sending frequency of the explicit contact when receiving the event next time, the event level corresponds to an event level threshold initially set, for example, when the first entity is initially set to be a secondary event, then the event of two or more levels can be sent to the first entity.
And when the contact type between the first entity and the second entity is an explicit contact and the second operation behavior is reading, reducing the event level of sending the event to the first entity until the event level is reduced to the minimum. For example, assuming that the event threshold for the initial setting of the explicit contact is two-level, when the second operation behavior is reading, the contact between the first entity and the second entity is still the explicit contact, but at this time, the event level of sending the event to the first entity is reduced to one level, i.e. for this first entity, events of one level or more may be sent to it. When the event level threshold corresponding to the first entity is reduced to the lowest level, i.e. the first level, the next second operation is reading without changing the event level threshold of the first entity.
It will be appreciated that there may be a plurality of second entities of the same or different contact types for each first entity, and that there may be a plurality of first entities of the same or different contact types for each second entity, and that the adjustment of the contact types and the adjustment of the event level thresholds are performed between the first entity and the second entity that have interacted with by event triggering, without changing the contact types and the event level thresholds between the other first entities and the second entity.
Taking fig. 3 as an example, assuming that the event 2 is a five-level event, the event 2 is sent to the entity C3, and after the entity C3 reads the event 2, the hidden contact between the entity A2 and the entity C3 is established, so as to delete the potential contact between the original entity a and the entity C3. When the first entity and the second entity group have potential connection, and when the second operation behavior of the first entity is triggered based on the event of a certain second entity (recorded as a second first entity) in the second entity group, the hidden connection of the second entity and the first entity is established, and the potential connection of the first entity and the second entity group is deleted, namely, in the case, the second entity is clarified.
The reduction of the contact type between the first entity and the second entity can be divided into the following cases:
and deleting the contact between the first entity and the second entity when the contact type between the first entity and the second entity group owner is potential contact, the second operation behavior is unread, and the unread operation times reach a first preset threshold value.
And when the contact type between the first entity and the second entity is a hidden contact, the second operation behavior is not read, and the operation times of the unread operation reach a second preset threshold value, the contact type between the first entity and the second entity is adjusted to be a potential contact.
And when the contact type between the first entity and the second entity is explicit contact, the second operation behavior is unread, and the unread operation times reach a third preset threshold, the event grade of sending the event to the first entity is improved until the event grade is improved to the preset grade, and the contact type between the first entity and the second entity is adjusted to be implicit contact. For example, assuming that the event threshold for initially setting the explicit contact is two-level, when the second operation behavior is not read, the contact between the first entity and the second entity is still the explicit contact, but at this time, the event level for sending the event to the first entity is increased to three-level, i.e. for this first entity, three or more levels of events can be sent to it. When the event level threshold corresponding to the first entity rises to the highest explicit contact event level threshold (in the embodiment of the present invention, the event level threshold of the explicit contact is one level to three levels), and the next second operation is not read, the contact type between the first entity and the second entity is adjusted to be an implicit contact.
The setting of the first preset threshold may be smaller than the second preset threshold, and the setting of the second preset threshold may be smaller than the third preset threshold, and for the first preset threshold corresponding to the potential contact, if only one event is sent to the first entity with the potential contact, the first preset threshold is set to 1.
From the above, it can be seen that, in the embodiment of the present invention, personalized information is pushed to the first entity based on the operation behavior of the first entity, without portraying the first entity, and the push policy is adjusted at any time according to the operation behavior of the first entity, thereby being more beneficial to improving user experience.
Example two
Referring to fig. 4, fig. 4 is a schematic structural diagram of a medical apparatus knowledge base construction device according to an embodiment of the present invention. As shown in fig. 4, the medical instrument knowledge base construction apparatus may include:
a model building unit 310, configured to build an E-R model based on a first operation behavior of a first entity, where the E-R model includes the first entity, a second entity, an event corresponding to the second entity, and a connection between the first entity and the second entity, where the connection includes three types of explicit connection, implicit connection, and potential connection, and priorities of the three types are, in order from high to low, explicit connection, implicit connection, and potential connection;
a triggering unit 320, configured to trigger, in response to an event corresponding to the second entity, a second operation behavior of the first entity based on a level of the event and a connection between the first entity and the second entity;
And an updating unit 330, configured to update the E-R model according to the second operation behavior, where the updating is to adjust a contact type between the first entity and the second entity.
Preferably, the model construction unit 310 may include:
the first acquisition subunit is used for acquiring the retrieval behavior or/and the attention behavior of the first entity on the medical instrument platform;
a first judging subunit, configured to determine, based on the search behavior, that the contact between the first entity and the second entity is a implicit contact or a potential contact;
a second judging subunit, configured to determine, based on the attention behavior, that the contact between the first entity and the second entity is an explicit contact;
and the third judging subunit is used for determining that the contact between the first entity and the second entity is an explicit contact when the first entity simultaneously searches and pays attention to the medical instrument platform.
Preferably, the first judging subunit may include:
judging whether the search behavior is accurate search or fuzzy search;
when the search behavior is accurate search, determining that the contact between the first entity and the target second entity is an implicit contact;
when the search behavior is fuzzy search, determining that the contact between the first entity and the second entity group is potential contact;
The target second entity is a second entity determined by accurate retrieval; the second entity group is all second entities determined for fuzzy retrieval.
Preferably, the triggering unit 320 may include:
the second acquisition subunit is used for acquiring the event corresponding to the second entity at regular or irregular time or in real time;
a dividing subunit, configured to divide the event into levels based on a preset classification rule;
a sending subunit, configured to send the event to the first entity based on the event level, the contact type, and a preset sending rule;
and the receiving subunit is used for receiving a second operation behavior of the first entity on the event, wherein the second operation behavior is reading or not reading.
Preferably, the preset sending rule is a level threshold of an event sent to the first entity under the condition that the first entity and the second entity establish an initial contact state; the event level is five levels, wherein the level of the first-level event is lowest, and the level of the fifth-level event is highest;
when the contact between the first entity and the second entity is potential contact, sending an event to the first entity, wherein the event level threshold of the event is five levels;
when the contact between the first entity and the second entity is a hidden contact, sending an event to the first entity, wherein the event level threshold of the event is four levels;
And when the contact between the first entity and the second entity is the explicit contact, sending an event to the first entity, wherein the event level threshold of the event is two-level.
Preferably, the updating unit 330 may include:
a promotion subunit, configured to promote a contact type between the first entity and the second entity when the second operation behavior is reading;
and the reducing subunit is used for reducing the contact type between the first entity and the second entity when the second operation behavior is not read.
Preferably, the lifting subunit may comprise:
when the contact type between the first entity and the second entity is potential contact and the second operation behavior is reading, adjusting the contact between the first entity and the target second entity to be implicit contact;
when the contact type between the first entity and the second entity is a hidden contact and the second operation behavior is reading, adjusting the contact type between the first entity and the second entity to be a dominant contact;
and when the contact type between the first entity and the second entity is an explicit contact and the second operation behavior is reading, reducing the event level of sending the event to the first entity until the event level is reduced to the minimum.
Preferably, the lowering subunit may include:
when the contact type between the first entity and the second entity group owner is potential contact, the second operation behavior is unread, and the unread operation times reach a first preset threshold value, deleting the contact of the first entity and the second entity;
when the contact type between the first entity and the second entity is a hidden contact, the second operation behavior is unread, and the unread operation times reach a second preset threshold value, the contact type between the first entity and the second entity is adjusted to be a potential contact;
when the contact type between the first entity and the second entity is explicit contact, the second operation behavior is unread, and the unread operation times reach a third preset threshold, the event grade of sending the event to the first entity is improved until the event grade is improved to the preset grade, and the contact type between the first entity and the second entity is adjusted to be implicit contact;
the first preset threshold value is smaller than a second preset threshold value, and the second preset threshold value is smaller than a third preset threshold value.
Example III
Referring to fig. 5, fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the invention. As shown in fig. 5, the electronic device may include:
A memory 310 in which executable program code is stored;
a processor 320 coupled to the memory 310;
wherein the processor 320 invokes the executable program code stored in the memory 310 to perform some or all of the steps in a medical instrument knowledge base construction method according to the first embodiment.
An embodiment of the present invention discloses a computer-readable storage medium storing a computer program, wherein the computer program causes a computer to execute some or all of the steps in a medical instrument knowledge base construction method in the first embodiment.
The embodiment of the invention also discloses a computer program product, wherein the computer program product enables the computer to execute part or all of the steps in the medical instrument knowledge base construction method in the first embodiment.
The embodiment of the invention also discloses an application release platform, wherein the application release platform is used for releasing the computer program product, and the computer is caused to execute part or all of the steps in the medical instrument knowledge base construction method in the first embodiment when the computer program product runs on the computer.
In various embodiments of the present invention, it should be understood that the size of the sequence numbers of the processes does not mean that the execution sequence of the processes is necessarily sequential, and the execution sequence of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer-accessible memory. Based on this understanding, the technical solution of the present invention, or a part contributing to the prior art or all or part of the technical solution, may be embodied in the form of a software product stored in a memory, comprising several requests for a computer device (which may be a personal computer, a server or a network device, etc., in particular may be a processor in a computer device) to execute some or all of the steps of the method according to the embodiments of the present invention.
In the embodiments provided herein, it should be understood that "B corresponding to a" means that B is associated with a, from which B can be determined. It should also be understood that determining B from a does not mean determining B from a alone, but may also determine B from a and/or other information.
Those of ordinary skill in the art will appreciate that some or all of the steps of the various methods of the described embodiments may be implemented by hardware associated with a program that may be stored in a computer-readable storage medium, including Read-Only Memory (ROM), random-access Memory (Random Access Memory, RAM), programmable Read-Only Memory (Programmable Read-Only Memory, PROM), erasable programmable Read-Only Memory (Erasable Programmable Read-Only Memory, EPROM), one-time programmable Read-Only Memory (OTPROM), electrically erasable programmable Read-Only Memory (EEPROM), compact disc Read-Only Memory (Compact Disc Read-Only Memory, CD-ROM), or other optical disk Memory, magnetic disk Memory, tape Memory, or any other medium capable of being used to carry or store data that is readable by a computer.
The above describes in detail a medical apparatus knowledge base construction method, an electronic device and a storage medium disclosed in the embodiments of the present invention, and specific examples are applied to illustrate the principles and embodiments of the present invention, where the above description of the embodiments is only used to help understand the method and core idea of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Claims (10)
1. The medical instrument knowledge base construction method is characterized by comprising the following steps of:
based on a first operation behavior of a first entity, an E-R model is constructed, wherein the E-R model comprises the first entity, a second entity, events corresponding to the second entity and the contact between the first entity and the second entity, the contact comprises three types of dominant contact, implicit contact and potential contact, and the three types of priority levels are dominant contact, implicit contact and potential contact in sequence from high to low;
responding to an event corresponding to a second entity, and triggering a second operation behavior of the first entity based on the level of the event and the contact between the first entity and the second entity;
And updating the E-R model according to the second operation behavior, wherein the updating is to adjust the contact type between the first entity and the second entity.
2. The medical device knowledge base construction method according to claim 1, wherein constructing an E-R model based on a first operational behavior of a first entity comprises:
acquiring retrieval behaviors or/and attention behaviors of the first entity on a medical instrument platform;
determining that the contact of the first entity and the second entity is a hidden contact or a potential contact based on the retrieval behavior;
determining that the contact of the first entity and the second entity is an explicit contact based on the behavior of interest;
when the first entity simultaneously retrieves and pays attention to the medical instrument platform, the contact of the first entity and the second entity is determined to be an explicit contact.
3. The medical device knowledge base construction method according to claim 2, wherein determining that the contact of the first entity and the second entity is a implicit contact or a potential contact based on the retrieving behavior comprises:
judging whether the search behavior is accurate search or fuzzy search;
when the search behavior is accurate search, determining that the contact between the first entity and the target second entity is an implicit contact;
When the search behavior is fuzzy search, determining that the contact between the first entity and the second entity group is potential contact;
the target second entity is a second entity determined by accurate retrieval; the second entity group is all second entities determined for fuzzy retrieval.
4. The medical device knowledge base construction method according to claim 1, wherein in response to an event corresponding to a second entity, triggering a second operational behavior of the first entity based on a ranking of the event and a connection between the first entity and the second entity comprises:
acquiring an event corresponding to the second entity at regular or irregular time or in real time;
grading the event based on a preset grading rule;
transmitting the event to the first entity based on the event level, the contact type and a preset transmission rule;
a second operational behavior of the first entity on the event is received, the second operational behavior being read or not read.
5. The medical device knowledge base construction method according to claim 4, wherein updating the E-R model according to the second operation behavior, the updating being to adjust a contact type between a first entity and a second entity, comprises:
When the second operation behavior is reading, the contact type between the first entity and the second entity is promoted;
and when the second operation behavior is not read, reducing the contact type between the first entity and the second entity.
6. The medical device knowledge base construction method according to claim 5, wherein when the second operation behavior is reading, promoting a contact type between the first entity and the second entity comprises:
when the contact type between the first entity and the second entity is potential contact and the second operation behavior is reading, adjusting the contact between the first entity and the target second entity to be implicit contact;
when the contact type between the first entity and the second entity is a hidden contact and the second operation behavior is reading, adjusting the contact type between the first entity and the second entity to be a dominant contact;
and when the contact type between the first entity and the second entity is an explicit contact and the second operation behavior is reading, reducing the event level of sending the event to the first entity until the event level is reduced to the minimum.
7. The medical device knowledge base construction method according to claim 5, wherein reducing the contact type between the first entity and the second entity when the second operation behavior is not read comprises:
When the contact type between the first entity and the second entity group owner is potential contact, the second operation behavior is unread, and the unread operation times reach a first preset threshold value, deleting the contact of the first entity and the second entity;
when the contact type between the first entity and the second entity is a hidden contact, the second operation behavior is unread, and the unread operation times reach a second preset threshold value, the contact type between the first entity and the second entity is adjusted to be a potential contact;
when the contact type between the first entity and the second entity is explicit contact, the second operation behavior is unread, and the unread operation times reach a third preset threshold, the event grade of sending the event to the first entity is improved until the event grade is improved to the preset grade, and the contact type between the first entity and the second entity is adjusted to be implicit contact;
the first preset threshold value is smaller than a second preset threshold value, and the second preset threshold value is smaller than a third preset threshold value.
8. The medical device knowledge base construction method according to claim 4, wherein the preset transmission rule is a level of an event transmitted to the first entity in an initial contact state established between the first entity and the second entity; the event level is five levels, wherein the level of the first-level event is lowest, and the level of the fifth-level event is highest;
When the contact between the first entity and the second entity is potential contact, sending an event to the first entity, wherein the event level threshold of the event is five levels;
when the contact between the first entity and the second entity is a hidden contact, sending an event to the first entity, wherein the event level threshold of the event is four levels;
and when the contact between the first entity and the second entity is the explicit contact, sending an event to the first entity, wherein the event level threshold of the event is two-level.
9. An electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor invokes the executable program code stored in the memory for performing the medical instrument knowledge base construction method of any one of claims 1-8.
10. A computer-readable storage medium, characterized in that it stores a computer program, wherein the computer program causes a computer to execute the medical instrument knowledge base construction method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211653814.6A CN116049326B (en) | 2022-12-22 | 2022-12-22 | Medical instrument knowledge base construction method, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211653814.6A CN116049326B (en) | 2022-12-22 | 2022-12-22 | Medical instrument knowledge base construction method, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116049326A true CN116049326A (en) | 2023-05-02 |
| CN116049326B CN116049326B (en) | 2024-03-08 |
Family
ID=86115562
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211653814.6A Active CN116049326B (en) | 2022-12-22 | 2022-12-22 | Medical instrument knowledge base construction method, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116049326B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015176560A1 (en) * | 2014-05-22 | 2015-11-26 | 华为技术有限公司 | User behavior recognition method, user equipment, and behavior recognition server |
| FR3027757A1 (en) * | 2014-10-27 | 2016-04-29 | Orange | METHOD AND SYSTEM FOR MANAGING CONNECTED ENTITIES |
| CN112667819A (en) * | 2020-12-07 | 2021-04-16 | 数据地平线（广州）科技有限公司 | Entity description reasoning knowledge base construction and reasoning evidence quantitative information acquisition method and device |
| US20210117509A1 (en) * | 2019-10-17 | 2021-04-22 | Adobe Inc. | Creating a knowledge graph based on text-based knowledge corpora |
| CN113158081A (en) * | 2021-05-10 | 2021-07-23 | 微民保险代理有限公司 | User relationship construction method and device, electronic equipment and storage medium |
| WO2021157897A1 (en) * | 2020-02-03 | 2021-08-12 | Samsung Electronics Co., Ltd. | A system and method for efficient multi-relational entity understanding and retrieval |
| CN114116736A (en) * | 2020-09-01 | 2022-03-01 | 上海智臻智能网络科技股份有限公司 | Knowledge base updating method and device, knowledge base updating verification method and device, and knowledge base-based searching method and device |
| CN114138985A (en) * | 2022-02-08 | 2022-03-04 | 深圳希施玛数据科技有限公司 | Text data processing method and device, computer equipment and storage medium |
| CN114297370A (en) * | 2021-12-28 | 2022-04-08 | 北京金堤科技有限公司 | Knowledge graph display method and device, computer storage medium and electronic equipment |
-
2022
- 2022-12-22 CN CN202211653814.6A patent/CN116049326B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015176560A1 (en) * | 2014-05-22 | 2015-11-26 | 华为技术有限公司 | User behavior recognition method, user equipment, and behavior recognition server |
| FR3027757A1 (en) * | 2014-10-27 | 2016-04-29 | Orange | METHOD AND SYSTEM FOR MANAGING CONNECTED ENTITIES |
| US20210117509A1 (en) * | 2019-10-17 | 2021-04-22 | Adobe Inc. | Creating a knowledge graph based on text-based knowledge corpora |
| WO2021157897A1 (en) * | 2020-02-03 | 2021-08-12 | Samsung Electronics Co., Ltd. | A system and method for efficient multi-relational entity understanding and retrieval |
| CN114116736A (en) * | 2020-09-01 | 2022-03-01 | 上海智臻智能网络科技股份有限公司 | Knowledge base updating method and device, knowledge base updating verification method and device, and knowledge base-based searching method and device |
| CN112667819A (en) * | 2020-12-07 | 2021-04-16 | 数据地平线（广州）科技有限公司 | Entity description reasoning knowledge base construction and reasoning evidence quantitative information acquisition method and device |
| CN113158081A (en) * | 2021-05-10 | 2021-07-23 | 微民保险代理有限公司 | User relationship construction method and device, electronic equipment and storage medium |
| CN114297370A (en) * | 2021-12-28 | 2022-04-08 | 北京金堤科技有限公司 | Knowledge graph display method and device, computer storage medium and electronic equipment |
| CN114138985A (en) * | 2022-02-08 | 2022-03-04 | 深圳希施玛数据科技有限公司 | Text data processing method and device, computer equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 周园春;常青玲;杜一;: "SKS：一种科技领域大数据知识图谱平台", 数据与计算发展前沿, no. 05, pages 86 - 97 * |
| 黄炜;程钰;李岳峰;: "基于知识服务的中医药个人健康知识库构建研究", 现代情报, no. 12, pages 80 - 87 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116049326B (en) | 2024-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11487831B2 (en) | Compatibility scoring of users | |
| JP6533384B2 (en) | Question delivery method of question answering platform and question delivery system | |
| JP5613951B2 (en) | Method for aggressive information push notification and server therefor | |
| CN107889069B (en) | Short message gateway selection method, device, server and readable storage medium | |
| CN103620585B (en) | virtual identity manager | |
| US9203912B2 (en) | Method and system for message value calculation in a mobile environment | |
| KR101960007B1 (en) | Opportunistic network updates | |
| US20140040378A1 (en) | System and Method for Managing an Online Social Network | |
| CN102741845A (en) | URL reputation system | |
| US20100131335A1 (en) | User interest mining method based on user behavior sensed in mobile device | |
| WO2008083324A1 (en) | Seeking answers to questions | |
| US20090037443A1 (en) | Intelligent group communication | |
| CN110196805B (en) | Data processing method, data processing apparatus, storage medium, and electronic apparatus | |
| CN109829593B (en) | Credit determining method and device for target object, storage medium and electronic device | |
| CN112052399B (en) | Data processing method, device and computer readable storage medium | |
| CN116049326B (en) | Medical instrument knowledge base construction method, electronic equipment and storage medium | |
| EP3011528A2 (en) | Wireless network and mac address device detection system and methods | |
| CN114119123A (en) | Information pushing method and device | |
| CN111399875A (en) | Gray scale upgrade control method and device, electronic equipment and storage medium | |
| CN113283486B (en) | Device type determination method based on wifi, electronic device and storage medium | |
| CN113114734B (en) | Information processing method, device, equipment and storage medium | |
| US20220147583A1 (en) | System and method for quality based ranking of patents | |
| CN112417301A (en) | Information pushing method, device, server and storage medium | |
| CN112732136A (en) | Desktop component adding method, desktop component adding device and terminal equipment | |
| CN113283483B (en) | Device type determining method based on wifi, electronic device 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |