CN111858922A - Service side information query method and device, electronic equipment and storage medium - Google Patents
Service side information query method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN111858922A CN111858922A CN201910907622.5A CN201910907622A CN111858922A CN 111858922 A CN111858922 A CN 111858922A CN 201910907622 A CN201910907622 A CN 201910907622A CN 111858922 A CN111858922 A CN 111858922A
- Authority
- CN
- China
- Prior art keywords
- service
- service party
- historical
- query
- information
- 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 68
- 238000010801 machine learning Methods 0.000 claims abstract description 70
- 238000011156 evaluation Methods 0.000 claims abstract description 68
- 238000012549 training Methods 0.000 claims abstract description 43
- 238000012163 sequencing technique Methods 0.000 claims description 27
- 238000004590 computer program Methods 0.000 claims description 6
- GNKZMNRKLCTJAY-UHFFFAOYSA-N 4'-Methylacetophenone Chemical compound CC(=O)C1=CC=C(C)C=C1 GNKZMNRKLCTJAY-UHFFFAOYSA-N 0.000 description 24
- 241000213996 Melilotus Species 0.000 description 24
- 235000000839 Melilotus officinalis subsp suaveolens Nutrition 0.000 description 24
- 238000010586 diagram Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000012545 processing Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 235000012054 meals Nutrition 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 241000209140 Triticum Species 0.000 description 1
- 235000021307 Triticum Nutrition 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 235000013410 fast food Nutrition 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Abstract
The application provides a service side information query method, a service side information query device, electronic equipment and a storage medium. The embodiment of the application judges whether the keywords of the service party to be inquired accord with the preset type to be inquired or not by acquiring the query information of the service party, and according to the query information of the service party and the text classification machine learning model, if so, at least one service party to be inquired corresponding to the keywords of the service party to be inquired and the accuracy evaluation result corresponding to each service party to be inquired are acquired, because the text classification machine learning model is obtained by training according to the historical service information, and the keywords of the service party to be inquired are judged whether accord with the preset type to be inquired or not by the text classification machine learning model, and then at least one service party to be inquired corresponding to the keywords of the service party to be inquired and the accuracy evaluation result corresponding to each service party to be inquired are determined, so that the query requirement of a user can be more accurately identified, and the accurate query result can be, the experience degree of the user is improved.
Description
Technical Field
The present application relates to the field of data query technologies, and in particular, to a method and an apparatus for querying information of a server, an electronic device, and a storage medium.
Background
At present, with the rapid development of network informatization, people have more and more demands on data query services, for example, query functions provided in many clients (application programs) can query positions, shops, enterprises and the like.
In the prior art, a user usually inputs related keywords in a query interface provided by a client, and queries according to the keywords through a search engine to obtain corresponding results.
However, with the prior art, the query result obtained only from the keyword is not necessarily the content that the user actually wants to query, and the accuracy is not high.
Disclosure of Invention
In view of the above, an object of the present application is to provide a method and an apparatus for querying information of a server, an electronic device, and a storage medium, which can predict a query result of a server of a user through query information of the server and a text classification machine learning model, so as to achieve the technical effects of accurately identifying a query requirement of the user and obtaining an accurate query result.
In a first aspect, an embodiment of the present application provides a method for querying information based on a server, including:
acquiring inquiry information of a service party, wherein the inquiry information of the service party comprises: user identification and keywords of a service party to be inquired;
acquiring the probability that the keywords of the service party to be inquired accord with the preset type to be inquired according to the inquiry information of the service party and the text classification machine learning model, and judging whether the probability is not less than a first preset threshold value;
and if the probability is not less than a first preset threshold value, outputting at least one to-be-determined service party corresponding to the keywords of the to-be-queried service party and accuracy evaluation results corresponding to each to-be-determined service party, wherein the text classification machine learning model is obtained according to historical service information training.
Optionally, before obtaining the query information of the service provider, the method further includes:
acquiring historical service information, wherein the historical service information comprises historical service order information, historical service party inquiry information, service party information and a historical service party inquiry result;
and training to obtain a text classification machine learning model according to the historical service information.
Further, training to obtain a text classification machine learning model according to the historical service information, wherein the training comprises:
Identifying historical inquiry service party keywords and historical service party inquiry results in the historical service party inquiry information;
obtaining historical query service party keywords corresponding to historical query results of a historical service party, wherein one historical query result of the historical service party corresponds to a plurality of historical query service party keywords, and/or one historical query service party keyword corresponds to a plurality of historical query results of the historical service party;
and training to obtain a text classification machine learning model according to the historical query service party keywords corresponding to the historical query service party query result.
Optionally, before obtaining the query information of the service provider, the method further includes:
acquiring historical service information, wherein the historical service information comprises historical service order information, historical service party inquiry information, service party information and a historical service party inquiry result;
and training to obtain a text classification machine learning model according to the historical service information.
Further, after the accuracy evaluation results corresponding to the to-be-determined service party and the to-be-determined service party are output, the method further includes:
comparing the accuracy evaluation result corresponding to each service party to be determined with a second preset threshold value;
and if at least one accuracy evaluation result is not smaller than a second preset threshold, pushing at least one to-be-determined service party not smaller than the second preset threshold to the user.
Further, after the accuracy evaluation results corresponding to the to-be-determined service party and the to-be-determined service party are output, the method further includes:
comparing the accuracy evaluation result corresponding to the undetermined service party with the highest accuracy evaluation result with a third preset threshold value;
and if the accuracy evaluation result is not less than the third preset threshold, pushing the unique service party corresponding to the third preset threshold to the user.
Further, after determining whether there is a service party corresponding to the keyword of the service party to be queried, the method further includes:
and if it is determined that at least one to-be-determined service party corresponding to the keywords of the to-be-queried service party exists and a plurality of to-be-determined service parties exist, sequencing the to-be-determined service parties according to a preset sequencing model, and acquiring sequencing results corresponding to the to-be-determined service parties.
Further, the method further comprises:
and updating the sequencing result according to the accuracy evaluation result corresponding to each service party to be determined and a preset sequencing model.
In a second aspect, an embodiment of the present application provides a server side information query apparatus, including: the device comprises an acquisition module, a judgment module and an output module;
the acquisition module is used for acquiring inquiry information of a service party, wherein the inquiry information of the service party comprises: user identification and keywords of a service party to be inquired;
The judging module is used for acquiring the probability that the keywords of the service party to be inquired accord with the preset type to be inquired according to the inquiry information of the service party and the text classification machine learning model and judging whether the probability is not less than a first preset threshold value;
and the output module is used for outputting at least one to-be-determined service party corresponding to the keywords of the to-be-queried service party and the accuracy evaluation result corresponding to each to-be-determined service party if the probability is not less than a first preset threshold, wherein the text classification machine learning model is obtained according to the historical service information training.
Optionally, the apparatus further comprises: a training module;
the acquisition module is also used for acquiring historical service information before acquiring the query information of the service party, wherein the historical service information comprises historical service order information, historical service party query information, service party information and a historical service party query result;
and the training module is used for training to obtain a text classification machine learning model according to the historical service information.
Further, the training module is used for training to obtain a text classification machine learning model according to the historical service information, and specifically comprises:
identifying historical inquiry service party keywords and historical service party inquiry results in the historical service party inquiry information;
Obtaining historical query service party keywords corresponding to historical query results of a historical service party, wherein one historical query result of the historical service party corresponds to a plurality of historical query service party keywords, and/or one historical query service party keyword corresponds to a plurality of historical query results of the historical service party;
and training to obtain a text classification machine learning model according to the historical query service party keywords corresponding to the historical query service party query result.
Further, the above apparatus further comprises:
the first comparison module is used for comparing the accuracy evaluation results corresponding to the to-be-determined service parties with a second preset threshold after outputting the to-be-determined service parties and the accuracy evaluation results corresponding to the to-be-determined service parties;
and the first pushing module is used for pushing at least one to-be-determined service party which is not smaller than the second preset threshold value to the user if at least one accuracy evaluation result is not smaller than the second preset threshold value.
Further, the above apparatus further comprises:
the second comparison module is used for comparing the accuracy evaluation result corresponding to the undetermined service party with the highest accuracy evaluation result with a third preset threshold after outputting the accuracy evaluation results corresponding to the undetermined service party and the undetermined service party;
And the second pushing module is used for pushing the only service party corresponding to the third preset threshold value to the user if the accuracy evaluation result is not smaller than the third preset threshold value.
Further, the above apparatus further comprises: and the sequencing module is used for sequencing the plurality of to-be-determined service parties according to a preset sequencing model and acquiring a sequencing result corresponding to the plurality of to-be-determined service parties if the to-be-determined service parties corresponding to the keywords of the to-be-queried service parties exist and the plurality of to-be-determined service parties exist after determining whether the service parties corresponding to the keywords of the to-be-queried service parties exist.
Further, the above apparatus further comprises: and the updating module is used for updating the sequencing result according to the accuracy evaluation result corresponding to each service party to be determined and a preset sequencing model.
In a third aspect, an embodiment of the present application provides an electronic device, including: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating via the bus when the electronic device is operating, the processor executing the machine-readable instructions to perform the steps of the server information query method according to the first aspect.
In a fourth aspect, an embodiment of the present application further provides a storage medium, where the storage medium stores a computer program, and the computer program is executed by a processor to perform the steps of the server side information query method according to the first aspect.
Based on any one of the above aspects, the application has the following beneficial effects:
according to the method and the device, the query information of the server is obtained, the server corresponding to the keywords of the server to be queried is determined to exist according to the query information of the server and the text classification machine learning model for prediction, the accuracy evaluation results corresponding to the server to be determined and the server to be determined are output, and the text classification machine learning model is obtained according to the historical service information through training and predicts the keywords of the server to be queried according to the text classification machine learning model, so that the query requirement of a user can be identified more accurately, the accurate query result is obtained for the user, and the experience of the user is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 is a schematic diagram illustrating an architecture of a service system provided in an embodiment of the present application;
FIG. 2 is a flowchart illustrating a method for querying information of a service provider according to an embodiment of the present application;
fig. 3 is a flowchart illustrating a method for querying information of a service provider according to an embodiment of the present application;
FIG. 4 is a flowchart illustrating a method for querying information of a service provider according to an embodiment of the present disclosure;
FIG. 5 is a flowchart illustrating a method for querying information of a service provider according to an embodiment of the present disclosure;
fig. 6 shows another flowchart of a method for querying information of a service provider according to an embodiment of the present application;
fig. 7 is a schematic structural diagram illustrating a server information query apparatus provided in an embodiment of the present application;
fig. 8 is a schematic structural diagram illustrating a server information query apparatus according to an embodiment of the present application;
fig. 9 shows a schematic structural diagram of an electronic device provided in an embodiment of the present application.
Detailed Description
In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it should be understood that the drawings in the present application are for illustrative and descriptive purposes only and are not used to limit the scope of protection of the present application. Additionally, it should be understood that the schematic drawings are not necessarily drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of the present application. It should be understood that the operations of the flow diagrams may be performed out of order, and steps without logical context may be performed in reverse order or simultaneously. One skilled in the art, under the guidance of this application, may add one or more other operations to, or remove one or more operations from, the flowchart.
In addition, the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.
In order to enable those skilled in the art to use the present disclosure, in combination with a specific application scenario "interactive process for querying information of a service party in a service process", the service may be: a riding service, a meal delivery service, a single car service, a payment service, and the like, the following embodiments are given. It will be apparent to those skilled in the art that the general principles defined herein may be applied to other embodiments and applications without departing from the spirit and scope of the application. Although the present application is described primarily in the context of querying a chain of stores during a ride service, it should be understood that this is merely one exemplary embodiment.
It should be noted that in the embodiments of the present application, the term "comprising" is used to indicate the presence of the features stated hereinafter, but does not exclude the addition of further features.
The terms "passenger," "requestor," "service requestor," and "customer" are used interchangeably in this application to refer to an individual, entity, or tool that can request or order a service. The terms "driver," "service provider," and "provider" are used interchangeably in this application to refer to an individual, entity, or tool that can provide a service. The term "user" in this application may refer to an individual, entity or tool that requests a service, subscribes to a service, provides a service, or facilitates the provision of a service. For example, the user may be a passenger, a driver, an operator, etc., or any combination thereof. In the present application, "passenger" and "passenger terminal" may be used interchangeably, and "driver" and "driver terminal" may be used interchangeably.
The terms "service request" and "order" are used interchangeably herein to refer to a request initiated by a passenger, a service requester, a driver, a service provider, or a supplier, the like, or any combination thereof. Accepting the "service request" or "order" may be a passenger, a service requester, a driver, a service provider, a supplier, or the like, or any combination thereof. The service request may be charged or free.
Before the application is filed, the prior technical scheme is as follows: people usually input related keywords to query data through a search engine to obtain corresponding results. The technical problems caused by the method are as follows: the query requirement of the user cannot be accurately identified, and an accurate query result is obtained. However, the embodiment of the application provides a server side information query method, which accurately predicts a server side query result through server side query information and a text classification machine learning model, so that the technical effects of accurately identifying a query requirement of a user and obtaining an accurate query result are achieved.
One aspect of the present application relates to a server side information query system. The system can establish contact through the server inquiry information between the service requester terminal and the service provider terminal, and accurately predict the server inquiry result through the server inquiry information and the text classification machine learning model, so that the technical effects of accurately identifying the inquiry requirements of users and acquiring accurate inquiry results are achieved.
Fig. 1 is a schematic architecture diagram of a server information query system 100 according to an embodiment of the present disclosure. For example, the server information query system 100 may be an online transportation service platform for transportation services such as taxi cab, designated drive service, express, carpool, bus service, driver rental, or regular service, or any combination thereof. The server information query system 100 may include one or more of a server 110, a network 120, a service requester terminal 130, a service provider terminal 140, and a database 150.
In some embodiments, the server 110 may include a processor. The processor may process information and/or data related to the service request to perform one or more of the functions described herein. For example, the processor may determine the target vehicle based on a service request obtained from the service requester terminal 130. In some embodiments, a processor may include one or more processing cores (e.g., a single-core processor (S) or a multi-core processor (S)). Merely by way of example, a Processor may include a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), an Application Specific Instruction Set Processor (ASIP), a Graphics Processing Unit (GPU), a Physical Processing Unit (PPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), a controller, a microcontroller Unit, a reduced Instruction Set computer (reduced Instruction Set computer), a microprocessor, or the like, or any combination thereof.
In some embodiments, the device types corresponding to the service requester terminal 130 and the service provider terminal 140 may be mobile devices, such as smart home devices, wearable devices, smart mobile devices, virtual reality devices, augmented reality devices, and the like, and may also be tablet computers, laptop computers, built-in devices in motor vehicles, and the like.
In some embodiments, a database 150 may be connected to network 120 to communicate with one or more components in the server information query system 100 (e.g., server 110, service requestor terminal 130, service provider terminal 140, etc.). One or more components in the server information query system 100 may access data or instructions stored in the database 150 via the network 120. In some embodiments, the database 150 may be directly connected to one or more components in the server-side information query system 100, or the database 150 may be part of the server 110.
The service information query method provided by the embodiment of the present application is described in detail below with reference to the content described in the service information query system 100 shown in fig. 1.
Referring to fig. 2, a schematic flowchart of a method for querying information of a service provider provided in an embodiment of the present application is shown, where the method may be executed by a service provider terminal 140 in a system 100 for querying information of a service provider, and the specific execution process includes:
For example, in a scene of taking a car, a user wants to find a chain hotel near a destination, and at this time, the user may input a keyword of the chain hotel in real time, for example, a 7-day chain hotel, and the service provider obtains service query information of the user, that is, a user identifier, which may be a user identifier that can identify the user such as a name, a mobile phone number, a registered account number, and a keyword of a service party to be queried, for example: the keywords or character strings of the service party can be identified by 7-day and 7-day chain hotels, 7Days Inn and the like, and the types of the keywords and the character strings can be Chinese, English, pinyin, simple pinyin, text expression with wrongly written or mispronounced characters and the like, but not limited to the above.
102, obtaining the probability that the keywords of the service party to be inquired accord with the preset type to be inquired according to the inquiry information of the service party and the text classification machine learning model, and judging whether the probability is larger than a first preset threshold value.
Specifically, the query requirement of the user is predicted according to the acquired server query information and the text classification machine learning model, wherein the text classification machine learning model can adopt FastText (fast text classifier), which is a word vector and text classification tool of Facebook open source, and has the characteristics of being fast, greatly shortening training time while maintaining classification effect, being suitable for large-scale data processing, and supporting multi-language expression, inputting a word sequence (a text or a sentence) through the FastText model, outputting the probability that the word sequence belongs to different categories, in the application, the text classification machine learning model is acquired according to historical service information, and the probability that the to-be-queried server accords with the preset to-be-queried type can be acquired according to the server query information and the trained text classification machine learning model, the preset type to be searched can be a chain brand service party, an independent service party, a specific service party and the like, and the specific type setting can be set according to the actual situation, for example, the keyword of the service party to be searched is 7days, the probability value that the 7days are consistent with the chain brand service party is 80%, whether the probability value corresponding to the 7days is not less than a first preset threshold value is judged, and if the first threshold value is 60%, the keyword of the service party to be searched is consistent with the preset type to be searched, namely, the 7days are consistent with the type of the chain brand service party. For example, if the keyword of the service party to be queried is "beijing", and the obtained probability value is 0, it indicates that "beijing" does not conform to the preset type to be queried, and there is no pending service party corresponding to the chain brand service party.
And 103, if the probability is not less than a first preset threshold value, outputting at least one to-be-determined service party corresponding to the keywords of the to-be-queried service party and accuracy evaluation results corresponding to each to-be-determined service party, wherein the text classification machine learning model is obtained according to historical service information training.
Specifically, if the probability that the keyword of the service party to be queried meets the preset type is not less than the first preset threshold, it indicates that the keyword meets the requirement of the type to be queried, at least one service party to be determined corresponding to the keyword of the service party to be queried will be continuously obtained, and the service parties to be determined may be words whose names are the same as or similar to the keywords of the service party to be queried. Continuing with the above example, when the keyword of the service party to be queried is "7 days", the keyword conforms to the type to be queried of the chain brand service party, and then a text classification machine learning model can be used to obtain a plurality of service parties to be queried, such as "7-day chain hotels", "7-day premium products", and corresponding accuracy evaluation results, where the accuracy evaluation results can be represented by probability values, and also can be represented by accurate, inaccurate, fuzzy, and equal grades, where the probability values used as the accuracy evaluation results can be more accurate, for example, the probability of "7-day chain hotels" is 80%, the probability of "7-day premium products" is 20%, and in short, the sum of the probabilities output by each service party to be queried is 1, and the keyword can be determined according to actual situations, which is not limited herein.
In the method for querying information of a service provider provided by this embodiment, by obtaining query information of the service provider, according to the query information of the service provider and a text classification machine learning model, it is first determined whether a keyword of the service provider to be queried matches a preset type to be queried, and if so, at least one service provider to be queried corresponding to the keyword of the service provider to be queried and an accuracy assessment result corresponding to each service provider to be determined are obtained, because the text classification machine learning model is obtained by training according to historical service information, and the keyword of the service provider to be queried is first determined by the text classification machine learning model to match the preset type to be queried, and then at least one service provider corresponding to the keyword of the service provider to be queried and the accuracy assessment result corresponding to each service provider are determined, so that query requirements of a user can be identified more accurately, and an accurate query result is obtained for the user, the experience degree of the user is improved.
Optionally, referring to fig. 3, before obtaining the query information of the service provider, the method further includes:
Specifically, the historical service information may include historical service order information, historical service side query information, service side information, historical service side query results, and the like. The historical service order information may be order information of historical riding trips, including information of a departure place, a destination, time and the like, or historical order information of historical ordering, including information of restaurant addresses, meal delivery addresses, time and the like, or historical order information of home services, including information of home company addresses, home service addresses, time and the like. The history service side query information includes a user identifier and a history query service side keyword of the user, for example, the history query service side keyword may be "7-day", "Seven-day", "7 tie", "7D" and the like input by the user a and the history query service side result as "7-day chain hotel" and/or "7-day premium product", or the history query service side keyword may be "mcdonglou", "Mc", "mcdonglou", "Mcd" and the like input by the user B and the history query service side result as "mcdonglou"; the service side information may include a service side name, an address, a telephone number, identification information, and the like, and the service side identification result may include a historical service side query result corresponding to a plurality of historical query service side keywords, and/or a historical query service side keyword corresponding to a plurality of historical service side query results, by obtaining the historical service information, it is mainly intended to extract historical information of the user query service side from the historical service information, and obtain the historical query service side keywords, character strings, historical service side query results, and service side numbers or identification codes and the like corresponding to the historical service side query results, but not limited thereto.
The historical service information may select a data set of a certain period of time according to an actual situation, and the data set is input to a text classification machine learning model for training to obtain a trained text classification machine learning model, for example, the text classification machine model may be a FastText model, a FastText model is adopted, a historical query keyword, a word segmentation result such as a character string, and an N-gram feature are input, where N may be an integer greater than or equal to 2, a server information and a server query result are output, the server query result includes a server identifier and a probability of querying a server corresponding to the server keyword, but is not limited to that FastText may specifically select different text classification machine learning models according to an actual situation.
Further, referring to fig. 4, training to obtain a text classification machine learning model according to the historical service information includes:
And 303, training to obtain a text classification machine learning model according to the historical query service party keywords corresponding to the historical query service party query result.
Specifically, according to the obtained historical service information, the historical query service party keywords and the historical query service party query result in the historical service information can be identified. For example, the historical query service side keyword may be "7-Day," "7-Day hotel," "7-Day restaurant," "Seven Day," "7 tie," "7D," and the like, and the historical query service side result may be "7-Day chain hotel," "7-Day premium," and the like, and according to the identified historical query service side keyword and the historical query service side query result, the historical query service side keyword corresponding to the historical query result may be obtained, that is, one historical query service side query result corresponds to a plurality of historical query service side keywords, and/or one historical query service side keyword corresponds to a plurality of historical query service side query results, for example: the historical query service side keywords corresponding to the 7-Day chain hotel comprise 7-Day keywords, 7-Day hotels, Seven Day keywords, 7 tians and 7D keywords and the 7-Day superior product keywords comprise 7-Day keywords, 7-Day catering keywords, Seven Day keywords, 7 tians and 7D keywords and the like, and according to the corresponding relation, the following historical query service keywords comprising 7-Day keywords, Seven Day keywords, 7 tians and 7D can be obtained to correspond to a plurality of service sides such as the historical service side query result of 7-Day chain hotels, 7-Day superior products and the like, then according to the historical query service side keywords corresponding to the historical service side query result, a text classification machine learning model can be obtained through training, and the query service side keywords input by the user in real time are input into the text classification machine learning model, and determining whether at least one pending service party corresponding to the query service party keyword exists.
It should be noted that, the present application is not limited to training the model based on the historical service information, and may also configure the historical query service keyword corresponding to the historical query result according to experience.
An embodiment is given below, which is to obtain a text classification machine learning model by training a historical service side query result corresponding to a plurality of historical query service side keywords in the obtained historical service information, and the detailed description is as follows:
table 1 shows a result table of training a text classification machine learning model provided in the embodiment of the present application, and as shown in table 1, the following provides a historical server query result corresponding to a user historical query server keyword.
At this time, in the case that the historical service provider to be queried is "mcdonald chain fast food restaurant", first, a query (query) data set, a service provider number (code), a service provider name (name), and an accuracy evaluation result (prob) obtained through training of a text classification machine learning model may be queried according to the historical service provider obtained in the historical service information.
TABLE 1
| query | code numbering | name | prob probability value |
| Root of beautiful Sweetclover | 53115 | Root of beautiful Sweetclover | 0.9736367 |
| Caulis et folium Ipomoeae | 53115 | Root of beautiful Sweetclover | 0.1111111 |
| Maidang (wheat seed) | 53115 | Root of beautiful Sweetclover | 0.9577664 |
| Mc | 53115 | Root of beautiful Sweetclover | 0.6232382 |
| Maidanglau (a Chinese character of' Maidanglau | 53115 | Root of beautiful Sweetclover | 0.704918 |
| I/F | 53115 | Root of beautiful Sweetclover | 0.9224877 |
| Mcdonglo tian | 53115 | Root of beautiful Sweetclover | 0.6 |
| Maidan Lao | 53115 | Root of beautiful Sweetclover | 0.9099274 |
| mai | 53115 | Root of beautiful Sweetclover | 0.2624348 |
| mai dang l | 53115 | Root of beautiful Sweetclover | 0.9280443 |
| mai dang lao | 53115 | Root of beautiful Sweetclover | 0.9089953 |
| mai dang | 53115 | Root of beautiful Sweetclover | 0.9103967 |
| mc | 53115 | Root of beautiful Sweetclover | 0.0974961 |
| mai d | 53115 | Root of beautiful Sweetclover | 0.5830904 |
| Sell when | 53115 | Root of beautiful Sweetclover | 0.9064748 |
| Mcd | 53115 | Root of beautiful Sweetclover | 0.8902439 |
| McDonald | 53115 | Root of beautiful Sweetclover | 0.903876 |
| mdl | 53115 | Root of beautiful Sweetclover | 0.5598313 |
| maidanglao | 53115 | Root of beautiful Sweetclover | 0.8971119 |
| Maidang lao | 53115 | Root of beautiful Sweetclover | 0.9326241 |
| Mcdonald | 53115 | Root of beautiful Sweetclover | 0.8927944 |
| Wheat Dang | 53115 | Root of beautiful Sweetclover | 0.8964758 |
| mai dan | 53115 | Root of beautiful Sweetclover | 0.9094017 |
As can be seen from the information in table 1, the method can identify the keywords of the service party to be queried, which are chinese, english, pinyin, simple pinyin, and even have wrongly written characters, can accurately provide the service party corresponding to the keywords of the service party to be queried according to the keywords, and provide the corresponding accuracy evaluation result, i.e., the probability value, which can reflect the possibility that the keywords of the service party to be queried correspond to the query result, and the probability value is higher, and the probability value can be considered in the process of training the model or in the process of recommending the query result.
Further, referring to fig. 5, after the accuracy evaluation results corresponding to the to-be-determined service party and the to-be-determined service party are output, the method further includes:
Specifically, the obtained real-time service provider query information can be input into a trained text classification machine learning model, when the fact that the keywords of the service provider to be queried have corresponding undetermined service providers is judged, at least one undetermined service provider and accuracy evaluation results corresponding to the undetermined service providers, namely the probability corresponding to the undetermined service providers, are returned, and the probability value is compared with a second preset threshold value. For example, when the keyword of the service party to be queried is "7 days", a plurality of pending service parties such as "7-day chain hotels" and "7-day premium" may be obtained, and according to the text classification machine learning model, accuracy evaluation results corresponding to different service parties for "7 days" may be obtained, for example, according to the output after training of the text classification machine learning model, that is, the probability of the "7-day chain hotels" corresponding to the first pending service party is 55%, the probability of the "7-day premium" corresponding to the second pending service party is 45%, and the like, assuming that the second preset threshold is 40%, the accuracy evaluation results corresponding to the outputted plurality of service parties may be compared with the second preset threshold to obtain more than or equal to 40% of the pending service parties corresponding to the pending service parties, that is, the pending service parties for "7-day chain hotels" and "7-day premium" may be pushed to the user, and the user can select the method according to the actual requirement of the user.
Further, referring to fig. 6, after the accuracy evaluation results corresponding to the to-be-determined service party and the to-be-determined service party are output, the method further includes:
And 502, if the accuracy evaluation result is not less than a third preset threshold, pushing the unique service party corresponding to the third preset threshold to the user.
Specifically, the query information of the real-time service party is acquired, and can be input into a trained text classification machine learning model, and when the keyword of the service party to be queried is judged to have a corresponding undetermined service party, at least one undetermined service party and an accuracy evaluation result corresponding to the undetermined service party, that is, a probability corresponding to the undetermined service party is returned, wherein the highest probability value is compared with a third preset threshold value, for example, when the keyword of the service party to be queried is "wanda", a plurality of undetermined service parties such as "wanda market", "wanda district", "wanda cinema" and the like may come out, and according to the text classification machine learning model, the accuracy evaluation results corresponding to different service parties to be determined can be obtained, for example, according to the output after the text classification machine learning model is trained, that the probability of the "wanda market" corresponding to the first service party to be determined is 92%, the probability of the Wanda cell corresponding to the second undetermined service party is 5%, the probability of the Wanda cinema corresponding to the third undetermined service party is 3%, and the like, and if the third preset threshold is 90%, the highest probability value can be compared with the third preset threshold, and the unique service party corresponding to the Wanda cell is obtained, namely the Wanda market is pushed to the user, so that the user requirement can be accurately identified, and an accurate query result is obtained.
Further, after determining whether there is a service party corresponding to the keyword of the service party to be queried, the method further includes:
and if it is determined that at least one to-be-determined service party corresponding to the keywords of the to-be-queried service party exists and a plurality of to-be-determined service parties exist, sequencing the identifiers corresponding to the plurality of to-be-determined service parties according to a preset sequencing model, and acquiring sequencing results corresponding to the plurality of to-be-determined service parties.
Specifically, the obtained real-time service provider query information can be input into a trained text classification machine learning model, when the service provider to be queried has a corresponding service provider to be determined according to the keyword, then at least one undetermined service party and the accuracy evaluation result corresponding to the undetermined service party, namely the probability corresponding to the undetermined service party are returned, if a plurality of undetermined service parties exist, the multiple service parties to be inquired can be sequenced according to a preset sequencing model, and the sequencing results corresponding to the multiple service parties to be inquired can be obtained, for example, when the keyword of the service party to be inquired is 'Wanda', a plurality of undetermined service parties such as a Wanda mall, a Wanda district and a Wanda cinema can come out, and sequencing the plurality of to-be-determined service parties according to a preset sequencing model, for example, the sequencing result output after training of the sequencing model is as follows: the ranking result is pushed to the user, so that the user can conveniently select the ranking result according to the actual situation, wherein the ranking model can be obtained based on the probability value corresponding to the undetermined service party, the distance between the undetermined service party and the user, the frequency of inquiring the undetermined service party by the user, and other influence factors, and historical data of the influence factors, and the ranking model is obtained according to the actual situation, and is not limited herein.
Further, the method further comprises:
and updating the sequencing result according to the accuracy evaluation result corresponding to each service party to be determined and a preset sequencing model.
Specifically, after the accuracy evaluation result corresponding to each service party to be ordered is obtained according to the method, the accuracy evaluation result can be used as an influence factor of a preset ordering model, the ordering model is improved, and accurate ordering can be performed according to the requirements of users when a plurality of service parties to be ordered are output.
According to the method and the device, the query information of the server is obtained, the prediction is carried out according to the query information of the server and the text classification machine learning model, the accuracy evaluation results corresponding to the to-be-determined server and the to-be-determined server are output, a plurality of to-be-determined servers or the only server can be pushed to the user according to the accuracy evaluation results, the text classification machine learning model is obtained by training according to the historical service information, the keywords of the to-be-queried server are predicted according to the text classification machine learning model, the query requirement of the user can be identified more accurately, the accurate query result is obtained for the user, and the experience degree of the user is improved.
The embodiment of the application provides a server information query method, which comprises the steps of firstly judging whether a keyword of a server to be queried accords with a preset type to be queried according to the server query information and a text classification machine learning model, if so, obtaining at least one server to be determined corresponding to the keyword of the server to be queried and an accuracy evaluation result corresponding to each server to be determined, wherein the text classification machine learning model is obtained by training according to historical service information, firstly judging whether the keyword of the server to be queried accords with the preset type to be queried through the text classification machine learning model, and then determining at least one server to be determined corresponding to the keyword of the server to be queried and the accuracy evaluation result corresponding to each server to be determined, so that the query requirement of a user can be more accurately identified, and an accurate query result can be obtained for the user, the experience degree of the user is improved.
Based on the same inventive concept, the embodiment of the present application further provides a server information query device corresponding to the server information query method, and as the principle of solving the problem of the device in the embodiment of the present application is similar to that of the server information query method in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and repeated details are not repeated.
Referring to fig. 7, a schematic diagram of a server information query apparatus according to an embodiment of the present application is shown, where the server information query apparatus 600 includes: an acquisition module 601, a judgment module 602 and an output module 603;
the obtaining module 601 is configured to obtain service side query information, where the service side query information includes: user identification and keywords of a service party to be inquired;
the judging module 602 is configured to obtain, according to the service provider query information and the text classification machine learning model, a probability that a keyword of the service provider to be queried matches a preset type to be queried, and judge whether the probability is not less than a first preset threshold;
the output module 603 is configured to, if the probability is not smaller than a first preset threshold, obtain at least one to-be-determined service party corresponding to the to-be-queried service party keyword and an accuracy evaluation result corresponding to each to-be-determined service party, where the text classification machine learning model is obtained according to historical service information training.
The embodiment provides a server information query device, which comprises an acquisition module, a judgment module and an output module, wherein the acquisition module is used for acquiring server query information, the judgment module is used for judging whether a keyword of a server to be queried accords with a preset type to be queried or not according to the server query information and a text classification machine learning model, if the keyword of the server to be queried accords with the preset type to be queried, the output module is used for acquiring at least one server to be queried corresponding to the keyword of the server to be queried and an accuracy evaluation result corresponding to each server to be determined, the text classification machine learning model is obtained by training according to historical service information, the keyword of the server to be queried is judged whether accords with the preset type to be queried or not through the text classification machine learning model, and then at least one server to be queried corresponding to the keyword of the server to be queried and the accuracy evaluation result corresponding to each server to be determined, therefore, the query requirement of the user can be identified more accurately, an accurate query result can be obtained for the user, and the user experience is improved.
In a possible implementation, referring to fig. 8, the apparatus 600 further includes: a training module 604;
the obtaining module 601 is further configured to obtain historical service information before obtaining query information of a service provider, where the historical service information includes historical service order information, historical service provider query information, service provider information, and a historical service provider query result;
and the training module 604 is configured to train to obtain a text classification machine learning model according to the historical service information.
In a possible implementation manner, the training module 604 is configured to train to obtain a text classification machine learning model according to the historical service information, and specifically includes:
identifying historical inquiry service party keywords and historical service party inquiry results in the historical service party inquiry information;
obtaining historical query service party keywords corresponding to historical query results of a historical service party, wherein one historical query result of the historical service party corresponds to a plurality of historical query service party keywords, and/or one historical query service party keyword corresponds to a plurality of historical query results of the historical service party;
and training to obtain a text classification machine learning model according to the historical query service party keywords corresponding to the historical query service party query result.
In a possible implementation, referring to fig. 7, the apparatus 600 further includes:
the first comparing module 605 is configured to compare the accuracy evaluation results corresponding to the to-be-determined service providers and the second preset threshold after outputting the to-be-determined service providers and the accuracy evaluation results corresponding to the to-be-determined service providers;
the first pushing module 606 is configured to, if the at least one accuracy evaluation result is not smaller than the second preset threshold, push at least one to-be-determined server that is not smaller than the second preset threshold to the user.
In a possible implementation, referring to fig. 8, the apparatus 600 further includes:
the second comparing module 607 is configured to compare, after outputting the to-be-determined service party and the accuracy evaluation result corresponding to the to-be-determined service party, the accuracy evaluation result corresponding to the to-be-determined service party with the highest accuracy evaluation result with a third preset threshold;
the second pushing module 608 is configured to, if the accuracy evaluation result is not smaller than the third preset threshold, push the only service party corresponding to the third preset threshold to the user.
In a possible implementation, referring to fig. 8, the apparatus 600 further includes:
the sorting module 609 is configured to, after determining whether there is a server corresponding to the keyword of the server to be queried, if it is determined that there is at least one to-be-determined server corresponding to the keyword of the server to be queried and there are multiple to-be-determined servers, sort the multiple to-be-determined servers according to a preset sorting model, and obtain a sorting result corresponding to the multiple to-be-determined servers.
In a possible implementation, referring to fig. 8, the apparatus 600 further includes:
the updating module 610 is configured to update the ranking result according to the accuracy evaluation result corresponding to each service to be determined and a preset ranking model.
The description of the processing flow of each module in the device and the interaction flow between the modules may refer to the related description in the above method embodiments, and will not be described in detail here.
An embodiment of the present application further provides an electronic device 700, as shown in fig. 9, which is a schematic structural diagram of the electronic device 700 provided in the embodiment of the present application, and includes: a processor 701, a memory 702, and a bus 703. The memory 702 stores machine-readable instructions executable by the processor 701, when the electronic device 700 runs, the processor 701 communicates with the memory 702 through the bus 703, and the machine-readable instructions are executed by the processor 701 to execute instructions executed by each module in the service-side-based information query apparatus according to the foregoing method embodiment.
For ease of illustration, only one processor is described in the electronic device. However, it should be noted that the electronic device in the present application may also comprise a plurality of processors, and thus the steps performed by one processor described in the present application may also be performed by a plurality of processors in combination or individually. For example, if the processor of the electronic device executes steps a and B, it should be understood that steps a and B may also be executed by two different processors together or separately in one processor. For example, a first processor performs step a and a second processor performs step B, or the first processor and the second processor perform steps a and B together.
In addition, in the electronic device, the memory may include: various media capable of storing program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.
The functions described in the foregoing embodiments, if implemented in the form of software functional units and sold or used as independent products, may also be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application.
The embodiment of the application also provides a storage medium, wherein a computer program is stored on the storage medium, and when the computer program is executed by a processor, the steps of the server side information query method are executed.
Specifically, the storage medium can be a general storage medium, such as a mobile disk, a hard disk, and the like, when a computer program on the storage medium is run, the server side information query method can be executed, and a server side query result of a user can be predicted through server side query information and a text classification machine learning model, so that the technical effects of accurately identifying a query requirement of the user and obtaining an accurate query result are achieved.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the apparatus described above may refer to corresponding processes in the method embodiments, and are not described in detail in this application. In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. The above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical division, and there may be other divisions in actual implementation, and for example, a plurality of modules or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or modules through some communication interfaces, and may be in an electrical, mechanical or other form.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules 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 can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A method for inquiring service side information is characterized by comprising the following steps:
acquiring inquiry information of a service party, wherein the inquiry information of the service party comprises: user identification and keywords of a service party to be inquired;
acquiring the probability that the keywords of the service party to be inquired accord with the preset type to be inquired according to the inquiry information of the service party and a text classification machine learning model, and judging whether the probability is not less than a first preset threshold value;
and if the probability is not less than a first preset threshold value, outputting at least one to-be-determined service party corresponding to the to-be-queried service party keyword and an accuracy evaluation result corresponding to each to-be-determined service party, wherein the text classification machine learning model is obtained according to historical service information training.
2. The method of claim 1, wherein before obtaining the service query information, the method further comprises:
acquiring the historical service information, wherein the historical service information comprises historical service order information, historical service party query information, service party information and a historical service party query result;
and training to obtain the text classification machine learning model according to the historical service information.
3. The method of claim 2, wherein training the text classification machine learning model according to the historical service information comprises:
identifying historical inquiry service party keywords and historical service party inquiry results in the historical service party inquiry information;
obtaining historical query service party keywords corresponding to historical query results of a historical service party, wherein one historical query result of the historical service party corresponds to a plurality of historical query service party keywords, and/or one historical query service party keyword corresponds to a plurality of historical query results of the historical service party;
and training to obtain the text classification machine learning model according to the historical query service party keywords corresponding to the historical query service party query result.
4. The method according to any one of claims 1 to 3, wherein after the outputting the pending service and the accuracy evaluation result corresponding to the pending service, the method further comprises:
comparing the accuracy evaluation result corresponding to each service party to be determined with a second preset threshold value;
and if at least one accuracy evaluation result is not smaller than a second preset threshold, pushing at least one to-be-determined service party not smaller than the second preset threshold to the user.
5. The method according to any one of claims 1 to 3, wherein after the outputting the pending service and the accuracy evaluation result corresponding to the pending service, the method further comprises:
comparing the accuracy evaluation result corresponding to the undetermined service party with the highest accuracy evaluation result with a third preset threshold value;
and if the accuracy evaluation result is not less than a third preset threshold, pushing the only service party corresponding to the third preset threshold to the user.
6. The method according to any one of claims 1 to 3, wherein after determining whether there is a service party corresponding to the service party keyword to be queried, the method further comprises:
if it is determined that at least one to-be-determined service party corresponding to the to-be-queried service party keyword exists and a plurality of to-be-determined service parties exist, sequencing the to-be-determined service parties according to a preset sequencing model, and obtaining a sequencing result corresponding to the to-be-determined service parties.
7. The method of claim 6, further comprising:
and updating the sequencing result according to the accuracy evaluation result corresponding to each service party to be determined and the preset sequencing model.
8. A server side information inquiry apparatus, comprising: the device comprises an acquisition module, a judgment module and an output module;
the obtaining module is configured to obtain service side query information, where the service side query information includes: user identification and keywords of a service party to be inquired;
the judging module is used for acquiring the probability that the keywords of the service party to be inquired accord with the preset type to be inquired according to the inquiry information of the service party and the text classification machine learning model, and judging whether the probability is not less than a first preset threshold value;
and the output module is used for outputting at least one to-be-determined service party corresponding to the to-be-queried service party keyword and an accuracy evaluation result corresponding to each to-be-determined service party if the probability is not smaller than a first preset threshold, wherein the text classification machine learning model is obtained according to historical service information training.
9. An electronic device, comprising: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating over the bus when the electronic device is operating, the processor executing the machine-readable instructions to perform the steps of the method of any one of claims 1 to 7.
10. A storage medium, having stored thereon a computer program which, when executed by a processor, performs the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910907622.5A CN111858922A (en) | 2019-09-24 | 2019-09-24 | Service side information query method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910907622.5A CN111858922A (en) | 2019-09-24 | 2019-09-24 | Service side information query method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111858922A true CN111858922A (en) | 2020-10-30 |
Family
ID=72970578
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910907622.5A Pending CN111858922A (en) | 2019-09-24 | 2019-09-24 | Service side information query method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111858922A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112100202A (en) * | 2020-11-12 | 2020-12-18 | 北京药联健康科技有限公司 | Product identification and product information completion method, storage medium and robot |
| CN115293790A (en) * | 2022-09-30 | 2022-11-04 | 中信建投证券股份有限公司 | User loss prediction method and device |
| CN116028700A (en) * | 2023-03-29 | 2023-04-28 | 小米汽车科技有限公司 | Off-line inquiring method and device for vehicle |
| CN116304277A (en) * | 2023-03-01 | 2023-06-23 | 深圳一资源网络平台有限公司 | Intelligent matching method, system and storage medium based on AI |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017035970A1 (en) * | 2015-08-31 | 2017-03-09 | 北京百度网讯科技有限公司 | Information pushing method and apparatus |
| US20170193020A1 (en) * | 2015-12-30 | 2017-07-06 | Yahoo!, Inc. | Query-goal-mission structures |
| CN107958406A (en) * | 2017-11-30 | 2018-04-24 | 北京小度信息科技有限公司 | Inquire about acquisition methods, device and the terminal of data |
| CN110019676A (en) * | 2017-12-01 | 2019-07-16 | 北京搜狗科技发展有限公司 | A kind of method, apparatus and equipment identifying core word in query information |
-
2019
- 2019-09-24 CN CN201910907622.5A patent/CN111858922A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017035970A1 (en) * | 2015-08-31 | 2017-03-09 | 北京百度网讯科技有限公司 | Information pushing method and apparatus |
| US20170193020A1 (en) * | 2015-12-30 | 2017-07-06 | Yahoo!, Inc. | Query-goal-mission structures |
| CN107958406A (en) * | 2017-11-30 | 2018-04-24 | 北京小度信息科技有限公司 | Inquire about acquisition methods, device and the terminal of data |
| CN110019676A (en) * | 2017-12-01 | 2019-07-16 | 北京搜狗科技发展有限公司 | A kind of method, apparatus and equipment identifying core word in query information |
Non-Patent Citations (2)
| Title |
|---|
| 向来生;孙威;刘希玉;: "基于SAS的web文本分类模型研究", 山东师范大学学报(自然科学版), no. 02 * |
| 杨杰;徐越;余建桥;蒋建华;: "基于搜索引擎日志的用户查询意图分类", 指挥信息系统与技术, no. 02 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112100202A (en) * | 2020-11-12 | 2020-12-18 | 北京药联健康科技有限公司 | Product identification and product information completion method, storage medium and robot |
| CN115293790A (en) * | 2022-09-30 | 2022-11-04 | 中信建投证券股份有限公司 | User loss prediction method and device |
| CN116304277A (en) * | 2023-03-01 | 2023-06-23 | 深圳一资源网络平台有限公司 | Intelligent matching method, system and storage medium based on AI |
| CN116304277B (en) * | 2023-03-01 | 2023-12-15 | 张素愿 | Intelligent matching method, system and storage medium based on AI |
| CN116028700A (en) * | 2023-03-29 | 2023-04-28 | 小米汽车科技有限公司 | Off-line inquiring method and device for vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106296059B (en) | Method and equipment for determining delivery network points | |
| CN111858922A (en) | Service side information query method and device, electronic equipment and storage medium | |
| TWI508011B (en) | Category information providing method and device | |
| US8095547B2 (en) | Method and apparatus for detecting spam user created content | |
| CN109492180A (en) | Resource recommendation method, device, computer equipment and computer readable storage medium | |
| JP5969697B2 (en) | Completing the application interface using search query keywords | |
| WO2013009947A2 (en) | System and method for advertisement placement | |
| CN109300059B (en) | Dish recommending method and device | |
| CN105468649B (en) | Method and device for judging matching of objects to be displayed | |
| TW201401088A (en) | Search method and apparatus | |
| CN106815265B (en) | Method and device for searching referee document | |
| CN112102031A (en) | Recommendation method, recommendation device and terminal equipment | |
| CN111858873A (en) | Method and device for determining recommended content, electronic equipment and storage medium | |
| CN106934679A (en) | information matching method and device | |
| KR20210032691A (en) | Method and apparatus of recommending goods based on network | |
| CN110704486B (en) | Data processing method, device, system, storage medium and server | |
| CN110717095B (en) | Service item pushing method and device | |
| CN109101630B (en) | Method, device and equipment for generating search result of application program | |
| CN111582967A (en) | Content search method, device, equipment and storage medium | |
| CN113744002A (en) | Method, device, equipment and computer readable medium for pushing information | |
| WO2017049760A1 (en) | Search result processing method, apparatus and device, and computer storage medium | |
| CN107391728B (en) | Data mining method and data mining device | |
| CN111274471A (en) | Information pushing method and device, server and readable storage medium | |
| CN113469792A (en) | Phone skill recommendation method and device, electronic equipment and storage medium | |
| CN113327132A (en) | Multimedia recommendation method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |