CN112767096B - Product recommendation method and device - Google Patents
Product recommendation method and device Download PDFInfo
- Publication number
- CN112767096B CN112767096B CN202110205485.8A CN202110205485A CN112767096B CN 112767096 B CN112767096 B CN 112767096B CN 202110205485 A CN202110205485 A CN 202110205485A CN 112767096 B CN112767096 B CN 112767096B
- Authority
- CN
- China
- Prior art keywords
- product
- target
- information
- recommendation
- algorithm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 72
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 133
- 238000004364 calculation method Methods 0.000 claims description 39
- 230000008569 process Effects 0.000 claims description 23
- 238000012163 sequencing technique Methods 0.000 claims description 22
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 description 15
- 238000004590 computer program Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- 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
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a product recommending method and a product recommending device, which are characterized in that target characteristic data are gradually determined in a preset configuration table through a recommending bit identifier carried in product recommending request information sent by a user side, and after the target characteristic data are processed by using a corresponding target recommending algorithm, a product recommending result which meets the scene requirement of a recommending bit corresponding to the recommending bit identifier can be obtained, so that the product recommending result is more accurate, and the quality of product recommending service is improved.
Description
Technical Field
The present invention relates to the field of information processing technologies, and in particular, to a product recommendation method and apparatus.
Background
With the annual development of internet technology, the means for providing online product services are also diversified. Currently, a product service provider may provide a product recommendation service, a product description service, a product sales service, and the like to a customer through a product-related website and APP, as well as a product-related applet developed on a third party.
Today, the customer population and the product application scenario for the product service provider are gradually diversified, which brings higher challenges to the product service provider in providing the product recommendation service. Therefore, in order to improve the quality of product services as a whole in a new form, product service providers are pressing to need an efficient product recommendation method.
Disclosure of Invention
In view of the above problems, the present invention provides a product recommendation method and apparatus for overcoming the above problems or at least partially solving the above problems, and the technical solution is as follows:
a product recommendation method comprising:
obtaining product recommendation request information sent by a user side, wherein the product recommendation request information carries a recommendation bit identifier;
inquiring the recommended position identification in a preset tenant configuration table to obtain tenant characteristic information corresponding to the recommended position identification;
determining a target model identification through the tenant characteristic information or task configuration information corresponding to the recommended bit identification in a preset task configuration table;
inquiring the target model identification in a preset model configuration table to obtain algorithm characteristic information corresponding to the target model identification;
obtaining target feature data according to the recommendation bit service data in the product recommendation request information, the product service line identification in the tenant feature information and the algorithm feature table name in the algorithm feature information;
and according to the model interface address in the algorithm characteristic information, calling a target recommendation algorithm model corresponding to the target model identifier to process the target characteristic data, and obtaining a product recommendation result.
Optionally, the determining the target model identifier according to the tenant feature information or the task configuration information corresponding to the recommended bit identifier in a preset task configuration table includes:
under the condition that the recommended bit identifier is inquired in a preset task configuration table, determining task configuration information corresponding to the recommended bit identifier in the preset task configuration table; determining a target model identification through a model shunting mode in the task configuration information;
and under the condition that the recommendation bit identification is not queried in the preset task configuration table, determining an algorithm model identification in the tenant characteristic information as the target model identification.
Optionally, the obtaining target feature data according to the recommendation bit service data in the product recommendation request information, the product service line identifier in the tenant feature information, and the algorithm feature table name in the algorithm feature information includes:
inquiring and obtaining original characteristic data in a preset database table according to the recommendation bit service data in the product recommendation request information, the product service line identification in the tenant characteristic information and the algorithm characteristic table name in the algorithm characteristic information;
And converting the original characteristic data into target characteristic data by using a preset characteristic project corresponding to the target recommendation algorithm model.
Optionally, after the target feature data is processed by calling a target recommendation algorithm model corresponding to the target model identifier according to the model interface address in the algorithm feature information to obtain a product recommendation result, the method further includes:
according to the target information in the product recommendation request information, grouping and sorting the product recommendation results to obtain grouping and sorting results;
determining a target product to be calculated in a trial mode according to the grouping sequencing result;
and performing trial calculation on the target product to obtain trial calculation data corresponding to the target product.
Optionally, before the calculating the target product and obtaining the calculating data corresponding to the target product, the method further includes:
and determining whether a product combination function is started or not according to the product combination information in the tenant characteristic information, if so, combining each target product according to a preset product combination mode to obtain a product combination scheme, and displaying the product combination scheme at the user side.
Optionally, before the calculating the target product and obtaining the calculating data corresponding to the target product, the method further includes:
and determining whether a new product recommending function is started according to the new product recommending information in the tenant characteristic information, if so, carrying out new product sequencing on each target product according to a preset new product sequencing mode to obtain a new product sequencing result, and displaying the new product sequencing result at the user side.
A product recommendation device, comprising: a request information obtaining unit, a tenant characteristic information obtaining unit, a target model identification determining unit, an algorithm characteristic information obtaining unit, a target characteristic data obtaining unit and a product recommendation result obtaining unit,
the request information obtaining unit is used for obtaining product recommendation request information sent by a user side, wherein the product recommendation request information carries a recommendation bit identifier;
the tenant characteristic information obtaining unit is used for inquiring the recommended bit identifier in a preset tenant configuration table to obtain tenant characteristic information corresponding to the recommended bit identifier;
the target model identification determining unit is used for determining a target model identification through the tenant characteristic information or task configuration information corresponding to the recommended bit identification in a preset task configuration table;
The algorithm characteristic information obtaining unit is used for inquiring the target model identifier in a preset model configuration table to obtain algorithm characteristic information corresponding to the target model identifier;
the target feature data obtaining unit is used for obtaining target feature data according to the recommendation bit service data in the product recommendation request information, the product service line identification in the tenant feature information and the algorithm feature table name in the algorithm feature information;
and the product recommendation result obtaining unit is used for calling a target recommendation algorithm model corresponding to the target model identifier to process the target feature data according to the model interface address in the algorithm feature information, so as to obtain a product recommendation result.
Optionally, the object model identification determining unit includes: a task configuration information determination subunit, a first object model identification determination subunit, and a second object model identification determination subunit,
the task configuration information determining subunit is configured to determine task configuration information corresponding to the recommended bit identifier in a preset task configuration table when the recommended bit identifier is queried in the preset task configuration table;
The first target model identification determining subunit is configured to determine a target model identification according to a model splitting mode in the task configuration information;
the second target model identifier determining subunit is configured to determine, when the recommendation bit identifier is not queried in the preset task configuration table, an algorithm model identifier in the tenant feature information as the target model identifier.
Optionally, the target feature data obtaining unit includes: the raw feature data acquisition subunit and the feature data conversion subunit,
the original characteristic data obtaining subunit is configured to query and obtain original characteristic data in a preset database table according to the recommendation bit service data in the product recommendation request information, the product service line identifier in the tenant characteristic information, and the algorithm characteristic table name in the algorithm characteristic information;
the feature data conversion subunit is configured to convert the original feature data into target feature data by using a preset feature project corresponding to the target recommendation algorithm model.
Optionally, the apparatus further includes: a grouping sorting result obtaining unit, a product to be calculated determining unit and a calculation data obtaining unit,
The grouping and sorting result obtaining unit is used for calling a target recommendation algorithm model corresponding to the target model identifier according to the model interface address in the algorithm feature information to process the target feature data, and after obtaining a product recommendation result, sorting the product recommendation result in a grouping manner according to the target information in the product recommendation request information to obtain a grouping and sorting result;
the product to be calculated determining unit is used for determining a target product to be calculated according to the grouping sequencing result;
and the trial calculation data obtaining unit is used for carrying out trial calculation on the target product to obtain trial calculation data corresponding to the target product.
By means of the technical scheme, the product recommendation method and device provided by the invention acquire the product recommendation request information sent by the user side, wherein the product recommendation request information carries a recommendation position identifier; inquiring the recommended position identification in a preset tenant configuration table to obtain tenant characteristic information corresponding to the recommended position identification; determining a target model identification through the tenant characteristic information or task configuration information corresponding to the recommended bit identification in a preset task configuration table; inquiring the target model identification in a preset model configuration table to obtain algorithm characteristic information corresponding to the target model identification; obtaining target feature data according to the recommendation bit service data in the product recommendation request information, the product service line identification in the tenant feature information and the algorithm feature table name in the algorithm feature information; and according to the model interface address in the algorithm characteristic information, calling a target recommendation algorithm model corresponding to the target model identifier to process the target characteristic data, and obtaining a product recommendation result. According to the recommendation bit identification carried in the product recommendation request information sent by the user side, the target feature data is determined step by step in the preset configuration table, and after the target feature data is processed by using the corresponding target recommendation algorithm, the product recommendation result which meets the scene requirement of the recommendation bit corresponding to the recommendation bit identification can be obtained, so that the product recommendation result is more accurate, and the quality of product recommendation service is improved.
The foregoing description is only an overview of the present invention, and is intended to be implemented in accordance with the teachings of the present invention in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present invention more readily apparent.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
fig. 1 shows a flow chart of a product recommendation method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of another product recommendation method according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart of another product recommendation method according to an embodiment of the present invention;
FIG. 4 is a schematic flow chart of another product recommendation method according to an embodiment of the present invention;
fig. 5 shows a schematic structural diagram of a product recommendation device according to an embodiment of the present invention;
Fig. 6 shows a schematic structural diagram of another product recommendation device according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
As shown in fig. 1, a product recommendation method provided by an embodiment of the present invention includes:
s100, obtaining product recommendation request information sent by a user side, wherein the product recommendation request information carries a recommendation bit identifier.
The user side may also be referred to as a client side or a tenant service side. The recommendation bit identification corresponds to a recommendation bit. Optionally, the recommendation-site identification may include a tenant identification of the tenant of the recommendation site. For example: the first bit of the recommendation bit identification is the tenant identification of the tenant of the recommendation bit.
Optionally, the product recommendation request information may further include recommendation bit service data. The recommended position business data at least comprises information of the insured life. Optionally, the recommended bits business data may also include product risk and other data related to the recommended bits.
Optionally, the user may input the insured life information on a visual interface of the user side, where the insured life information may include the date of birth information, age information, sex information, and other basic information of the insured life.
According to the embodiment of the invention, after the corresponding recommendation bit is determined, the recommendation bit service data and the recommendation bit identifier corresponding to the recommendation bit are packaged into the product recommendation request information, and the product recommendation request information is sent.
S200, inquiring the recommended bit identifier in a preset tenant configuration table to obtain tenant characteristic information corresponding to the recommended bit identifier.
The preset tenant configuration table may record feature information related to the tenant of the recommendation bit. Specifically, the embodiment of the invention can query the recommended bit identifier in the preset tenant configuration table, and determine tenant characteristic information corresponding to the recommended bit identifier in the preset tenant configuration table under the condition that the recommended bit identifier is queried.
Optionally, the tenant feature information may include: tenant identity (tensid), recommendation bit identity (clientId), product line identity (operationId), product combination information (projectGenInclude), new product recommendation information (newproduct include), product recommendation number (recductnum), and algorithm model identity (algoModelname).
It will be appreciated that the algorithm model identification corresponds to a recommended algorithm model. For example: the algorithm model identification corresponding to any recommended algorithm model can be a model name or a model code number.
It can be understood that when a new recommendation bit is added, the embodiment of the invention can add the corresponding tenant characteristic information for the recommendation bit in the preset tenant configuration table so as to provide a product recommendation function for the tenant of the recommendation bit.
S300, determining a target model identification through the tenant characteristic information or task configuration information corresponding to the recommendation bit identification in a preset task configuration table.
Optionally, the embodiment of the invention can query the recommended bit identifier in a preset task configuration table and determine task configuration information corresponding to the recommended bit identifier, wherein the task configuration information comprises the recommended bit identifier.
Optionally, the task configuration information may include tenant identifier (tenant id), recommendation bit identifier (clientId), model splitting mode (Rule), enable status (status), and dead time (endTime).
Optionally, in the embodiment of the present invention, the algorithm model identifier in the tenant feature information may be determined as the target model identifier, and the algorithm model identifier determined by the model splitting manner in the task configuration information may also be determined as the target model identifier.
Optionally, based on the method shown in fig. 1, as shown in fig. 2, another product recommendation method provided in the embodiment of the present invention, step S300 may include:
s310, under the condition that the recommended bit identification is inquired in a preset task configuration table, determining task configuration information corresponding to the recommended bit identification in the preset task configuration table.
The preset task configuration table is related to the current service line. The service line may be a related service of any kind of item. For example: insurance product related services. And under the condition that the recommended bit corresponding to the recommended bit identifier participates in the test of the current service line, task configuration information corresponding to the recommended bit identifier is stored in a preset task configuration list.
Optionally, in the embodiment of the present invention, if the recommended bit identifier is queried in the preset task configuration table, an enabling state and/or a failure time in the task configuration information corresponding to the recommended bit identifier may be determined, and if the enabling state is enabled and/or the failure time is not exceeded, step S320 is executed, otherwise step S330 is executed.
S320, determining a target model identification through a model shunting mode in the task configuration information.
The model split mode may be an AB split mode (running). Specifically, in the embodiment of the invention, under the condition that the recommended bit identifier is queried in the task configuration table, a random number is generated, and the algorithm model identifier corresponding to the random number is determined to be the target model identifier through the AB split-flow mode in the task configuration information corresponding to the recommended bit identifier. For example: the AB split mode can be that when the random number is larger than 0.3, the algorithm model identification A is determined to be the target model identification, and when the random number is not larger than 0.3, the algorithm model identification B is determined to be the target model identification.
S330, determining an algorithm model identifier in the tenant characteristic information as the target model identifier under the condition that the recommendation bit identifier is not queried in the preset task configuration table.
According to the embodiment of the invention, under the condition that the recommendation bit participates in the current service line test, the target model identification is preferentially determined according to the model splitting mode in the task configuration information corresponding to the recommendation bit identification corresponding to the recommendation bit, so that the target recommendation algorithm model corresponding to the target model identification is invoked later to be more suitable for the actual requirement of the current service line, and the quality of the whole product recommendation service is improved.
S400, inquiring the target model identification in a preset model configuration table to obtain algorithm characteristic information corresponding to the target model identification.
The preset model configuration table may store algorithm feature information of at least one recommended algorithm model. According to the embodiment of the invention, the target model identifier can be queried in the preset model configuration table, and the algorithm characteristic information corresponding to the target model identifier in the preset model configuration table is determined under the condition that the target model identifier is queried.
Alternatively, the algorithm characteristic information may include: an algorithm model identification (algoModelName), a model interface address (serviceUrl), a list of features required for the algorithm model (features_tables), and an algorithm model state (config_status).
The feature list required by the algorithm model may correspond to at least one algorithm feature table name.
It can be understood that when a new recommended algorithm model is added, algorithm feature information including information such as a model identifier, a model interface address and a feature list required by the algorithm model can be configured for the recommended algorithm model in a preset model configuration table, so that a new recommended algorithm model is provided for tenants in a recommendation position.
S500, obtaining target feature data according to the recommendation bit service data in the product recommendation request information, the product service line identification in the tenant feature information and the algorithm feature table name in the algorithm feature information.
Optionally, based on the method shown in fig. 1, as shown in fig. 3, another product recommendation method provided in the embodiment of the present invention, step S500 may include:
s510, inquiring and obtaining original characteristic data in a preset database table according to the recommendation bit service data in the product recommendation request information, the product service line identification in the tenant characteristic information and the algorithm characteristic table name in the algorithm characteristic information.
Optionally, the original feature data may include customer feature data in a customer feature wide table in the preset feature wide table library, product feature data in a product feature wide table, products belonging to a service line of a planning book in the product wide table, recommended dangerous seed range, customer feature information and product feature information.
Optionally, the customer characteristic data includes a customer source channel and a registration duration.
Optionally, the product characteristic data includes product shelf time and product sales data.
Specifically, the embodiment of the invention can query and read the customer characteristic data in the customer characteristic wide table and the product characteristic data in the product characteristic wide table corresponding to the algorithm characteristic table name according to the algorithm characteristic table name. The embodiment of the invention can inquire and read the products belonging to the planned business line in the product characteristic wide table according to the business line identification of the products. The embodiment of the invention can determine the recommended dangerous seed range according to the identification of the product dangerous seed in the recommended bit service data. For example: "2026-child safety_serious disease", "2031-child safety_medical risk".
Optionally, the embodiment of the invention can encapsulate the recommended bit service data in the product recommendation request information, the product service line identifier in the tenant feature information and the algorithm feature table name in the algorithm feature information into feature data request information, send the feature data request information to a preset feature system server, store the feature data request information in a preset process database by the preset feature system server, and query and obtain the original feature data in a preset database table of the preset feature system server according to the recommended bit service data in the product recommendation request information in the feature data request information, the product service line identifier in the tenant feature information and the algorithm feature table name in the algorithm feature information.
Optionally, the preset feature system server may perform preprocessing including summary statistics and structured extraction architecture on the pre-stored data at regular time, and generate a fine-grained feature broad table usable by the target recommendation algorithm model. The preset feature system server can monitor the process and the result of generating the feature broad table. Optionally, the preset feature system service end may provide a data query service in a webservice interface service manner, so as to provide high available feature data. The preset feature system server side can store interface request parameters, interface return results and response time consumption of each interface at each stage in the whole execution process of the embodiment of the invention, so that the related interfaces can be optimized later.
S520, converting the original characteristic data into target characteristic data by using a preset characteristic project corresponding to the target recommendation algorithm model.
Optionally, the embodiment of the present invention may execute, by a program for invoking a preset feature project corresponding to a target recommendation algorithm model, a feature project step at least including feature-associating product feature data in the original feature data with the insured person information, taking product sales volume data corresponding to the insured person information as a sales volume feature value, and generating an average sales volume and an average sales volume ordered high-order derivative feature from the product shelf time and the product sales volume data. Optionally, the program of the preset feature engineering may further fill the feature missing values in the original feature data, segment the continuous feature values, sequence number or one-hot map the discrete feature values, and perform computation such as cross addition, subtraction, multiplication, division and logarithm on the multiple basic features to generate advanced derivative features, thereby completing conversion from the original feature data to the target feature data.
Optionally, after the original feature data sent by the preset feature system server is obtained, the embodiment of the invention can splice the original feature data with the insured life information to generate the recommendation request information, send the recommendation request information to the preset recommendation algorithm server, call a program of the preset feature engineering by the preset recommendation algorithm server to convert the original feature data in the recommendation request information into the target feature data, and assemble the target feature data with the insured life information.
S600, according to the model interface address in the algorithm characteristic information, a target recommendation algorithm model corresponding to the target model identification is called to process the target characteristic data, and a product recommendation result is obtained.
Alternatively, the target recommendation algorithm model may include a secondary category recommendation model, a similar product recommendation model, an associated product recommendation model, a family method recommendation model, a underwriting product recommendation model, and a specific crowd product recommendation model.
Specifically, in the embodiment of the invention, the target recommendation algorithm model is called through the model interface address in the algorithm feature information corresponding to the target model identification, the target feature data is input into the target recommendation algorithm model, the recommendation value of each product in the preset product set is determined according to the target feature data by the target recommendation algorithm model, and the product recommendation result comprising the recommendation value of each product is output.
Optionally, in the embodiment of the present invention, the recommendation request information may be sent to a model interface address in the preset model configuration table configured by the preset recommendation algorithm server, and after the original feature data is converted into the target feature data, the target feature data is processed by using a target recommendation algorithm model corresponding to the model interface address.
Optionally, the embodiment of the invention can store the product recommendation result in a preset process database of a preset feature system server.
Optionally, the embodiment of the invention can send the product recommendation result to the user side for display.
Optionally, the embodiment of the invention can directly provide the product recommendation result to the user terminal through the RPC (Remote Procedure Call Protocol) interface, thereby ensuring the safety of data transmission and saving computer resources.
According to the product recommendation method provided by the embodiment of the invention, the product recommendation request information sent by the user side is obtained, wherein the product recommendation request information carries a recommendation position identifier; inquiring the recommended position identification in a preset tenant configuration table to obtain tenant characteristic information corresponding to the recommended position identification; determining a target model identification through the tenant characteristic information or task configuration information corresponding to the recommended bit identification in a preset task configuration table; inquiring the target model identification in a preset model configuration table to obtain algorithm characteristic information corresponding to the target model identification; obtaining target feature data according to the recommendation bit service data in the product recommendation request information, the product service line identification in the tenant feature information and the algorithm feature table name in the algorithm feature information; and according to the model interface address in the algorithm characteristic information, calling a target recommendation algorithm model corresponding to the target model identifier to process the target characteristic data, and obtaining a product recommendation result. According to the recommendation bit identification carried in the product recommendation request information sent by the user side, the target feature data is determined step by step in the preset configuration table, and after the target feature data is processed by using the corresponding target recommendation algorithm, the product recommendation result which meets the scene requirement of the recommendation bit corresponding to the recommendation bit identification can be obtained, so that the product recommendation result is more accurate, and the quality of product recommendation service is improved.
Optionally, based on the method shown in fig. 1, as shown in fig. 4, another product recommendation method provided in the embodiment of the present invention, after step S600, the method further includes:
s700, sorting the product recommendation results in groups according to the target information in the product recommendation request information, and obtaining the sorting results.
Alternatively, the target information may be a product hazard. The embodiment of the invention can group the product recommendation results according to the product dangerous types. For example: the dangerous products include serious child risks, serious adult risks and serious adult risks, and the recommended products can be divided into four groups according to the embodiment of the invention.
The embodiment of the invention can determine the recommended product number of each group according to the product recommended number in the tenant characteristic information. For example, when the number of product recommendations is 10, the products in each group in the grouping results of the product recommendation results are sorted in descending order according to the recommendation values, and 10 products with higher ranks in each group are screened out.
S800, determining a target product to be calculated in a trial mode according to the grouping sequencing result.
For ease of understanding, this is illustrated by way of example: if the product recommendation results can be divided into four groups including serious child risks, serious adult risks and serious adult risks, and the product recommendation number is 10, the serious child risks group comprises 10 products, the serious child risks comprise 10 products, the serious adult risks comprise 10 products and the serious adult risks comprise 10 products, and 40 products are target products to be calculated.
Optionally, the embodiment of the invention can store the grouping sequencing result in a preset process database of a preset feature system server.
S900, performing trial calculation on the target product to obtain trial calculation data corresponding to the target product.
The embodiment of the invention can call the preset trial calculation interface, substitutes the information of the person to be protected into the target products for simulation trial calculation, and determines the trial calculation data calculated by each target product under the information of the person to be protected and the specific trial calculation items associated with the preset trial calculation interface.
Optionally, the embodiment of the invention can call the preset trial calculation interface for multiple times, read the product trial calculation factor corresponding to the target product, combine the product trial calculation factor and the information of the person to be protected, and simulate and trial calculate the trial calculation data of the target product calculated under the information of the person to be protected and the specific trial calculation item associated with the preset trial calculation interface.
Optionally, the trial calculation data may include a premium corresponding to the insured life information and the target product.
Optionally, in the trial calculation process, the failed target product can be filtered, and the sorting result of the packet is reordered.
Optionally, the embodiment of the invention can send the final grouping sequencing result and the trial calculation data corresponding to each target product in the grouping sequencing result to the user side for display.
According to the method and the device for recommending the target product, through the trial calculation data obtained after the target product is subjected to trial calculation, clear and accurate trial calculation data of the target product can be provided for the user in the process of recommending the target product, and the quality of product recommending service is further improved.
Optionally, before trial calculation is performed on the target products, the embodiment of the invention can determine whether a product combination function is started according to the product combination information in the tenant characteristic information, if so, each target product is combined according to a preset product combination mode to obtain a product combination scheme, and the product combination scheme is displayed at the user side.
It can be appreciated that the embodiment of the invention can pre-configure different parameters for whether the product combination function is started. For example: 1 is "on" and 0 is "not on". And when the parameters corresponding to the product combination information in the tenant characteristic information are 1, determining that the product combination function is started. And when the parameters corresponding to the product combination information in the tenant characteristic information are 0, determining that the product combination function is not started.
Optionally, the preset product combination mode may be that the target product with the highest recommended value in each group in the group sorting result is combined into one product combination scheme, or that the target product with the next highest recommended value in each group in the group sorting result is combined into another product combination scheme. It is understood that the preset product combination may be set according to actual requirements, and the present disclosure is not limited to the preset product combination.
Optionally, the embodiment of the invention can store the product combination scheme into a preset process database of a preset feature system server.
According to the product combination scheme obtained by combining the target products according to the preset product combination mode, the product combination scheme can be directly displayed at the user side, so that part or all of the target products in the product recommendation result can be conveniently recommended to the user, and the quality of product recommendation service is improved.
Optionally, before trial calculation is performed on the target products, the embodiment of the invention can determine whether a new product recommending function is started according to the new product recommending information in the tenant characteristic information, if so, the new product ordering is performed on each target product according to a preset new product ordering mode, a new product ordering result is obtained, and the new product ordering result is displayed on the user side.
It can be appreciated that the embodiment of the invention can pre-configure different parameters for whether the new product recommending function is started. For example: 1 is "on" and 0 is "not on". And when the parameter corresponding to the new product recommendation information in the tenant characteristic information is 1, determining that the new product recommendation function is started. And when the parameter corresponding to the new product recommendation information in the tenant characteristic information is 0, determining that the new product recommendation function is not started.
Optionally, the embodiment of the invention can determine the new product value of each target product according to the recommended value of each target product in the grouping sequencing result and the preset new product weight value corresponding to each target product, and then based on the grouping sequencing result, sequencing the new product values of each target product from large to small to obtain the new product sequencing result of each group. The preset new weight value is related to the product shelf time of the target product. For example: the longer the product shelf life of any target product is, the smaller the corresponding preset new product weight value of the target product is.
Optionally, the embodiment of the invention can store the new product ordering result of each group into a preset process database of a preset feature system server.
According to the embodiment of the invention, the new product value of each target product in the grouping sequencing result is determined, each grouping is reordered according to the new product value, so that the new product sequencing result of each grouping is obtained, the newly-shelf target products in the product recommending result are conveniently recommended to the user preferentially, and the quality of product recommending service is improved.
Although the present disclosure depicts operations in a particular order, this should not be understood as requiring that these operations be performed in the particular order shown or in sequential order. In certain circumstances, multitasking and parallel processing may be advantageous.
It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order and/or performed in parallel. Furthermore, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.
Corresponding to the above method embodiment, the embodiment of the present invention further provides a product recommendation device, where the structure of the product recommendation device is shown in fig. 5, and the product recommendation device may include: a request information obtaining unit 100, a tenant feature information obtaining unit 200, a target model identification determining unit 300, an algorithm feature information obtaining unit 400, a target feature data obtaining unit 500, and a product recommendation result obtaining unit 600.
The request information obtaining unit 100 is configured to obtain product recommendation request information sent by a user side, where the product recommendation request information carries a recommendation bit identifier.
The tenant feature information obtaining unit 200 is configured to query the recommended bit identifier in a preset tenant configuration table, and obtain tenant feature information corresponding to the recommended bit identifier.
The target model identifier determining unit 300 is configured to determine a target model identifier according to the tenant feature information or task configuration information corresponding to the recommended bit identifier in a preset task configuration table.
Optionally, the object model identification determining unit 300 includes: the task configuration information determining subunit, the first object model identification determining subunit and the second object model identification determining subunit.
The task configuration information determining subunit is configured to determine task configuration information corresponding to the recommended bit identifier in the preset task configuration table when the recommended bit identifier is queried in the preset task configuration table.
The first target model identification determining subunit is configured to determine a target model identification according to a model splitting mode in the task configuration information.
The second target model identifier determining subunit is configured to determine, when the recommendation bit identifier is not queried in the preset task configuration table, an algorithm model identifier in the tenant feature information as the target model identifier.
The algorithm feature information obtaining unit 400 is configured to query the target model identifier in a preset model configuration table, and obtain algorithm feature information corresponding to the target model identifier.
The target feature data obtaining unit 500 is configured to obtain target feature data according to the recommended bit service data in the product recommendation request information, the product service line identifier in the tenant feature information, and the algorithm feature table name in the algorithm feature information.
Optionally, the target feature data obtaining unit 500 includes: a raw feature data obtaining subunit and a feature data converting subunit.
The original characteristic data obtaining subunit is configured to query and obtain original characteristic data in a preset database table according to the recommendation bit service data in the product recommendation request information, the product service line identifier in the tenant characteristic information, and the algorithm characteristic table name in the algorithm characteristic information;
the feature data conversion subunit is configured to convert the original feature data into target feature data by using a preset feature project corresponding to the target recommendation algorithm model.
The product recommendation result obtaining unit 600 is configured to call a target recommendation algorithm model corresponding to the target model identifier according to the model interface address in the algorithm feature information to process the target feature data, so as to obtain a product recommendation result.
According to the product recommendation device provided by the embodiment of the invention, the target characteristic data is determined step by step in the preset configuration table through the recommendation bit identifier carried in the product recommendation request information sent by the user side, and the corresponding target recommendation algorithm is used for processing the target characteristic data, so that the product recommendation result which meets the scene requirement of the recommendation bit corresponding to the recommendation bit identifier can be obtained, the product recommendation result is more accurate, and the quality of product recommendation service is improved.
Optionally, based on the apparatus shown in fig. 5, as shown in fig. 6, another product recommendation apparatus provided in the embodiment of the present invention may further include: a grouping sorting result obtaining unit 700, a to-be-calculated product determining unit 800, and a trial calculation data obtaining unit 900.
The grouping and sorting result obtaining unit 700 is configured to invoke a target recommendation algorithm model corresponding to the target model identifier according to the model interface address in the algorithm feature information to process the target feature data, obtain a product recommendation result, and then perform grouping and sorting on the product recommendation result according to the target information in the product recommendation request information to obtain a grouping and sorting result.
The product to be calculated determining unit 800 is configured to determine a target product to be calculated according to the grouping ordering result.
The trial calculation data obtaining unit 900 is configured to perform a trial calculation on the target product, and obtain trial calculation data corresponding to the target product.
Optionally, another product recommendation device provided by the embodiment of the present invention may further include: the product combination scheme results in a unit.
The product combination scheme obtaining unit is configured to determine whether a product combination function is turned on according to product combination information in the tenant feature information, if so, combine each target product according to a preset product combination mode to obtain a product combination scheme, and display the product combination scheme at the user side.
Optionally, another product recommendation device provided by the embodiment of the present invention may further include: and a new product sorting result obtaining unit.
The new product sorting result obtaining unit is configured to determine whether a new product recommending function is started according to new product recommending information in the tenant feature information, and if so, sort each target product according to a preset new product sorting mode to obtain a new product sorting result, and display the new product sorting result at the user side.
The product recommendation device includes a processor and a memory, the request information obtaining unit 100, the tenant characteristic information obtaining unit 200, the object model identification determining unit 300, the algorithm characteristic information obtaining unit 400, the object characteristic data obtaining unit 500, the product recommendation result obtaining unit 600, and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.
The processor includes a kernel, and the kernel fetches the corresponding program unit from the memory. The kernel can be provided with one or more than one, and the target recommendation algorithm model meeting the requirements of scenes and recommendation positions corresponding to the product recommendation request information is determined by adjusting kernel parameters through a configuration table matched with the product recommendation request information, so that the product recommendation result output after the target feature data are processed through the target recommendation algorithm model is more accurate, and the quality of product recommendation service is improved.
The embodiment of the application provides a storage medium, on which a program is stored, which when executed by a processor, implements the product recommendation method.
The embodiment of the application provides a processor which is used for running a program, wherein the program executes the product recommendation method when running.
The embodiment of the application provides electronic equipment, which comprises at least one processor, and at least one memory and a bus which are connected with the processor; the processor and the memory complete communication with each other through a bus; the processor is used for calling the program instructions in the memory to execute the product recommendation method. The electronic device herein may be a server, a PC, a PAD, a mobile phone, etc.
The present application also provides a computer program product adapted to perform a program initialized with the above-mentioned product recommendation method steps when executed on an electronic device.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus, electronic devices (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, the electronic device includes one or more processors (CPUs), memory, and a bus. The electronic device may also include input/output interfaces, network interfaces, and the like.
The memory may include volatile memory, random Access Memory (RAM), and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), among other forms in computer readable media, the memory including at least one memory chip. Memory is an example of a computer-readable medium.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.
Claims (10)
1. A method of product recommendation, comprising:
obtaining product recommendation request information sent by a user side, wherein the product recommendation request information carries a recommendation bit identifier;
inquiring the recommended position identification in a preset tenant configuration table to obtain tenant characteristic information corresponding to the recommended position identification;
determining a target model identification through the tenant characteristic information or task configuration information corresponding to the recommended bit identification in a preset task configuration table;
inquiring the target model identification in a preset model configuration table to obtain algorithm characteristic information corresponding to the target model identification;
obtaining target feature data according to the recommendation bit service data in the product recommendation request information, the product service line identification in the tenant feature information and the algorithm feature table name in the algorithm feature information;
and according to the model interface address in the algorithm characteristic information, calling a target recommendation algorithm model corresponding to the target model identifier to process the target characteristic data, and obtaining a product recommendation result.
2. The method of claim 1, wherein the determining the target model identifier by the tenant feature information or task configuration information corresponding to the recommended bit identifier in a preset task configuration table includes:
Under the condition that the recommended bit identifier is inquired in a preset task configuration table, determining task configuration information corresponding to the recommended bit identifier in the preset task configuration table; determining a target model identification through a model shunting mode in the task configuration information;
and under the condition that the recommendation bit identification is not queried in the preset task configuration table, determining an algorithm model identification in the tenant characteristic information as the target model identification.
3. The method of claim 1, wherein the obtaining the target feature data according to the recommendation bit service data in the product recommendation request information, the product service line identifier in the tenant feature information, and the algorithm feature table name in the algorithm feature information comprises:
inquiring and obtaining original characteristic data in a preset database table according to the recommendation bit service data in the product recommendation request information, the product service line identification in the tenant characteristic information and the algorithm characteristic table name in the algorithm characteristic information;
and converting the original characteristic data into target characteristic data by using a preset characteristic project corresponding to the target recommendation algorithm model.
4. The method according to claim 1, wherein after the target feature data is processed by calling a target recommendation algorithm model corresponding to the target model identifier according to the model interface address in the algorithm feature information, the method further comprises:
according to the target information in the product recommendation request information, grouping and sorting the product recommendation results to obtain grouping and sorting results;
determining a target product to be calculated in a trial mode according to the grouping sequencing result;
and performing trial calculation on the target product to obtain trial calculation data corresponding to the target product.
5. The method of claim 4, wherein prior to said calculating said target product to obtain calculation data corresponding to said target product, said method further comprises:
and determining whether a product combination function is started or not according to the product combination information in the tenant characteristic information, if so, combining each target product according to a preset product combination mode to obtain a product combination scheme, and displaying the product combination scheme at the user side.
6. The method of claim 4, wherein prior to said calculating said target product to obtain calculation data corresponding to said target product, said method further comprises:
and determining whether a new product recommending function is started according to the new product recommending information in the tenant characteristic information, if so, carrying out new product sequencing on each target product according to a preset new product sequencing mode to obtain a new product sequencing result, and displaying the new product sequencing result at the user side.
7. A product recommendation device, comprising: a request information obtaining unit, a tenant characteristic information obtaining unit, a target model identification determining unit, an algorithm characteristic information obtaining unit, a target characteristic data obtaining unit and a product recommendation result obtaining unit,
the request information obtaining unit is used for obtaining product recommendation request information sent by a user side, wherein the product recommendation request information carries a recommendation bit identifier;
the tenant characteristic information obtaining unit is used for inquiring the recommended bit identifier in a preset tenant configuration table to obtain tenant characteristic information corresponding to the recommended bit identifier;
The target model identification determining unit is used for determining a target model identification through the tenant characteristic information or task configuration information corresponding to the recommended bit identification in a preset task configuration table;
the algorithm characteristic information obtaining unit is used for inquiring the target model identifier in a preset model configuration table to obtain algorithm characteristic information corresponding to the target model identifier;
the target feature data obtaining unit is used for obtaining target feature data according to the recommendation bit service data in the product recommendation request information, the product service line identification in the tenant feature information and the algorithm feature table name in the algorithm feature information;
and the product recommendation result obtaining unit is used for calling a target recommendation algorithm model corresponding to the target model identifier to process the target feature data according to the model interface address in the algorithm feature information, so as to obtain a product recommendation result.
8. The apparatus according to claim 7, wherein the object model identification determination unit includes: a task configuration information determination subunit, a first object model identification determination subunit, and a second object model identification determination subunit,
The task configuration information determining subunit is configured to determine task configuration information corresponding to the recommended bit identifier in a preset task configuration table when the recommended bit identifier is queried in the preset task configuration table;
the first target model identification determining subunit is configured to determine a target model identification according to a model splitting mode in the task configuration information;
the second target model identifier determining subunit is configured to determine, when the recommendation bit identifier is not queried in the preset task configuration table, an algorithm model identifier in the tenant feature information as the target model identifier.
9. The apparatus according to claim 7, wherein the target feature data obtaining unit includes: the raw feature data acquisition subunit and the feature data conversion subunit,
the original characteristic data obtaining subunit is configured to query and obtain original characteristic data in a preset database table according to the recommendation bit service data in the product recommendation request information, the product service line identifier in the tenant characteristic information, and the algorithm characteristic table name in the algorithm characteristic information;
The feature data conversion subunit is configured to convert the original feature data into target feature data by using a preset feature project corresponding to the target recommendation algorithm model.
10. The apparatus as recited in claim 7, further comprising: a grouping sorting result obtaining unit, a product to be calculated determining unit and a calculation data obtaining unit,
the grouping and sorting result obtaining unit is used for calling a target recommendation algorithm model corresponding to the target model identifier according to the model interface address in the algorithm feature information to process the target feature data, and after obtaining a product recommendation result, sorting the product recommendation result in a grouping manner according to the target information in the product recommendation request information to obtain a grouping and sorting result;
the product to be calculated determining unit is used for determining a target product to be calculated according to the grouping sequencing result;
and the trial calculation data obtaining unit is used for carrying out trial calculation on the target product to obtain trial calculation data corresponding to the target product.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110205485.8A CN112767096B (en) | 2021-02-24 | 2021-02-24 | Product recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110205485.8A CN112767096B (en) | 2021-02-24 | 2021-02-24 | Product recommendation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112767096A CN112767096A (en) | 2021-05-07 |
| CN112767096B true CN112767096B (en) | 2023-09-19 |
Family
ID=75704049
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110205485.8A Active CN112767096B (en) | 2021-02-24 | 2021-02-24 | Product recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112767096B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109522480A (en) * | 2018-11-12 | 2019-03-26 | 北京羽扇智信息科技有限公司 | A kind of information recommendation method, device, electronic equipment and storage medium |
| CN110717099A (en) * | 2019-09-25 | 2020-01-21 | 优地网络有限公司 | Method and terminal for recommending film |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6459968B2 (en) * | 2013-09-20 | 2019-01-30 | 日本電気株式会社 | Product recommendation device, product recommendation method, and program |
| WO2015162458A1 (en) * | 2014-04-24 | 2015-10-29 | Singapore Telecommunications Limited | Knowledge model for personalization and location services |
| US20170169341A1 (en) * | 2015-12-14 | 2017-06-15 | Le Holdings (Beijing) Co., Ltd. | Method for intelligent recommendation |
| US20200401978A1 (en) * | 2019-06-20 | 2020-12-24 | Salesforce.Com, Inc. | Intelligent recommendation of goals using ingested database data |
-
2021
- 2021-02-24 CN CN202110205485.8A patent/CN112767096B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109522480A (en) * | 2018-11-12 | 2019-03-26 | 北京羽扇智信息科技有限公司 | A kind of information recommendation method, device, electronic equipment and storage medium |
| CN110717099A (en) * | 2019-09-25 | 2020-01-21 | 优地网络有限公司 | Method and terminal for recommending film |
Non-Patent Citations (2)
| Title |
|---|
| Octreotide acetate is efficacious and safe in children for treating diarrhea due to chemotherapy but not acute graft versus host disease;Vinita Pai等;Pediatric Blood & Cancer;第56卷(第1期);45 - 49 * |
| 移动云环境下服务推荐模型及关键技术研究;周作建等;中国博士学位论文全文数据库信息科技辑(第2期);I138-231 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112767096A (en) | 2021-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210326729A1 (en) | Recommendation Model Training Method and Related Apparatus | |
| CN109902224A (en) | Source of houses recommended method, device, equipment and medium based on user behavior analysis | |
| CN112380213B (en) | Information acquisition method and device, computer equipment and storage medium | |
| CN106844372B (en) | Logistics information query method and device | |
| CN110008397B (en) | Recommendation model training method and device | |
| US11244153B2 (en) | Method and apparatus for processing information | |
| CN107291744A (en) | It is determined that and with the method and device of the relationship between application program | |
| CN111522735B (en) | Shunting method and device for test experiment | |
| CN110069573A (en) | Product data integration method, apparatus, computer equipment and storage medium | |
| CN108809896A (en) | A kind of information calibration method, device and electronic equipment | |
| CN112767096B (en) | Product recommendation method and device | |
| CN116776030A (en) | Gray release method, device, computer equipment and storage medium | |
| CN116680480A (en) | Product recommendation method and device, electronic equipment and readable storage medium | |
| CN111026963A (en) | Data query method and device, and configuration information setting method and device | |
| CN112491943A (en) | Data request method, device, storage medium and electronic equipment | |
| CN108345600B (en) | Management of search application, data search method and device thereof | |
| CN106161570A (en) | Document down loading method based on page script, device, server group and system | |
| US11244019B2 (en) | Enrichment of user specific information | |
| CN113836428A (en) | Business pushing method and device, computer equipment and storage medium | |
| CN112835573A (en) | Data query method and device, electronic equipment and storage medium | |
| CN112560938A (en) | Model training method and device and computer equipment | |
| CN109165049A (en) | Module data processing method and processing device | |
| CN113515713B (en) | Webpage caching strategy generation method and device and webpage caching method and device | |
| CN112308167A (en) | Data generation method and device, storage medium and electronic equipment | |
| CN117609603A (en) | Information recommendation method and device, storage medium and electronic equipment |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231212 Address after: B3, No.1 Jinyun East Third Lane, Chengdu High tech Zone, Chengdu City, Sichuan Province, 610000 Patentee after: Huize (Chengdu) Network Technology Co.,Ltd. Address before: 1201-1207, Jingxing Haihai building, 91 guiwan Third Road, Nanshan street, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong 518000 Patentee before: SHENZHEN HUIZE TIMES TECHNOLOGY CO.,LTD. |
|
| TR01 | Transfer of patent right |