Service recommendation method, device, equipment and storage medium based on associated information

By extracting the semantics of user demand matching with service tags, and combining the service records of users and associated users, and calculating service weights, the problem of low accuracy of service recommendation on medical platforms is solved, and more efficient service recommendations are achieved.

CN113707302BActive Publication Date: 2024-12-03KANG JIAN INFORMATION TECH (SHENZHEN) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111004871.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-08-30
Publication Date
2024-12-03
Estimated Expiration
2041-08-30

AI Technical Summary

Technical Problem

When providing consulting services, existing medical platforms are difficult to provide precise service recommendations based on users' specific needs, making it difficult for users to find their needs among many services.

Method used

By obtaining the user's service demand data, extracting the demand semantics and matching them with the preset service tags, combining the service records of the user and associated users, calculating the service weight, and recommending services with greater importance than the threshold.

Benefits of technology

It improves the accuracy of service recommendations, enables users to find the services they need more quickly, and reduces the search time and energy on the platform.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113707302B_ABST
    Figure CN113707302B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of artificial intelligence and digital medical technology, and discloses a service recommendation method based on associated information, including: extracting service objects and demand semantics from user's service demand data, determining the target service required by the service object according to the demand semantics, obtaining the service records of the service object and the associated user, counting and calculating the weight of each different preset service according to the business records, and then calculating the importance of each preset service according to the weight, and pushing the services with importance greater than a preset threshold and the target service to the user. In addition, the present invention also relates to blockchain technology, and service demand data can be stored in the nodes of the blockchain. The present invention also proposes a service recommendation device, electronic device and storage medium based on associated information. The present invention can improve the accuracy of service recommendations.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a service recommendation method, device, electronic device and computer-readable storage medium based on association information. Background Art

[0002] In recent years, with the rapid development of social economy and the leap-forward improvement in living standards, people's attention to daily health and the demand for diverse online medical services have also increased day by day. More and more people are using online methods to analyze their health conditions, for example, consulting on health conditions on medical platforms that provide medical consultation, diagnosis and other functions.

[0003] When providing consulting services, existing medical platforms will indiscriminately provide users with a wide variety of services and complicated service entrances, which requires users to spend a lot of time and energy to distinguish the services they need when using the medical platform. Therefore, how to achieve accurate service recommendations based on user data has become an urgent problem to be solved. Summary of the invention

[0004] The present invention provides a service recommendation method and device based on association information and a computer-readable storage medium, the main purpose of which is to solve the problem of low accuracy when performing service recommendation.

[0005] To achieve the above object, the present invention provides a service recommendation method based on association information, comprising:

[0006] Acquire the user's service demand data, and extract the service object and demand semantics from the service demand data;

[0007] Calculating the matching values ​​between the demand semantics and the service label of each of the multiple preset services, and selecting the preset service corresponding to the service label with the largest matching value as the target service;

[0008] Obtaining a service record of the service object, counting the number of times each preset service in the service record of the service object as a first number, and calculating a first service weight of each of the preset services according to the first number;

[0009] Querying from a preset user table to obtain associated users who have an associated relationship with the service object;

[0010] Obtaining the service record of the associated user, counting the number of times each preset service in the service record of the associated user as a second number, and calculating a second service weight of each of the preset services according to the second number;

[0011] The importance of each of the preset services is calculated according to the first service weight and the second service weight, and the target service and the services whose importance is greater than a preset threshold are recommended to the user.

[0012] Optionally, extracting demand semantics from the service demand data includes:

[0013] Performing word segmentation processing on the standard requirements to obtain demand word segmentation;

[0014] Counting the segmentation frequency of each segmentation in the demand segmentation, selecting the demand segmentation whose segmentation frequency is greater than a preset frequency threshold as a keyword, and converting each demand segmentation in the keyword into a word vector;

[0015] The word vectors are concatenated into a vector matrix, and the vector matrix is ​​determined to be the demand semantics of the service demand data.

[0016] Optionally, concatenating the word vectors into a vector matrix includes:

[0017] Counting the vector length of each word vector in the word vector, and determining the maximum value of the vector lengths as the target length;

[0018] Using preset parameters to extend the vector length of each vector in the word vector to the target length;

[0019] Each vector in the extended word vector is concatenated as a row vector to obtain a vector matrix.

[0020] Optionally, calculating the matching value between the demand semantics and the service label of each of the plurality of preset services includes:

[0021]

[0022] Where P is the matching value, a is the requirement semantics, and b u is the service label of the uth service among the multiple preset services.

[0023] Optionally, the counting of the number of times each preset service in the service record of the service object is the first number includes:

[0024] Get the data format of the service name of each preset service;

[0025] Compiling the preset characters into a regular expression corresponding to the service name of each preset service according to the data format;

[0026] The service name of each preset service in the service record is extracted by using the regular expression, the number of times of each preset service is counted according to the service name, and the number is used as the first number of each preset service.

[0027] Optionally, querying from a preset user table to obtain an associated user having an associated relationship with the service object includes:

[0028] Build the index of the preset user table;

[0029] The demand semantics are used to search in the index to obtain users corresponding to the demand semantics, and the retrieved users are aggregated as associated users of the service object.

[0030] Optionally, the recommending the target service and the preset service whose importance is greater than a preset threshold to the user includes:

[0031] Sort the preset services whose importance is greater than a preset threshold in order from large to small to obtain a service list;

[0032] The target service is written into the first position of the service list, and services are recommended to the user according to the order of the service list.

[0033] In order to solve the above problem, the present invention further provides a service recommendation device based on association information, the device comprising:

[0034] A data extraction module is used to obtain the user's service demand data and extract the service object and demand semantics from the service demand data;

[0035] A matching value calculation module, used to calculate the matching values ​​between the demand semantics and the service label of each of the multiple preset services, and select the preset service corresponding to the service label with the largest matching value as the target service;

[0036] A first weight analysis module is used to obtain the service record of the service object, count the number of times of each preset service in the service record of the service object as a first number, and calculate a first service weight of each preset service according to the first number;

[0037] An associated user query module is used to query and obtain associated users having an associated relationship with the service object from a preset user table;

[0038] A second weight analysis module is used to obtain the service record of the associated user, count the number of times each preset service in the service record of the associated user as a second number, and calculate a second service weight of each of the preset services according to the second number;

[0039] A service recommendation module is used to calculate the importance of each of the preset services according to the first service weight and the second service weight, and recommend the target service and the services whose importance is greater than a preset threshold to the user.

[0040] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising:

[0041] at least one processor; and,

[0042] a memory communicatively connected to the at least one processor; wherein,

[0043] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the above-mentioned service recommendation method based on association information.

[0044] In order to solve the above problem, the present invention also provides a computer-readable storage medium, in which at least one computer program is stored. The at least one computer program is executed by a processor in an electronic device to implement the above-mentioned service recommendation method based on associated information.

[0045] The embodiment of the present invention can analyze the user's service record and the service record of the associated user with the user after analyzing the semantics of the user's needs, so as to determine the services that the user may need, and then recommend services to the user in combination with the semantic analysis and the analysis of the service record, thereby improving the accuracy of the service recommendation. Therefore, the service recommendation method, device, electronic device and computer-readable storage medium based on the associated information proposed by the present invention can solve the problem of low accuracy when making service recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A schematic diagram of a process flow of a service recommendation method based on association information provided by an embodiment of the present invention;

[0047] Figure 2 A schematic diagram of a process for extracting demand semantics provided by an embodiment of the present invention;

[0048] Figure 3 A schematic diagram of a process for counting the first number of numbers provided by an embodiment of the present invention;

[0049] Figure 4 A functional module diagram of a service recommendation device based on association information provided by an embodiment of the present invention;

[0050] Figure 5A schematic diagram of the structure of an electronic device for implementing the service recommendation method based on association information provided by an embodiment of the present invention.

[0051] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0052] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0053] The embodiment of the present application provides a service recommendation method based on associated information. The execution subject of the service recommendation method based on associated information includes but is not limited to at least one of the electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided by the embodiment of the present application. In other words, the service recommendation method based on associated information can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms.

[0054] Reference Figure 1 FIG. 1 is a flow chart of a method for recommending services based on association information according to an embodiment of the present invention. In this embodiment, the method for recommending services based on association information includes:

[0055] S1. Obtain user service demand data, and extract service objects and demand semantics from the service demand data.

[0056] In an embodiment of the present invention, the service demand data includes demand data for each of a plurality of preset services purchased and reserved by the user for a designated service object. For example, the user needs to obtain a service for purchasing medicines or a service for diagnosing health conditions in a medical platform.

[0057] In detail, the service object is the object that needs to be served by the preset service corresponding to the service demand data. For example, when a user consults about drug purchase services for himself on the medical platform, the service object is the user himself; or, when a user consults about drug purchase services for his son on the medical platform, the service object is the user's son.

[0058] The service objects and service demand data uploaded by users through the web page, user terminal and other interfaces of the preset medical platform can be obtained through a pre-installed message acquisition plug-in, and the message acquisition plug-in includes but is not limited to a kafka plug-in and a redis plug-in.

[0059] In an embodiment of the present invention, since the user's service demand data may contain a large amount of data, if the service demand data is directly processed, a large amount of computing resources will be occupied. Therefore, an embodiment of the present invention can analyze the service demand data to extract the demand semantics from the service demand data. In detail, the demand semantics is the sentence meaning that the service demand data wants to express.

[0060] In one embodiment of the present invention, Figure 2 As shown, extracting demand semantics from the service demand data includes:

[0061] S21, performing word segmentation processing on the standard demand to obtain demand word segmentation;

[0062] S22, counting the segmentation frequency of each segmentation in the demand segmentation, selecting the demand segmentation whose segmentation frequency is greater than a preset frequency threshold as a keyword, and converting each demand segmentation in the keyword into a word vector;

[0063] S23, concatenating the word vectors into a vector matrix, and determining that the vector matrix is ​​the demand semantics of the service demand data.

[0064] In detail, a pre-trained artificial intelligence model with a word segmentation function can be used to perform word segmentation on the standard requirements to obtain the requirement segmentation, wherein the artificial intelligence model includes but is not limited to an NLP (Natural Language Processing) model and an HMM (Hidden Markov Model).

[0065] Specifically, the word segmentation frequency refers to the number of times a certain word segmentation appears in the demand word segmentation of the standard demand. The higher the word segmentation frequency of a word segmentation, the greater the importance of the word segmentation. Therefore, the demand word segmentation whose word segmentation frequency is greater than the preset frequency threshold can be selected as a keyword.

[0066] Furthermore, in order to improve the processing efficiency of the keywords, a pre-trained word vector model may be used to convert the keywords into word vectors in numerical form, wherein the word vector model includes but is not limited to a word2vec model and a bert model.

[0067] In the embodiment of the present invention, the step of concatenating the word vectors into a vector matrix includes:

[0068] Counting the vector length of each word vector in the word vector, and determining the maximum value of the vector lengths as the target length;

[0069] Using preset parameters to extend the vector length of each vector in the word vector to the target length;

[0070] Each vector in the extended word vector is concatenated as a row vector to obtain a vector matrix.

[0071] In detail, since the word vectors are converted from different keywords, the vector lengths of different vectors in the word vectors may be different. In order to facilitate subsequent splicing, the lengths of all word vectors can be extended to a uniform length using preset parameters.

[0072] For example, the word vector includes vector A: (1, 4, 6), vector B: (2, 3), and vector C: (3, 7, 8, 9). According to statistics, the vector length of vector A is 3, the vector length of vector B is 2, and the vector length of vector C is 4. Then 4 is determined as the target length, and the vector length of vector A is extended to 4 using preset parameters (such as x), and the extended vector A is obtained: (1, 4, 6, x), and the vector length of vector B is extended to 4, and the extended vector B is obtained: (2, 3, x, x).

[0073] Furthermore, each extended word vector can be used as a row vector and concatenated into the following vector matrix:

[0074]

[0075] In the embodiment of the present invention, since the vector matrix is ​​formed by concatenating vectors corresponding to keywords of the service demand data, the vector matrix can be used as the demand semantics of the service demand data.

[0076] S2. Calculate the matching values ​​between the demand semantics and the service label of each of the multiple preset services, and select the preset service corresponding to the service label with the largest matching value as the target service.

[0077] In an embodiment of the present invention, the plurality of preset services include any services available to the user, for example, a drug purchasing service available to the user on a medical platform, a health status diagnosis service available to the user, and the like.

[0078] In detail, the service tag is a pre-generated tag used to mark the content of different preset services, for example, a tag used to mark the preset service generated according to the content, keywords, price and other data of the preset service.

[0079] In the embodiment of the present invention, the service corresponding to the service demand data may be determined by calculating the matching value between the demand semantics and the service label of each of the multiple preset services.

[0080] In detail, when the matching value between the demand semantics and the preset tag is greater, it means that the service demand data corresponding to the demand semantics is more likely to want to obtain the preset service corresponding to the preset tag.

[0081] In the embodiment of the present invention, the calculating of the matching value between the demand semantics and the service label of each of the plurality of preset services includes:

[0082]

[0083] Where P is the matching value, a is the requirement semantics, and b u is the service label of the ith service among the plurality of preset services.

[0084] In the embodiment of the present invention, according to the matching value between the demand semantics and each service tag, the preset service corresponding to the service tag with the largest matching value may be selected as the target service.

[0085] In the embodiment of the present invention, a target service is screened out from a plurality of preset services through the service semantics of the service demand data, so that service recommendations based on user needs can be achieved.

[0086] S3. Obtain the service record of the service object, count the number of times each preset service in the service record of the service object as a first number, and calculate a first service weight of each of the preset services according to the first number.

[0087] In the embodiment of the present invention, the service record includes records such as the service name and acquisition time of each preset service that the service object has acquired.

[0088] In detail, computer statements with data capture functions (such as java statements, python statements, etc.) can be used to capture user-authorized service records from a pre-built storage area, and the storage area includes but is not limited to a database, a blockchain, and a network cache.

[0089] In one of the actual application scenarios of the present invention, due to the large differences in expression habits of different users, the target service determined by using demand semantics may not be the service that the user actually needs. Therefore, in order to determine user needs more accurately, the service records of the service object can be analyzed to count the number of times each preset service in the service record of the service object is used as the first number.

[0090] In the embodiment of the present invention, since the name of each preset service is inconsistent and has a fixed form, a regular expression can be constructed to extract the service name of each preset service in the service record, and the extracted results are counted to determine the number of each preset service in the service record.

[0091] In the embodiment of the present invention, Figure 3 As shown, the counting of the number of times each preset service in the service record of the service object is the first number, including:

[0092] S31, obtaining the data format of the service name of each preset service;

[0093] S32, compiling the preset characters into a regular expression corresponding to the service name of each preset service according to the data format;

[0094] S33: extract the service name of each preset service in the service record by using the regular expression, count the number of times of each preset service according to the service name, and use the number as the first number of times of each preset service.

[0095] In detail, the data format refers to the format of the service name of each preset service, and the regular expression can realize the extraction of fields, characters, etc. in a fixed format in the data.

[0096] Specifically, a preset compiler may be used to compile the preset characters into a regular expression corresponding to the service name of each preset service, which is beneficial to the efficiency of extracting the service name of each preset service from the service record.

[0097] In the embodiment of the present invention, the service times of each preset service are determined by counting the extracted service names.

[0098] For example, the extracted service names include 10 names of service A, 20 names of service B, and 15 names of service C. Therefore, it can be determined that the number of times service A appears in the service record is 10, the number of times service B appears is 20, and the number of times service C appears is 15.

[0099] In the embodiment of the present invention, in order to determine the importance of each preset service to the user, a first service weight of each preset service may be calculated according to the first number of times.

[0100] In detail, the calculating the first service weight of each of the preset services according to the first number of times includes:

[0101] The first service weight of each of the preset services is calculated according to the first number of times using the following weight algorithm:

[0102]

[0103] Among them, W k is the first service weight of the kth preset service, ω k is the first number of the kth preset service, and C is the sum of the first numbers of all preset services.

[0104] In the embodiment of the present invention, calculating the first service weight of each preset service according to the first number is conducive to subsequently selecting services according to the service weights for recommendation to users, thereby improving the accuracy of service recommendations to users.

[0105] S4. Query and obtain associated users who have an associated relationship with the service object from a preset user table.

[0106] In the embodiment of the present invention, the user table is a pre-built table for storing information of multiple users.

[0107] In detail, the associated users include any users related to the service object, for example, family members of the service object, users who have obtained the same preset service as the service object, etc.

[0108] In the embodiment of the present invention, an index may be constructed in the user table, and associated users having an associated relationship with the service object may be queried from the user table according to the index.

[0109] In the embodiment of the present invention, the querying from the preset user table to obtain the associated user having an associated relationship with the service object includes:

[0110] Build the index of the preset user table;

[0111] The demand semantics are used to search in the index to obtain users corresponding to the demand semantics, and the retrieved users are aggregated as associated users of the service object.

[0112] In detail, the index of the user table may be constructed using the CREATE TABLE function in SQL.

[0113] For example, the following index is constructed using the CREATE TABLE function:

[0114] CREATE INDEX index name

[0115] ON table name(column name)

[0116] Among them, index name is the index name, table name is the table name of the user table, and column name is the column name of the data column in the user table that needs to create an index.

[0117] In the embodiment of the present invention, the demand semantics may be used to search in the index to retrieve users related to the demand semantics from the user table, and the retrieved users are used as associated users of the service object.

[0118] S5. Obtain the service record of the associated user, count the number of times each preset service in the service record of the associated user as a second number, and calculate a second service weight of each of the preset services according to the second number.

[0119] In the embodiment of the present invention, the service record of the associated user includes the record of the associated user's acquisition time, acquisition location, etc. for each preset service in history.

[0120] In detail, the steps of obtaining the service record of the associated user, counting the number of times each preset service in the service record of the associated user as the second number, and calculating the second service weight of each of the preset services based on the second number, are consistent with the steps of obtaining the service record of the service object, counting the number of times each preset service in the service record of the service object as the first number, and calculating the first service weight of each of the preset services based on the first number in S3, and will not be repeated here.

[0121] S6. Calculate the importance of each of the preset services according to the first service weight and the second service weight, and recommend the target service and the services whose importance is greater than a preset threshold to the user.

[0122] In the embodiment of the present invention, the calculating the importance of each of the preset services according to the first service weight and the second service weight includes:

[0123] The importance of each of the preset services is calculated according to the first service weight and the second service weight using the following importance algorithm:

[0124] P n =θ1*A n +θ2*B n

[0125] Among them, P n The importance of the nth preset service, A n is the first number of the nth preset service in the service record of the service object, B nis the second number of the nth preset service in the service record of the associated user, and θ1 and θ2 are preset coefficients.

[0126] Further, the recommending the target service and the preset service whose importance is greater than a preset threshold to the user includes:

[0127] Sort the preset services whose importance is greater than a preset threshold in order from large to small to obtain a service list;

[0128] The target service is written into the first position of the service list, and services are recommended to the user according to the order of the service list.

[0129] In detail, since the target service is a preset service corresponding to the semantics of the user's demand, the preset service can be placed first in the service list, and the preset services whose importance is greater than a preset threshold can be sorted in descending order, and then service recommendations can be made to the user in the order of each preset service in the service list.

[0130] The embodiment of the present invention can analyze the user's service record and the service record of the associated user with the user after analyzing the semantics of the user's needs, so as to determine the services that the user may need, and then recommend services to the user in combination with the semantic analysis and the analysis of the service record, thereby improving the accuracy of the service recommendation. Therefore, the service recommendation method based on associated information proposed by the present invention can solve the problem of low accuracy when making service recommendations.

[0131] like Figure 4 FIG. 1 is a functional module diagram of a service recommendation device based on association information provided by an embodiment of the present invention.

[0132] The service recommendation device 100 based on association information of the present invention can be installed in an electronic device. According to the functions implemented, the service recommendation device 100 based on association information can include a data extraction module 101, a matching value calculation module 102, a first weight analysis module 103, an associated user query module 104, a second weight analysis module 105 and a service recommendation module 106. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0133] In this embodiment, the functions of each module / unit are as follows:

[0134] The data extraction module 101 is used to obtain the user's service demand data and extract the service object and demand semantics from the service demand data;

[0135] The matching value calculation module 102 is used to calculate the matching value between the demand semantics and the service label of each preset service in the plurality of preset services, and select the preset service corresponding to the service label with the largest matching value as the target service;

[0136] The first weight analysis module 103 is used to obtain the service record of the service object, count the number of times of each preset service in the service record of the service object as a first number, and calculate the first service weight of each preset service according to the first number;

[0137] The associated user query module 104 is used to query and obtain associated users having an associated relationship with the service object from a preset user table;

[0138] The second weight analysis module 105 is used to obtain the service record of the associated user, count the number of times each preset service in the service record of the associated user as a second number, and calculate the second service weight of each preset service according to the second number;

[0139] The service recommendation module 106 is used to calculate the importance of each of the preset services according to the first service weight and the second service weight, and recommend the target service and the services whose importance is greater than a preset threshold to the user.

[0140] In detail, each module in the service recommendation device 100 based on association information in the embodiment of the present invention is used in the same manner as described above. Figures 1 to 3 The same technical means as the service recommendation method based on associated information described in the specification and can produce the same technical effects are used, and will not be repeated here.

[0141] like Figure 5 FIG. 1 is a schematic diagram of the structure of an electronic device for implementing a service recommendation method based on association information provided by an embodiment of the present invention.

[0142] The electronic device 1 may include a processor 10, a memory 11, a communication bus 12, and a communication interface 13, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a service recommendation program based on association information.

[0143] In some embodiments, the processor 10 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The processor 10 is the control core (ControlUnit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules stored in the memory 11 (for example, executing a service recommendation program based on associated information, etc.), and calls data stored in the memory 11 to execute various functions of the electronic device and process data.

[0144] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory 11 may be an internal storage unit of an electronic device, such as a mobile hard disk of the electronic device. In other embodiments, the memory 11 may also be an external storage device of an electronic device, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Further, the memory 11 may also include both an internal storage unit of the electronic device and an external storage device. The memory 11 can be used not only to store application software and various types of data installed in the electronic device, such as the code of a service recommendation program based on associated information, but also to temporarily store data that has been output or is to be output.

[0145] The communication bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0146] The communication interface 13 is used for communication between the above-mentioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface may also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visual user interface.

[0147] Figure 5 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 5 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0148] For example, although not shown, the electronic device may also include a power source (such as a battery) for supplying power to each component. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0149] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0150] The service recommendation program based on the association information stored in the memory 11 of the electronic device 1 is a combination of multiple instructions, and when executed in the processor 10, it can achieve:

[0151] Acquire the user's service demand data, and extract the service object and demand semantics from the service demand data;

[0152] Calculating the matching values ​​between the demand semantics and the service label of each of the multiple preset services, and selecting the preset service corresponding to the service label with the largest matching value as the target service;

[0153] Obtaining a service record of the service object, counting the number of times each preset service in the service record of the service object as a first number, and calculating a first service weight of each of the preset services according to the first number;

[0154] Querying from a preset user table to obtain associated users who have an associated relationship with the service object;

[0155] Obtaining the service record of the associated user, counting the number of times each preset service in the service record of the associated user as a second number, and calculating a second service weight of each of the preset services according to the second number;

[0156] The importance of each of the preset services is calculated according to the first service weight and the second service weight, and the target service and the services whose importance is greater than a preset threshold are recommended to the user.

[0157] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, which will not be repeated here.

[0158] Furthermore, if the module / unit integrated in the electronic device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0159] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement:

[0160] Acquire the user's service demand data, and extract the service object and demand semantics from the service demand data;

[0161] Calculating the matching values ​​between the demand semantics and the service label of each of the multiple preset services, and selecting the preset service corresponding to the service label with the largest matching value as the target service;

[0162] Obtaining a service record of the service object, counting the number of times each preset service in the service record of the service object as a first number, and calculating a first service weight of each of the preset services according to the first number;

[0163] Querying from a preset user table to obtain associated users who have an associated relationship with the service object;

[0164] Obtaining the service record of the associated user, counting the number of times each preset service in the service record of the associated user as a second number, and calculating a second service weight of each of the preset services according to the second number;

[0165] The importance of each of the preset services is calculated according to the first service weight and the second service weight, and the target service and the services whose importance is greater than a preset threshold are recommended to the user.

[0166] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0167] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0168] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0169] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0170] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0171] The blockchain referred to in this invention is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0172] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0173] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the system claim can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

[0174] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A service recommendation method based on association information, characterized in that: The method comprises: Acquire the user's service demand data, extract the service object from the service demand data, perform word segmentation processing on the service demand data to obtain demand word segmentations, count the word segmentation frequency of each word in the demand word segmentations, select the demand word segmentations whose word segmentation frequency is greater than a preset frequency threshold as keywords, convert each demand word in the keywords into a word vector, splice the word vectors into a vector matrix, and determine that the vector matrix is ​​the demand semantics of the service demand data; Calculating the matching values ​​between the demand semantics and the service label of each of the multiple preset services, and selecting the preset service corresponding to the service label with the largest matching value as the target service; Obtaining a service record of the service object, counting the number of times each preset service in the service record of the service object as a first number, and calculating a first service weight of each of the preset services according to the first number; Querying from a preset user table to obtain associated users who have an associated relationship with the service object, the associated users including all users related to the service object; Obtaining the service record of the associated user, counting the number of times each preset service in the service record of the associated user as a second number, and calculating a second service weight of each of the preset services according to the second number; The importance of each of the preset services is calculated according to the first service weight and the second service weight, and the target service and the preset services whose importance is greater than a preset threshold are recommended to the user.

2. The service recommendation method based on association information according to claim 1, characterized in that: The step of concatenating the word vectors into a vector matrix includes: Counting the vector length of each word vector in the word vector, and determining the maximum value of the vector lengths as the target length; Using preset parameters to extend the vector length of each vector in the word vector to the target length; Each vector in the extended word vector is concatenated as a row vector to obtain a vector matrix.

3. The service recommendation method based on association information according to claim 1, characterized in that: The calculating the matching value between the demand semantics and the service label of each of the plurality of preset services includes: Where P is the matching value, a is the requirement semantics, and b i is the service label of the i-th service among the multiple preset services.

4. The service recommendation method based on association information according to claim 1, characterized in that: The counting of the number of times of each preset service in the service record of the service object is the first number, including: Get the data format of the service name of each preset service; Compiling the preset characters into a regular expression corresponding to the service name of each preset service according to the data format; The service name of each preset service in the service record is extracted by using the regular expression, the number of times of each preset service is counted according to the service name, and the number is used as the first number of each preset service.

5. The service recommendation method based on association information according to claim 1, characterized in that: The querying from the preset user table to obtain the associated user having an associated relationship with the service object includes: Build the index of the preset user table; The demand semantics are used to search in the index to obtain users corresponding to the demand semantics, and the retrieved users are aggregated as associated users of the service object.

6. The service recommendation method based on associated information according to any one of claims 1 to 5, characterized in that: The recommending the target service and the preset service whose importance is greater than a preset threshold to the user includes: Sort the preset services whose importance is greater than a preset threshold in order from large to small to obtain a service list; The target service is written into the first position of the service list, and services are recommended to the user according to the order of the service list.

7. A service recommendation device based on associated information, characterized in that: The device comprises: A data extraction module is used to obtain the user's service demand data, extract the service object from the service demand data, perform word segmentation processing on the service demand data to obtain demand word segmentations, count the word segmentation frequency of each word in the demand word segmentations, select the demand word segmentations whose word segmentation frequency is greater than a preset frequency threshold as keywords, and convert each demand word in the keywords into a word vector, splice the word vectors into a vector matrix, and determine that the vector matrix is ​​the demand semantics of the service demand data; A matching value calculation module, used to calculate the matching values ​​between the demand semantics and the service label of each of the multiple preset services, and select the preset service corresponding to the service label with the largest matching value as the target service; A first weight analysis module is used to obtain the service record of the service object, count the number of times of each preset service in the service record of the service object as a first number, and calculate a first service weight of each preset service according to the first number; An associated user query module, used to query and obtain associated users having an associated relationship with the service object from a preset user table, wherein the associated users include all users related to the service object; A second weight analysis module is used to obtain the service record of the associated user, count the number of times each preset service in the service record of the associated user as a second number, and calculate a second service weight of each of the preset services according to the second number; The service recommendation module is used to calculate the importance of each of the preset services according to the first service weight and the second service weight, and recommend the target service and the preset services whose importance is greater than a preset threshold to the user.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the service recommendation method based on association information as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the service recommendation method based on associated information as claimed in any one of claims 1 to 6 is implemented.