Information recommendation method and device, computer equipment and storage medium

Abstract

The invention belongs to the technical field of artificial intelligence, and relates to an information recommendation method, which is applied to the field of financial science and technology, and comprises the following steps: if an information recommendation request is received, collecting position information of a user, and converting the position information into a target code; searching a first client list corresponding to the target code; obtaining customer feature data of the target processing customer and generating a corresponding customer feature vector; searching a similarity ordered list corresponding to the customer feature vector; screening the first client list and the similarity ordered list to generate a second client list; performing score sorting on the clients in the second client list to obtain a target client list; and performing display processing on the target client list. The invention further provides an information recommendation device, computer equipment and a storage medium. In addition, the invention also relates to a block chain technology, and the target client list can be stored in a block chain. According to the invention, intelligent peripheral customer recommendation service is realized, and the accuracy and intelligence of customer recommendation are improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence development technology and financial technology, and in particular to information recommendation methods, devices, computer equipment and storage media. Background Art

[0002] In the traditional sales model and operation system of the insurance industry, insurance agents are the key bridge between insurance companies and customers. Their work efficiency and service quality directly affect the sales effect of insurance products and customer satisfaction. For a long time, insurance agents have relied on the standardized business paths and customer relationship management systems (CRM) provided by the company to assist their daily sales activities. These systems usually integrate a large amount of customer data, including but not limited to basic customer information, policy information, and wealth information, aiming to help agents better understand customer needs and achieve precision marketing.

[0003] However, in actual operation, agents need to manually screen individual customers who meet the current sales strategy or have potential purchasing intentions from a huge customer database. This process is not only time-consuming and laborious, but also highly dependent on the agent's personal experience and intuition, making it difficult to ensure the comprehensiveness and accuracy of the screening results. In addition, due to the diversity of customer needs and the rapid changes in the market environment, static customer labels often cannot reflect the customer's latest status and real needs in real time, thus limiting the pertinence and effectiveness of sales activities.

[0004] More importantly, when agents are out visiting clients and face unexpected situations such as clients failing to keep appointments for some reason, most existing customer relationship management systems can only provide random customer recommendations based on geographic location, so that the recommended customers may not be the best choice, which in turn leads to low accuracy of customer recommendations. Summary of the invention

[0005] The purpose of the embodiments of the present application is to propose an information recommendation method, apparatus, computer device and storage medium to solve the technical problem that most existing customer relationship management systems can only provide random customer recommendations based on geographic location, so that the recommended customers may not be the best choice, which in turn leads to low accuracy of customer recommendations.

[0006] In order to solve the above technical problems, the present application embodiment provides an information recommendation method, which adopts the following technical solution:

[0007] Determine whether an information recommendation request triggered by a user in a preset interface is received;

[0008] If yes, collecting the location information of the user and converting the location information into a target code corresponding to a target code format;

[0009] Calling a preset code database to search for a first customer list corresponding to the target code and meeting the target distance range condition;

[0010] Acquire customer feature data of a target processing customer corresponding to the user, and generate a customer feature vector corresponding to the customer feature data based on a preset component interface;

[0011] Searching for a similarity ordered list corresponding to the customer feature vector based on a preset vector database;

[0012] Screening the first customer list and the similarity ordered list to generate a corresponding second customer list;

[0013] Sorting the customers in the second customer list by scores based on a preset sorting strategy to obtain a sorted target customer list;

[0014] The target customer list is displayed.

[0015] Furthermore, the step of searching for a similarity ordered list corresponding to the customer feature vector based on a preset vector database specifically includes:

[0016] Get the preset search parameters;

[0017] Based on the search parameters and the customer feature vector, a similarity search is performed on the full set of customer feature vectors stored in the vector database to obtain a corresponding index array and a similarity score array;

[0018] Convert the index array and the similarity score array to obtain a corresponding data list;

[0019] Sorting the data list based on the similarity scores included in the similarity score array to obtain a sorted data list;

[0020] The sorted data list is used as the similarity ordered list.

[0021] Furthermore, the step of screening the first customer list and the similarity ordered list to generate a corresponding second customer list specifically includes:

[0022] Get the preset customer ID;

[0023] Based on the customer identifier, performing intersection calculation on the first customer list and the similarity ordered list to obtain target customers that appear in both the first customer list and the similarity ordered list;

[0024] Get the initial list of presets;

[0025] Adding information of the target customer to the initial list to obtain a processed initial list;

[0026] The processed initial list is used as the second customer list.

[0027] Furthermore, the step of performing score sorting processing on the customers in the second customer list based on a preset sorting strategy to obtain a sorted target customer list specifically includes:

[0028] Obtaining first similarity scores of all first customers included in the second customer list;

[0029] Call the preset sort statement;

[0030] Based on the sorting statement, sort all the first customers included in the second customer list from high to low according to the first similarity score to obtain a sorted third customer list;

[0031] The third customer list is used as the target customer list.

[0032] Furthermore, the step of performing score sorting processing on the customers in the second customer list based on a preset sorting strategy to obtain a sorted target customer list specifically includes:

[0033] respectively obtaining distance information between the user and all second customers included in the second customer list;

[0034] Obtaining second similarity scores of all second customers included in the second customer list;

[0035] Scoring the distance information and the second similarity score based on a preset scoring strategy to obtain a customer score for each of the second customers;

[0036] Call the preset sorting algorithm;

[0037] Based on the sorting algorithm, sort all the second customers included in the second customer list from high to low according to the customer scores to obtain a sorted fourth customer list;

[0038] The fourth customer list is used as the target customer list.

[0039] Furthermore, the step of scoring the distance information and the second similarity score based on a preset scoring strategy to obtain a customer score of each second customer specifically includes:

[0040] Call the preset weight setting algorithm;

[0041] generating a first weight corresponding to the distance factor based on the weight setting algorithm, and generating a second weight corresponding to the similarity factor;

[0042] Obtaining designated distance information and designated similarity score of a designated customer; wherein the designated customer is any one of all the second customers;

[0043] Calculating the specified distance information, the specified similarity score, the first weight, and the second weight based on a preset score generation algorithm to obtain a corresponding calculation result;

[0044] The calculation result is used as the customer score of the designated customer.

[0045] Furthermore, the step of displaying the target customer list specifically includes:

[0046] Get the preset customer distribution map;

[0047] Determining recommended customers included in the target customer list;

[0048] Performing location highlighting processing on the recommended customers in the customer distribution map to obtain a corresponding target customer distribution map;

[0049] The target customer distribution map and the target customer list are displayed in the preset interface.

[0050] In order to solve the above technical problems, the embodiment of the present application further provides an information recommendation device, which adopts the following technical solution:

[0051] A determination module, used to determine whether an information recommendation request triggered by a user in a preset interface is received;

[0052] A conversion module, configured to collect the location information of the user and convert the location information into a target code corresponding to a target code format;

[0053] A first search module, used to call a preset code database to search for a first customer list corresponding to the target code and meeting the target distance range condition;

[0054] A generating module, used for acquiring customer characteristic data of a target processing customer corresponding to the user, and generating a customer characteristic vector corresponding to the customer characteristic data based on a preset component interface;

[0055] A second search module, used to search for a similarity ordered list corresponding to the customer feature vector based on a preset vector database;

[0056] A screening module, used for screening the first customer list and the similarity ordered list to generate a corresponding second customer list;

[0057] A sorting module, used to sort the customers in the second customer list by scores based on a preset sorting strategy to obtain a sorted target customer list;

[0058] A display module is used to display the target customer list.

[0059] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0060] Determine whether an information recommendation request triggered by a user in a preset interface is received;

[0061] If yes, collecting the location information of the user and converting the location information into a target code corresponding to a target code format;

[0062] Calling a preset code database to search for a first customer list corresponding to the target code and meeting the target distance range condition;

[0063] Acquire customer feature data of a target processing customer corresponding to the user, and generate a customer feature vector corresponding to the customer feature data based on a preset component interface;

[0064] Searching for a similarity ordered list corresponding to the customer feature vector based on a preset vector database;

[0065] Screening the first customer list and the similarity ordered list to generate a corresponding second customer list;

[0066] Sorting the customers in the second customer list by scores based on a preset sorting strategy to obtain a sorted target customer list;

[0067] The target customer list is displayed.

[0068] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0069] Determine whether an information recommendation request triggered by a user in a preset interface is received;

[0070] If yes, collecting the location information of the user and converting the location information into a target code corresponding to a target code format;

[0071] Calling a preset code database to search for a first customer list corresponding to the target code and meeting the target distance range condition;

[0072] Acquire customer feature data of a target processing customer corresponding to the user, and generate a customer feature vector corresponding to the customer feature data based on a preset component interface;

[0073] Searching for a similarity ordered list corresponding to the customer feature vector based on a preset vector database;

[0074] Screening the first customer list and the similarity ordered list to generate a corresponding second customer list;

[0075] Sorting the customers in the second customer list by scores based on a preset sorting strategy to obtain a sorted target customer list;

[0076] The target customer list is displayed.

[0077] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0078] The present application first determines whether an information recommendation request triggered by a user in a preset interface is received; if so, the user's location information is collected and converted into a target code corresponding to a target coding format; then a preset coding database is called to search for a first customer list corresponding to the target code that meets a target distance range condition; thereafter, customer feature data of a target processing customer corresponding to the user is obtained, and a customer feature vector corresponding to the customer feature data is generated based on a preset component interface; subsequently, a similarity ordered list corresponding to the customer feature vector is searched based on a preset vector database; and the first customer list and the similarity ordered list are screened to generate a corresponding second customer list; further, the customers in the second customer list are sorted by scores based on a preset sorting strategy to obtain a sorted target customer list; and finally, the target customer list is displayed. After receiving an information recommendation request triggered by a user in a preset interface, the present application searches for a first customer list that meets the target distance range condition and corresponds to a target code that matches the user's location information based on the use of a code database, then obtains customer feature data of a target processing customer corresponding to the user, and generates a customer feature vector corresponding to the customer feature data based on a preset component interface, and searches for a similarity ordered list corresponding to the customer feature vector based on a vector database, then screens the first customer list and the similarity ordered list to generate a second customer list, and then sorts the customers in the second customer list by scores based on a sorting strategy to obtain a sorted target customer list, so that subsequent display processing based on the generated target customer list can realize an intelligent surrounding customer recommendation service for the user, improve the accuracy and intelligence of surrounding customer recommendations, and thus improve the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0080] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0081] Figure 2 A flowchart of an embodiment of the information recommendation method according to the present application;

[0082] Figure 3 is a structural schematic diagram of an embodiment of an information recommendation device according to the present application;

[0083] Figure 4 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0084] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0085] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0086] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0087] like Figure 1 As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0088] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0089] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to the laptop computer 1011, tablet computer 1012 or mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer, a desktop computer, etc.

[0090] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0091] It should be noted that the information recommendation method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the information recommendation device is generally arranged in the server / terminal device.

[0092] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0093] Continue to refer Figure 2 , shows a flow chart of an embodiment of the information recommendation method according to the present application. According to different requirements, the order of the steps in the flow chart can be changed, and some steps can be omitted. The information recommendation method provided in the embodiment of the present application can be applied to any scenario where information recommendation is required, and the information recommendation method can be applied to products in these scenarios, for example, customer recommendation in the financial insurance field. The information recommendation method includes the following steps:

[0094] Step S201, determining whether an information recommendation request triggered by a user in a preset interface is received.

[0095] In this embodiment, the information recommendation method is executed on the electronic device (eg Figure 1The server / terminal device shown in the figure) can obtain the information recommendation request through a wired connection or a wireless connection. It should be pointed out that the above-mentioned wireless connection method may include but is not limited to 3G / 4G / 5G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future. The executor of the present application is specifically an information recommendation system, or a customer relationship management system, which can be referred to as the system for short. The present application can be applied to the business marketing field of financial insurance to realize the function of automatically recommending surrounding customers to sales personnel. The above-mentioned preset interface is an interface for the system to interact with the sales personnel, specifically a surrounding customer recommendation visualization system interface. The above-mentioned user may be a salesperson. The above-mentioned information recommendation request may be a business request triggered by a customer to request the system to provide a recommendation service for visiting surrounding customers.

[0096] Step S202: If yes, collect the user's location information and convert the location information into a target code corresponding to a target coding format.

[0097] In this embodiment, after receiving the information recommendation request triggered by the user, the system starts the real-time location tracking function and uses the front-end technology or the SDK of the mobile device to request the user's current location. Specifically, the user's location information is obtained through various methods such as GPS, base station information or WIFI. The location information can be longitude and latitude information.

[0098] The target encoding format is specifically a GEO hash encoding format. The user's location information can be converted into a format recognizable by the Redis GEO database by using a Redis GEO command, such as GEORADIUSBYMEMBER or GEORADIUS, to obtain the corresponding GEO hash encoding, namely the target encoding.

[0099] Step S203, calling a preset code database to search for a first customer list corresponding to the target code and meeting the target distance range condition.

[0100] In this embodiment, the above-mentioned coding database is specifically a Redis GEO database. The system processes the common addresses of all customers in the preset customer database offline through a distributed timing scheduling platform, and resolves the Chinese address into the address longitude and latitude with the help of the LBS map interface. And with the help of the ability of the distributed Redis GEO database to process the GEO hash coding address, the address longitude and latitude data of all customers are stored to provide the address distance range search capability. By passing the above-mentioned target code into the coding database, all customers within the target distance range corresponding to the user's surroundings (current location) can be searched. Among them, the search radius (N kilometers) and unit (such as km) can be specified according to actual usage requirements to determine the target distance range. Then, according to the customer IDs of all customers within the target distance range obtained, the detailed information of all customers, such as name, address, etc., is queried from the customer database, and the corresponding first customer list is constructed. Among them, the above-mentioned first customer list includes at least the customer ID, and can also include customer information corresponding to the customer ID.

[0101] Step S204, acquiring customer feature data of a target processing customer corresponding to the user, and generating a customer feature vector corresponding to the customer feature data based on a preset component interface.

[0102] In this embodiment, the target processing customer is specifically the user's most recent interactive customer or sales customer. The customer feature data is a key field for determining the generation of a customer feature vector corresponding to the customer that the user frequently serves. Among them, the selection of customer feature data is related to the specific business scenario, and the quality of the recommendation mainly depends on the selection of data. Preferably, high-value clue data related to the salesperson's recent interaction is selected. For example, the specialist's face-to-face interview work record, the customer's interests and hobbies, wealth level, the customer's recent interactive communication record, the customer's recent insurance policy preservation and claim information, community service clue description, etc.

[0103] Specifically, the above component interface is specifically an embedding component interface. By preprocessing the customer feature data to ensure that they are consistent with the data format used to train the embedding model, the specified customer feature data is obtained. Then, the embedding component interface sends the preprocessed specified customer feature data to the model service. After receiving the data, the model service uses the embedding component of T5-base or a similar model to generate a real-time feature vector, that is, the above customer feature vector, and returns it to the system.

[0104] Step S205: searching a similarity ordered list corresponding to the customer feature vector based on a preset vector database.

[0105] In this embodiment, the above-mentioned similarity ordered list is a list of customer IDs and their similarity scores that are most similar to the above-mentioned customer feature vectors returned by the vector database. Specifically, the system scans the feature data of all customers in the preset customer database offline through a distributed timing scheduling platform, generates feature vector data of each customer with the help of the embedding component interface of the open source large model T5-base, and stores the feature vector data in the customer feature vector database (referred to as the vector database) to provide a fast high-dimensional vector similarity search capability.

[0106] The specific implementation process of searching for the similarity ordered list corresponding to the customer feature vector based on the preset vector database will be described in further detail in subsequent specific embodiments of the present application, and will not be elaborated on here.

[0107] Step S206: screening the first customer list and the similarity ordered list to generate a corresponding second customer list.

[0108] In this embodiment, the specific implementation process of screening the first customer list and the similarity ordered list to generate the corresponding second customer list will be further described in detail in subsequent specific embodiments of the present application and will not be elaborated on here.

[0109] Step S207: sorting the customers in the second customer list by scores based on a preset sorting strategy to obtain a sorted target customer list.

[0110] In this embodiment, the specific implementation process of performing score sorting processing on the customers in the second customer list based on the preset sorting strategy to obtain the sorted target customer list will be further described in detail in subsequent specific embodiments of the present application and will not be elaborated on here.

[0111] Step S208: display the target customer list.

[0112] In this embodiment, the specific implementation process of displaying the target customer list will be described in further detail in subsequent specific embodiments of the present application, and will not be elaborated on here.

[0113] After receiving an information recommendation request triggered by a user in a preset interface, the present application searches for a first customer list that meets the target distance range condition and corresponds to a target code that matches the user's location information based on the use of a code database, then obtains customer feature data of a target processing customer corresponding to the user, and generates a customer feature vector corresponding to the customer feature data based on a preset component interface, and searches for a similarity ordered list corresponding to the customer feature vector based on a vector database, then screens the first customer list and the similarity ordered list to generate a second customer list, and then sorts the customers in the second customer list by scores based on a sorting strategy to obtain a sorted target customer list, so that subsequent display processing based on the generated target customer list can realize an intelligent surrounding customer recommendation service for the user, improve the accuracy and intelligence of surrounding customer recommendations, and thus improve the user experience.

[0114] In some optional implementations, step S205 includes the following steps:

[0115] Gets the preset search parameters.

[0116] In this embodiment, the above-mentioned search parameters are search parameters corresponding to the vector database. The search parameters may at least include the K nearest neighbor number (KNN). The K nearest neighbor number indicates the number of nearest neighbors to be returned. The value of the K nearest neighbor number can be determined according to the specific application scenario to balance the search speed and the relevance of the results. In addition, the search parameters may also include a search radius. By specifying a search radius, only vectors within the radius of the query vector are returned. Alternatively, other parameters may also be included, such as the detection depth during the search.

[0117] Based on the search parameters and the customer feature vector, a similarity search is performed on the full set of customer feature vectors stored in the vector database to obtain a corresponding index array and a similarity score array.

[0118] In this embodiment, by passing the customer feature vector as a query vector to the search function in the vector database and passing in the set search parameters, the vector database will perform a similarity search on the entire set of stored customer feature vectors and return two arrays (an index array and a similarity score array): the index array is an index containing the K nearest neighbors (i.e., the index of the customer ID), and the similarity score array contains the similarity scores of these neighbors and the query vector (usually the negative value of the Euclidean distance or the positive value of the cosine similarity, depending on the configuration of the index).

[0119] The index array and the similarity score array are converted to obtain a corresponding data list.

[0120] In this embodiment, the returned index array and similarity score array are converted to obtain an easily understandable data list containing the mapping relationship between the customer identification (customer ID) and the customer's similarity score.

[0121] The data list is sorted based on the similarity scores included in the similarity score array to obtain a sorted data list.

[0122] In this embodiment, the customer identifiers included in the data list may be sorted from large to small according to the similarity scores included in the similarity score array, thereby obtaining a sorted data list.

[0123] The sorted data list is used as the similarity ordered list.

[0124] The present application obtains preset search parameters; then based on the search parameters and the customer feature vector, performs a similarity search on the stored full set of customer feature vectors through the vector database to obtain a corresponding index array and a similarity score array; then converts the index array and the similarity score array to obtain a corresponding data list; subsequently, sorts the data list based on the similarity scores contained in the similarity score array to obtain a sorted data list, and uses the sorted data list as the similarity ordered list. In the process of using a vector database to perform a similarity search on the stored full set of customer feature vectors, the present application can effectively control the search process and optimize the search performance and result quality by specifying search parameters, effectively improving the generation efficiency and accuracy of the similarity ordered list generated based on the index array and the similarity score array.

[0125] In some optional implementations of this embodiment, step S206 includes the following steps:

[0126] Get the preset customer ID.

[0127] In this embodiment, the above-mentioned customer identification refers to the customer identification corresponding to the customers included in the first customer list and the similarity ordered list, that is, the customer ID.

[0128] Based on the customer identifier, an intersection calculation is performed on the first customer list and the similarity ordered list to obtain target customers that appear in both the first customer list and the similarity ordered list.

[0129] In this embodiment, the first customer list and the similarity ordered list are traversed, and the customer identifier is used as a key to match and filter out customers that appear in both lists, thereby obtaining the target customer.

[0130] Gets an initial list of presets.

[0131] In this embodiment, the initial list is a new list constructed in advance.

[0132] The target customer adds information to the initial list to obtain a processed initial list.

[0133] In this embodiment, the target customers are added to the initial list to obtain a processed initial list.

[0134] The processed initial list is used as the second customer list.

[0135] The present application calculates the intersection of the first customer list and the similarity ordered list based on the use of customer identifiers, thereby enabling the target customers that appear in both the first customer list and the similarity ordered list to be obtained quickly and accurately. Then, information is added to the preset initial list based on the target customer, thereby automatically and intelligently completing the construction of the second customer list, improving the construction efficiency of the second customer list and ensuring the data accuracy of the obtained second customer list.

[0136] In some optional implementations, step S207 includes the following steps:

[0137] The first similarity scores of all first customers included in the second customer list are obtained.

[0138] In this embodiment, the second customer list is a list including the customer ID of the first customer and the first similarity score corresponding to the first customer. The first similarity score of the corresponding first customer can be obtained by extracting information from the second customer list.

[0139] Calls the preset sort statement.

[0140] In this embodiment, the above-mentioned sorting statement may specifically adopt a sorting function statement provided by the database, for example, it may be an ORDER BY clause of SQL.

[0141] Based on the sorting statement, all the first customers included in the second customer list are sorted from high to low according to the first similarity scores to obtain a sorted third customer list.

[0142] In this embodiment, the second customer list is sorted by using the above sorting statement to sort all the first customers included in the second customer list from high to low according to the first similarity scores, thereby obtaining a sorted third customer list.

[0143] The third customer list is used as the target customer list.

[0144] This application uses a sorting statement to sort all the first customers included in the second customer list from high to low according to the first similarity score, thereby quickly and accurately completing the score sorting process for the customers in the second customer list, optimizing the sorting process, improving the processing efficiency of the score sorting process, and improving the efficiency of generating the target customer list. This is conducive to the subsequent intelligent surrounding customer recommendation service for the user based on the generated target customer list, improving the accuracy and intelligence of the surrounding customer recommendation, and thus improving the user experience.

[0145] In some optional implementations, step S207 includes the following steps:

[0146] The distance information between the user and all second customers included in the second customer list is respectively obtained.

[0147] In this embodiment, the customer location information of the second customer can be queried from a preset customer database, and then the distance between the customer location information of the second customer and the location information of the user can be calculated, so as to obtain the distance of the second customer relative to the user, that is, the location information.

[0148] The second similarity scores of all the second customers included in the second customer list are obtained.

[0149] In this embodiment, the second customer list is a list including customer IDs of second customers and second similarity scores corresponding to the second customers.

[0150] The distance information and the second similarity score are scored based on a preset scoring strategy to obtain a customer score for each of the second customers.

[0151] In this embodiment, the specific implementation process of scoring the distance information and the second similarity score based on the preset scoring strategy to obtain the customer score of each second customer will be further described in detail in subsequent specific embodiments of the present application and will not be elaborated on here.

[0152] Call the preset sorting algorithm.

[0153] In this embodiment, the above-mentioned sorting algorithm may specifically adopt algorithms such as quick sort and merge sort.

[0154] Based on the sorting algorithm, all the second customers included in the second customer list are sorted from high to low according to the customer scores to obtain a sorted fourth customer list.

[0155] In this embodiment, the second customer list is sorted by using the above-mentioned sorting algorithm to sort all the second customers included in the second customer list from high to low according to the customer scores, thereby obtaining a sorted fourth customer list.

[0156] The fourth customer list is used as the target customer list.

[0157] This application obtains the distance information between the user and all the second customers included in the second customer list, and obtains the second similarity scores of all the second customers included in the second customer list, and then sorts all the second customers included in the second customer list from high to low according to the second similarity scores based on the use of the sorting algorithm, thereby achieving efficient and accurate score sorting processing for customers in the second customer list, optimizing the sorting process, improving the processing efficiency of the score sorting processing, and improving the efficiency of generating the target customer list. It is beneficial to subsequently realize intelligent surrounding customer recommendation services for users based on the generated target customer list, improve the accuracy and intelligence of surrounding customer recommendations, and thus improve the user experience.

[0158] In some optional implementations of this embodiment, the scoring process of the distance information and the second similarity score based on a preset scoring strategy to obtain a customer score of each second customer includes the following steps:

[0159] Call the preset weight setting algorithm.

[0160] In this embodiment, there is no specific limitation on the selection of the above-mentioned weight setting algorithm, and specifically, any one of the principal component analysis method, entropy method, factor analysis method, standardization method, etc. can be adopted.

[0161] A first weight corresponding to the distance factor is generated based on the weight setting algorithm, and a second weight corresponding to the similarity factor is generated.

[0162] In this embodiment, weight calculation processing can be performed on all factors corresponding to generating customer scores (distance factors and similarity factors) according to the corresponding weight calculation processing steps in the above-mentioned weight setting algorithm, so as to obtain a first weight corresponding to the distance factor and generate a second weight corresponding to the similarity factor.

[0163] Obtaining designated distance information and a designated similarity score of a designated customer; wherein the designated customer is any one of all the second customers.

[0164] In this embodiment, information about a designated customer may be obtained to obtain designated distance information and a designated similarity score of the designated customer.

[0165] The specified distance information, the specified similarity score, the first weight, and the second weight are calculated based on a preset score generation algorithm to obtain a corresponding calculation result.

[0166] In this embodiment, the score generation algorithm may specifically include: S=a*X+b*Y, where S is the customer score, X is the distance information, a is the first weight, Y is the similarity score, and b is the second weight. The specified distance information, the specified similarity score, the first weight, and the second weight may be substituted into the corresponding positions in the score generation algorithm for calculation processing to obtain the corresponding calculation result.

[0167] The calculation result is used as the customer score of the designated customer.

[0168] The present application generates a first weight corresponding to the distance factor and a second weight corresponding to the similarity factor based on the use of a weight setting algorithm, and then calculates and processes the specified distance information and the specified similarity score of the specified customer, as well as the first weight and the second weight based on the use of a score generation algorithm, thereby enabling the rapid and accurate generation of the customer score of the specified customer, and effectively ensuring the data accuracy of the generated customer score. This is conducive to accurately sorting the customers in the second customer list based on the obtained customer scores, thereby improving the accuracy and intelligence of the generated target customer list.

[0169] In some optional implementations of this embodiment, step S208 includes the following steps:

[0170] Get the preset customer distribution map.

[0171] In this embodiment, the customer distribution map is a pre-built distribution map containing customer information for assisting sales personnel in business marketing.

[0172] Determine the recommended customers included in the target customer list.

[0173] In this embodiment, the recommended customers are all customers included in the target customer list.

[0174] The recommended customers are processed by position highlighting in the customer distribution map to obtain a corresponding target customer distribution map.

[0175] In this embodiment, the locations of the recommended customers can be plotted on the customer distribution map of the salesperson by using the API of the map service, and the location of each recommended customer can be highlighted. Different colors or icons can be used to distinguish different similarity scores or customer scores.

[0176] The target customer distribution map and the target customer list are displayed in the preset interface.

[0177] In this embodiment, two areas may be preset in the preset interface, including a map area and a customer list area, and the target customer distribution map may be displayed in the map area, and the target customer list may be displayed in the customer list area.

[0178] In addition, detailed information of each recommended customer can be displayed in the preset interface, including name, address, similarity score, distance, customer score, etc. This information can be displayed in the form of a list, table or card, so that sales staff can quickly browse and select. Furthermore, interactive functions can be provided, such as clicking on a customer name or address to jump to a more detailed customer information page, or directly jump to the customer location on a map.

[0179] The present application, based on the use of a customer distribution map, highlights the locations of recommended customers included in a target customer list in the customer distribution map to obtain a corresponding target customer distribution map, and then displays the target customer distribution map and the target customer list in the preset interface, thereby improving the display executability and diversity of the recommendation information, thereby providing users with an intelligent and enriched surrounding customer recommendation examination, effectively improving the user experience.

[0180] In some optional implementations, the user information obtained is subject to the user's consent and complies with relevant laws and policies.

[0181] In addition, the non-Company software tools or components that appear in the embodiments of the present application are merely examples and do not represent actual use.

[0182] This application uses the best recommendation algorithm of surrounding customers combined with real-time geographic location information obtained with the permission of sales personnel, instant or frequently used address information of company customers, interactive information between sales personnel and customers, and various types of customer label feature data. Under the protection of the privacy of customers and sales personnel and the legality, compliance and security of data, it uses big data and intelligent recommendation algorithms to recommend nearby ideal customers to sales personnel in real time. On the one hand, it meets the immediate needs of sales personnel in mobile business development and provides sales personnel with a more convenient and personalized service experience. On the other hand, it promptly solves customers' proactive needs and improves customer satisfaction. At the same time, it increases the number of face-to-face visits per person for sales personnel, increases the amount of activities, and thus increases sales opportunities, thereby improving customer conversion rates.

[0183] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0184] It should be emphasized that in order to further ensure the privacy and security of the above-mentioned target customer list, the above-mentioned target customer list can also be stored in a node of a blockchain.

[0185] The blockchain referred to in this application is a new application model 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.

[0186] 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.

[0187] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0188] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0189] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0190] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of an information recommendation device, and the device embodiment is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0191] like Figure 3 As shown, the information recommendation device 300 described in this embodiment includes: a judgment module 301, a conversion module 302, a first search module 303, a generation module 304, a second search module 305, a screening module 306, a sorting module 307 and a display module 308. Among them:

[0192] The judgment module 301 is used to judge whether an information recommendation request triggered by a user in a preset interface is received;

[0193] A conversion module 302 is used to collect the user's location information and convert the location information into a target code corresponding to a target code format;

[0194] A first search module 303 is used to call a preset code database to search for a first customer list corresponding to the target code and meeting the target distance range condition;

[0195] A generating module 304, configured to obtain customer feature data of a target processing customer corresponding to the user, and generate a customer feature vector corresponding to the customer feature data based on a preset component interface;

[0196] A second search module 305 is used to search for a similarity ordered list corresponding to the customer feature vector based on a preset vector database;

[0197] A screening module 306, configured to screen the first customer list and the similarity ordered list to generate a corresponding second customer list;

[0198] A sorting module 307 is used to sort the customers in the second customer list by scores based on a preset sorting strategy to obtain a sorted target customer list;

[0199] The display module 308 is used to display the target customer list.

[0200] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the information recommendation method in the above-mentioned implementation mode, and are not described in detail here.

[0201] In some optional implementations of this embodiment, the second search module 305 includes:

[0202] A first acquisition submodule, used to acquire preset search parameters;

[0203] A search submodule, configured to perform a similarity search on the full set of stored customer feature vectors through the vector database based on the search parameters and the customer feature vectors, and obtain a corresponding index array and a similarity score array;

[0204] A conversion submodule, used for converting the index array and the similarity score array to obtain a corresponding data list;

[0205] A first sorting submodule, configured to sort the data list based on the similarity scores included in the similarity score array to obtain a sorted data list;

[0206] The first determining submodule is used to use the sorted data list as the similarity ordered list.

[0207] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the information recommendation method in the above-mentioned implementation mode, and are not described in detail here.

[0208] In some optional implementations of this embodiment, the screening module 306 includes:

[0209] The second acquisition submodule is used to acquire a preset customer identifier;

[0210] A calculation submodule, configured to perform intersection calculation on the first customer list and the similarity ordered list based on the customer identifier, to obtain target customers that appear in both the first customer list and the similarity ordered list;

[0211] The third acquisition submodule is used to acquire a preset initial list;

[0212] An adding submodule, used for adding information of the target customer to the initial list to obtain a processed initial list;

[0213] The second determining submodule is configured to use the processed initial list as the second customer list.

[0214] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the information recommendation method in the above-mentioned implementation mode, and are not described in detail here.

[0215] In some optional implementations of this embodiment, the sorting module 307 includes:

[0216] A third acquisition submodule, configured to acquire first similarity scores of all first customers included in the second customer list;

[0217] The first calling submodule is used to call a preset sorting statement;

[0218] A second sorting submodule, configured to sort all the first customers included in the second customer list from high to low according to the first similarity scores based on the sorting statement, to obtain a sorted third customer list;

[0219] The third determining submodule is configured to use the third customer list as the target customer list.

[0220] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the information recommendation method in the above-mentioned implementation mode, and are not described in detail here.

[0221] In some optional implementations of this embodiment, the sorting module 307 includes:

[0222] a fourth acquisition submodule, configured to respectively acquire distance information between the user and all second customers included in the second customer list;

[0223] A fifth acquisition submodule, configured to acquire second similarity scores of all second customers included in the second customer list;

[0224] a scoring submodule, configured to score the distance information and the second similarity score based on a preset scoring strategy to obtain a customer score for each of the second customers;

[0225] The second calling submodule is used to call a preset sorting algorithm;

[0226] A third sorting submodule, configured to sort all the second customers included in the second customer list from high to low according to the customer scores based on the sorting algorithm, to obtain a sorted fourth customer list;

[0227] The fourth determining submodule is configured to use the fourth customer list as the target customer list.

[0228] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the information recommendation method in the above-mentioned implementation mode, and are not described in detail here.

[0229] In some optional implementations of this embodiment, the scoring submodule includes:

[0230] A calling unit, used to call a preset weight setting algorithm;

[0231] A generating unit, configured to generate a first weight corresponding to a distance factor and a second weight corresponding to a similarity factor based on the weight setting algorithm;

[0232] An acquisition unit, configured to acquire designated distance information and a designated similarity score of a designated customer; wherein the designated customer is any one of all the second customers;

[0233] a calculation unit, configured to calculate the specified distance information, the specified similarity score, the first weight, and the second weight based on a preset score generation algorithm to obtain a corresponding calculation result;

[0234] A determination unit is configured to use the calculation result as the customer score of the designated customer.

[0235] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the information recommendation method in the above-mentioned implementation mode, and are not described in detail here.

[0236] In some optional implementations of this embodiment, the display module 308 includes:

[0237] The sixth acquisition submodule is used to acquire a preset customer distribution map;

[0238] A fifth determination submodule, used to determine the recommended customers included in the target customer list;

[0239] A marking submodule, used to highlight the location of the recommended customer in the customer distribution map to obtain a corresponding target customer distribution map;

[0240] The display submodule is used to display the target customer distribution map and the target customer list in the preset interface.

[0241] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the information recommendation method in the above-mentioned implementation mode, and are not described in detail here.

[0242] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0243] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 4 with components 41-43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0244] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0245] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk equipped on the computer device 4, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of the information recommendation method, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0246] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run computer-readable instructions stored in the memory 41 or process data, such as computer-readable instructions for running the information recommendation method.

[0247] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0248] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the information recommendation method as described above.

[0249] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0250] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. An information recommendation method, characterized in that: The steps include: Determine whether an information recommendation request triggered by a user in a preset interface is received; If yes, collecting the location information of the user and converting the location information into a target code corresponding to a target code format; Calling a preset code database to search for a first customer list corresponding to the target code and meeting the target distance range condition; Acquire customer feature data of a target processing customer corresponding to the user, and generate a customer feature vector corresponding to the customer feature data based on a preset component interface; Searching for a similarity ordered list corresponding to the customer feature vector based on a preset vector database; Screening the first customer list and the similarity ordered list to generate a corresponding second customer list; Sorting the customers in the second customer list by scores based on a preset sorting strategy to obtain a sorted target customer list; The target customer list is displayed.

2. The information recommendation method according to claim 1, characterized in that: The step of searching for a similarity ordered list corresponding to the customer feature vector based on a preset vector database specifically includes: Get the preset search parameters; Based on the search parameters and the customer feature vector, a similarity search is performed on the full set of customer feature vectors stored in the vector database to obtain a corresponding index array and a similarity score array; Convert the index array and the similarity score array to obtain a corresponding data list; Sorting the data list based on the similarity scores included in the similarity score array to obtain a sorted data list; The sorted data list is used as the similarity ordered list.

3. The information recommendation method according to claim 1, characterized in that: The step of screening the first customer list and the similarity ordered list to generate a corresponding second customer list specifically includes: Get the preset customer ID; Based on the customer identifier, performing intersection calculation on the first customer list and the similarity ordered list to obtain target customers that appear in both the first customer list and the similarity ordered list; Get the initial list of presets; Adding information of the target customer to the initial list to obtain a processed initial list; The processed initial list is used as the second customer list.

4. The information recommendation method according to claim 1, characterized in that: The step of performing score sorting processing on the customers in the second customer list based on a preset sorting strategy to obtain a sorted target customer list specifically includes: Obtaining first similarity scores of all first customers included in the second customer list; Call the preset sort statement; Based on the sorting statement, sort all the first customers included in the second customer list from high to low according to the first similarity score to obtain a sorted third customer list; The third customer list is used as the target customer list.

5. The information recommendation method according to claim 1, characterized in that: The step of performing score sorting processing on the customers in the second customer list based on a preset sorting strategy to obtain a sorted target customer list specifically includes: respectively obtaining distance information between the user and all second customers included in the second customer list; Obtaining second similarity scores of all second customers included in the second customer list; Scoring the distance information and the second similarity score based on a preset scoring strategy to obtain a customer score for each of the second customers; Call the preset sorting algorithm; Based on the sorting algorithm, sort all the second customers included in the second customer list from high to low according to the customer scores to obtain a sorted fourth customer list; The fourth customer list is used as the target customer list.

6. The information recommendation method according to claim 5, characterized in that: The step of scoring the distance information and the second similarity score based on a preset scoring strategy to obtain a customer score of each of the second customers specifically includes: Call the preset weight setting algorithm; generating a first weight corresponding to the distance factor based on the weight setting algorithm, and generating a second weight corresponding to the similarity factor; Obtaining designated distance information and designated similarity score of a designated customer; wherein the designated customer is any one of all the second customers; Calculating the specified distance information, the specified similarity score, the first weight, and the second weight based on a preset score generation algorithm to obtain a corresponding calculation result; The calculation result is used as the customer score of the designated customer.

7. The information recommendation method according to claim 1, characterized in that: The step of displaying the target customer list specifically includes: Get the preset customer distribution map; Determining recommended customers included in the target customer list; Performing location highlighting processing on the recommended customers in the customer distribution map to obtain a corresponding target customer distribution map; The target customer distribution map and the target customer list are displayed in the preset interface.

8. An information recommendation device, characterized in that: include: A determination module, used to determine whether an information recommendation request triggered by a user in a preset interface is received; A conversion module, configured to collect the location information of the user and convert the location information into a target code corresponding to a target code format; A first search module, used to call a preset code database to search for a first customer list corresponding to the target code and meeting the target distance range condition; A generating module, used for acquiring customer characteristic data of a target processing customer corresponding to the user, and generating a customer characteristic vector corresponding to the customer characteristic data based on a preset component interface; A second search module, used to search for a similarity ordered list corresponding to the customer feature vector based on a preset vector database; A screening module, used for screening the first customer list and the similarity ordered list to generate a corresponding second customer list; A sorting module, used to sort the customers in the second customer list by scores based on a preset sorting strategy to obtain a sorted target customer list; A display module is used to display the target customer list.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the information recommendation method according to any one of claims 1 to 7 when executing the computer-readable instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the information recommendation method according to any one of claims 1 to 7 are implemented.

Images