Service recommendation method and device, electronic equipment and computer readable storage medium

Abstract

Embodiments of the invention provide a service recommendation method and apparatus, an electronic device and a computer readable storage medium. The method comprises the steps of obtaining search information of a user through a preset acquisition program; determining a target user; querying enterprise information of the target user based on a preset data system; determining the similarity between the enterprise information and the search information based on a preset matching model; the target users with the similarity larger than a preset similarity threshold value serve as recommended users; according to the method, the information disclosed by the user is actively acquired, the identity of the user is determined based on the public information, and the advertisement is pointedly delivered, so that the user does not need to fill in the information, the experience of browsing the marketing webpage by the user is improved, the acquisition of malicious or invalid information can be reduced, the wasting of resources by the marketing party for invalid follow-up is reduced, and further, the user experience is improved. And under the condition that the user does not actively leave the contact way, the user can be actively contacted to follow up, so that the customer conversion rate is improved.

Description

Technical Field

[0001] The present invention relates to the field of advertising technology, and in particular to a business recommendation method, device, electronic device and computer-readable storage medium. Background Art

[0002] Internet online advertising has become the main advertising method besides television and newspapers. The existing marketing webpage customer acquisition method is usually to attract users to the marketing page through search engine optimization and publishing eye-catching content, and then guide users to leave personal information or contact information, and the marketing party will then contact the user and convert him into a potential customer.

[0003] However, in the prior art, user operations are cumbersome and require filling in a large amount of information. In addition, for the sake of privacy protection, users may deliberately fill in incorrect information. Therefore, the information actively filled in by users may contain malicious or invalid information, causing the marketing party to waste resources for invalid follow-up; further, if the user does not actively leave contact information, the marketing party cannot actively contact the user. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide a business recommendation method, device, electronic device and computer-readable storage medium, which actively obtains user public information, determines the user identity based on the public information, and delivers targeted advertisements. This method does not require users to fill in information, thereby improving the user's experience of browsing marketing web pages. At the same time, it can reduce the acquisition of malicious or invalid information and reduce the marketing party's waste of resources for invalid follow-up. Furthermore, even if the user does not actively leave contact information, the user can be actively contacted for follow-up, thereby improving customer conversion rate.

[0005] In a first aspect, an embodiment of the present invention provides a business recommendation method, which includes: responding to a user's search request, obtaining the user's search information through a preset collection program; determining at least one target user based on the user address information included in the search information; querying the target user's corporate information based on a preset data system; wherein the corporate information includes: the business tag and industry tag of the enterprise; determining the similarity between the corporate information and the search information based on a preset matching model; and recommending the target user whose similarity is greater than a preset similarity threshold as a recommended user.

[0006] In some preferred embodiments of the present invention, in response to a user's search request, the step of obtaining the user's search information through a pre-set collection program includes: responding to the user's search request, collecting the search text input by the user; outputting a marketing interface based on the search text; the marketing interface includes at least one marketing information; responding to the user's request to enter the target marketing information, collecting the user's address information and promotional keywords of the target marketing information; and using the search text, user address information and promotional keywords as the user's search information.

[0007] In some preferred embodiments of the present invention, the enterprise information also includes: contact information; after the step of taking the target user whose similarity is greater than a preset similarity threshold as a recommended user, the method also includes: querying the contact information of the recommended user based on a preset data system.

[0008] In some preferred embodiments of the present invention, the data system is established through the following steps: crawling corporate information from public web pages; storing the corporate information in a database, and constructing a data system.

[0009] In some preferred embodiments of the present invention, the matching model is established through the following steps: determining a training set and a validation set; both the training set and the validation set include the business label, industry label, search text corresponding to the enterprise, and promotional keywords; wherein, one enterprise corresponds to one business label, one industry label and one promotional keyword, and one enterprise corresponds to multiple search texts; training the matching model based on the training set and the validation set.

[0010] In some preferred embodiments of the present invention, the step of training a matching model based on a training set and a validation set includes: inputting the training set into a basic model for model training; judging whether the trained basic model has converged based on the validation set; if converged, using the trained basic model as a matching model; if not converged, inputting the training set into the basic model for training until the basic model converges.

[0011] In a second aspect, an embodiment of the present invention provides a business recommendation device, which includes: a search information collection module, which is used to respond to a user's search request and obtain the user's search information through a preset collection program; a target user determination module, which is used to determine at least one target user based on the user address information included in the search information; an enterprise information acquisition module, which is used to query the enterprise information of the target user based on a preset data system; wherein the enterprise information includes: the enterprise's business label and industry label; a similarity determination module, which is used to determine the similarity between the enterprise information and the search information based on a preset matching model; and a recommended user determination module, which is used to select target users whose similarity is greater than a preset similarity threshold as recommended users.

[0012] In some preferred embodiments of the present invention, the search information collection module is used to respond to the user's search request and collect the search text input by the user; output a marketing interface based on the search text; the marketing interface includes at least one marketing information; respond to the user's request to enter the target marketing information, collect the user's address information and the promotional keywords of the target marketing information; use the search text, user address information and promotional keywords as the user's search information.

[0013] In a third aspect, an embodiment of the present invention provides an electronic device, including a processor and a memory, wherein the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement any of the above-mentioned business recommendation methods.

[0014] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement any of the above-mentioned business recommendation methods.

[0015] The embodiments of the present invention bring the following beneficial effects:

[0016] The embodiments of the present invention provide a business recommendation method, device, electronic device and computer-readable storage medium. The business recommendation method includes: responding to a user's search request, obtaining the user's search information through a preset collection program; determining at least one target user based on the user address information included in the search information; querying the target user's corporate information based on a preset data system; wherein the corporate information includes: the business label and industry label of the enterprise; determining the similarity between the corporate information and the search information based on a preset matching model; using the target user whose similarity is greater than a preset similarity threshold as a recommended user; actively obtaining the user's public information, determining the user's identity based on the public information, and delivering targeted advertisements. The method does not require the user to fill in information, thereby improving the user's experience of browsing marketing web pages, and at the same time can reduce the acquisition of malicious or invalid information, reduce the marketing party's waste of resources for invalid follow-up, and further, in the case where the user does not actively leave contact information, the user can be actively contacted for follow-up, thereby improving the customer conversion rate.

[0017] Other features and advantages disclosed in the present invention will be set forth in the following description, or some features and advantages may be inferred or unambiguously determined from the description, or may be learned by implementing the above-mentioned technology of the present invention.

[0018] In order to make the above-mentioned objectives, features and advantages of the present disclosure more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 A flowchart of a service recommendation method provided by an embodiment of the present invention;

[0021] Figure 2 A flowchart of a matching model training method provided by an embodiment of the present invention;

[0022] Figure 3 A schematic diagram of the structure of a business recommendation device provided by an embodiment of the present invention;

[0023] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention.

[0024] Icons: 310 - search information acquisition module; 320 - target user determination module; 330 - enterprise information acquisition module; 340 - similarity determination module; 350 - recommended user determination module; 400 - memory; 401 - processor; 402 - bus; 403 - communication interface. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0026] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0028] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inside", "outside", etc. indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, or the positions or positional relationships in which the product of the invention is usually placed when in use. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific position, be constructed and operated in a specific position, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0029] In addition, the terms "horizontal", "vertical", "overhanging" and the like do not mean that the components are required to be absolutely horizontal or overhanging, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", and does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0030] In the description of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0031] The existing marketing webpage customer acquisition method is usually to attract users to the marketing page through search engine optimization and the publication of eye-catching content, and then guide users to leave personal information or contact information, and the marketing party will then contact the user and convert him into a potential customer. However, in the existing technology, the user operation is relatively cumbersome and requires a large amount of information to be filled in. In addition, for the sake of privacy protection, users may deliberately fill in wrong information. Therefore, the information actively filled in by the user may contain malicious or invalid information, causing the marketing party to waste resources for invalid follow-up; further, if the user does not actively leave contact information, the marketing party cannot actively contact the user.

[0032] Some embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0033] Embodiment 1

[0034] The embodiment of the present invention provides a service recommendation method, see Figure 1 A flowchart of a service recommendation method provided by an embodiment of the present invention includes the following steps:

[0035] Step S102, responding to the user's search request, obtaining the user's search information through a pre-set collection program;

[0036] Specifically, JavaScript (JS, a lightweight, interpreted or just-in-time compiled programming language with function priority) code is embedded into the web page in advance to send HTTP requests to the back-end server and get responses. This technology is usually called Ajax (Asynchronous JavaScript and XML, a web development technology for creating interactive web applications), which can help web pages update part of the content without refreshing the page and improve the user experience.

[0037] Specifically, the search information is collected through the following steps A1 to A4:

[0038] Step A1, responding to a user's search request and collecting a search text input by the user;

[0039] Specifically, a user searching on a web page generally refers to a user using a search engine or other query tool to enter keywords on a web page to search for relevant information.

[0040] Step A2, outputting a marketing interface based on the search text; the marketing interface includes at least one piece of marketing information;

[0041] Specifically, search engines crawl and index a large amount of web content and return relevant search results based on user input. Search engines usually sort and rank search results based on a variety of factors, such as web page quality, keyword matching, user behavior, etc., to provide search results that best meet user needs.

[0042] Step A3, responding to the user's request to enter the target marketing information, collecting the user's address information and the promotion keywords of the target marketing information;

[0043] Specifically, for multiple search results, the user chooses to enter a certain result and uses the result as the target marketing information. When the user request reaches the server's gateway, such as nginx (a high-performance HTTP and reverse proxy web server), the nginx $remote_address (a variable in the nginx configuration file, used to obtain the client's IP address) variable can be parsed to obtain the requester's (i.e., user) IP. Then put this IP in the request header and forward it to the server; 1.2 After the gateway nginx proxy forwards to the server, the gateway reverse proxy will also forward the business keywords in the request to the server, and the server can get the business keywords.

[0044] Step A4: Use the search text, user address information and promotion keywords as the user's search information. The user's search information includes: the text input by the user, the user's address information, and the information of pictures and words in the web page.

[0045] Through the above method, users do not need to perform cumbersome operations or fill in a large amount of information, which improves the user's experience of browsing marketing web pages and reduces the acquisition of malicious or invalid information.

[0046] Step S104, determining at least one target user based on the user address information included in the search information;

[0047] Specifically, after the gateway nginx proxy forwards the request to the server, the server can obtain the IP information from the request header; based on the IP information of the visitor terminal, the IP identification service provider's interface is called to determine one or more industrial and commercial enterprises to which the IP may belong.

[0048] Step S106, querying the target user's corporate information based on a pre-set data system; wherein the corporate information includes: the business tag and industry tag of the enterprise; further, the data system is established through the following steps: crawling corporate information from public web pages; storing the corporate information in a database, and building a data system.

[0049] Specifically, through web page information crawling technologies such as xpath, regular matching, and json parsing, we crawled the corporate information on public web pages and stored it in the database, thus building a big data system for industrial and commercial enterprise contact information. XPath is a language used to navigate and search in XML documents. It can select specific elements and nodes in XML documents through simple expressions; regular matching refers to the process of matching and searching strings using regular expressions; JSON parsing refers to the process of converting a JSON string into a corresponding data structure or object.

[0050] Specifically, crawling the corporate information on public web pages through the above-mentioned technical means includes the following steps B1 to B5:

[0051] Step B1, determine the URL and page structure of the target website, and use a web crawler to obtain the web page content;

[0052] Step B2, using XPath or regular expressions to extract HTML elements or text containing enterprise information;

[0053] Step B3, cleaning and converting the extracted information, such as removing spaces and formatting phone numbers;

[0054] Furthermore, if the webpage provides a JSON data interface, execute step B4 to obtain and parse the JSON data using a JSON parsing library to obtain more abundant enterprise information;

[0055] Step B5, storing the extracted information in a database or file, and performing deduplication and screening to ensure the accuracy and completeness of the data.

[0056] Furthermore, the captured enterprise information is stored in the database, and a big data system of industrial and commercial enterprise contact information is constructed. Among them, enterprise information includes the business label and industry label of the enterprise; among them, the business label refers to the specific activities or services engaged in by an enterprise, such as sales, production, research and development, marketing, etc.; the industry label refers to a group of related enterprises or organizations that engage in similar or related business activities and share some similar characteristics and rules. For example, IT industry, financial industry, education industry, healthcare industry, etc.

[0057] Based on the at least one enterprise acquired in step S104, the corresponding business tag and industry tag are queried.

[0058] Step S108, determining the similarity between the enterprise information and the search information based on a preset matching model;

[0059] Specifically, the text input by the user in the search information, the information of the pictures and text in the web page clicked by the user, and the business tags and industry tags of the enterprise are input into a pre-set matching model to calculate the similarity, wherein the matching model can be a neural network model, or a decision tree model, support vector machine model, random forest model, naive Bayes model, K nearest neighbor model, etc. having the same function as the neural network model.

[0060] Step S110: taking target users whose similarity is greater than a preset similarity threshold as recommended users.

[0061] Specifically, a similarity threshold is preset, and enterprises corresponding to similarities greater than the threshold are used as recommended users.

[0062] Furthermore, the enterprise information also includes: contact information; after the step of taking the target user whose similarity is greater than a preset similarity threshold as a recommended user, the method also includes: querying the contact information of the recommended user based on a preset data system.

[0063] For example, the marketing party first integrates a JavaScript that automatically sends a request to the server in the marketing webpage of the toB business field that needs to be released. When a visitor visits the marketing webpage, clicks on or visits the image or text area in the marketing webpage, the visitor terminal will automatically send an access request to the server through js. The server can parse the IP address and business keywords of the visitor terminal from the access request.

[0064] Specifically, when the visitor request reaches the server's gateway, such as nginx, the ip of the requester (i.e. the visitor) can be parsed through nginx's $remote_address variable. Then this ip is put in the request header and forwarded to the server. After the gateway nginx proxy forwards it to the server, the server can get the ip information from the request header. At the same time, the gateway reverse proxy will also forward the business keywords in the request to the server, and the server can get the business keywords.

[0065] Furthermore, based on the IP information of the visitor's terminal, the IP identification service provider's interface is called to determine one or more industrial and commercial enterprises that the IP may belong to. Then, based on the business tags and industry tags of these industrial and commercial enterprises, matching analysis is performed with the visitor's business keywords and the promotion keywords of the marketing webpage, and finally the industrial and commercial enterprise information that the visitor may belong to is filtered out;

[0066] Specifically, assuming that the IP of the visitor terminal is 220.248.24.188, the IP identification service provider's interface identifies that the IP may correspond to three companies A, B, and C. Through our industrial and commercial enterprise big data system, we can identify the business and industry labels of the three companies A, B, and C as follows: A: furniture production, manufacturing; B: mobile phone manufacturers, electronic products; C: computer manufacturers, electronic products. Assume that the promotion keywords of the marketing webpage are electronics and electrical accessories; assume that the visitor business keywords identified in 1.2 are computer cooling fans and batteries. Based on 2.2 and 2.3, through the text similarity analysis of the business and industry labels of the three companies and the promotion keywords and visitor business keywords, a text similarity value and ranking are obtained. The final similarity score and ranking are: C (0.91)> B (0.83)> A (0.21). Set a threshold for the text similarity score to remove companies with a score below 0.6, and finally determine that the visitor's company may be C or B.

[0067] Furthermore, based on the company to which the visitor belongs, our industrial and commercial enterprise contact information big data system can identify the contact information of the company to which the visitor belongs. The marketer can use this contact information to proactively follow up and improve the conversion rate of potential customers.

[0068] Specifically, we use web page information crawling technologies such as xpath, regular matching, and json parsing to crawl the contact information of enterprises that are publicly displayed on the web page, store it in the database, and build a big data system for industrial and commercial enterprise contact information. According to the enterprise name, the contact information of the corresponding enterprise can be queried in the contact information big data system.

[0069] The embodiment of the present invention provides a business recommendation method, which includes: responding to a user's search request, obtaining the user's search information through a preset collection program; determining at least one target user based on the user address information included in the search information; querying the target user's corporate information based on a preset data system; wherein the corporate information includes: the business label and industry label of the enterprise; determining the similarity between the corporate information and the search information based on a preset matching model; using the target user whose similarity is greater than a preset similarity threshold as a recommended user; actively obtaining the user's public information, determining the user's identity based on the public information, and delivering targeted advertisements. This method does not require the user to fill in information, thereby improving the user's experience of browsing marketing web pages, and at the same time can reduce the acquisition of malicious or invalid information, reduce the marketing party's waste of resources for invalid follow-up, and further, in the case where the user does not actively leave contact information, the user can also be actively contacted for follow-up, thereby improving the customer conversion rate.

[0070] Embodiment 2

[0071] Based on the above embodiment, the present invention provides another matching model training method. Figure 2 A flowchart of a matching model training method provided by an embodiment of the present invention includes the following steps:

[0072] Step S202, determining a training set and a validation set;

[0073] Specifically, both the training set and the validation set include the business label, industry label, search text corresponding to the enterprise, and promotion keywords; one enterprise corresponds to one business label, one industry label, and one promotion keyword, and one enterprise corresponds to multiple search texts;

[0074] For example, the industry label corresponding to Apple Inc. may be electronic manufacturing, and the business labels may be computers, communications, semiconductors, consumer electronics, etc. The corresponding search labels may be Apple, Apple, iPhone4, etc. Different companies usually correspond to many business labels, and may also correspond to multiple industry labels. These information sets are combined into text sets as training sets and verification sets.

[0075] Step S204, inputting the training set into the basic model for model training;

[0076] Specifically, the basic model refers to a simple model, usually with fewer parameters and a simpler structure, which is used for preliminary exploration and testing of problem solving. Inputting the training set into the basic model for model training is a machine learning method. The training set usually contains multiple samples and their corresponding labels or outputs. The model learns and optimizes the training set to obtain parameters and function forms suitable for processing the problem.

[0077] Normally, when a certain number of iterations have been completed, or when the performance indicators of the model reach the preset standards after a certain iteration, the model training is completed, and the trained model needs to be verified to verify whether it has converged.

[0078] Step S206, judging whether the trained basic model has converged based on the verification set;

[0079] Step S208: if converged, the trained basic model is used as the matching model;

[0080] If the performance indicators of the model on the validation set (such as accuracy, F1 value, etc.) no longer improve or begin to decline, and the performance difference between the training set and the validation set is small, then the model can be considered to have converged or is close to convergence. At this time, model training can be stopped to avoid overfitting and waste of computing resources.

[0081] The method of judging whether the model has converged based on the validation set has the following advantages: it can timely detect the generalization ability and performance of the model and avoid overfitting; it can timely adjust and optimize the model parameters at different training stages; it can improve the stability and reliability of the model.

[0082] Step S210, if it does not converge, input the training set into the basic model for training until the basic model converges;

[0083] The above method provided by the embodiment of the present invention can establish a neural network model to calculate the matching degree, handle nonlinear problems through the connection and activation function between multiple layers of neurons, adaptively adjust network parameters and structure to adapt to different data distributions and task requirements, have strong fault tolerance for noise, missing and interference of input data, can effectively handle data anomalies and changes, and have strong expressiveness, adaptability and robustness.

[0084] Embodiment 3

[0085] Corresponding to the above method embodiment, the present invention provides a service recommendation device, see Figure 3 The structure diagram of a service recommendation device provided by an embodiment of the present invention is shown, and the service recommendation device includes:

[0086] The search information collection module 310 is used to respond to the user's search request and obtain the user's search information through a preset collection program.

[0087] The target user determination module 320 is used to determine at least one target user based on the user address information included in the search information.

[0088] The enterprise information acquisition module 330 is used to query the enterprise information of the target user based on a pre-set data system; wherein the enterprise information includes: the business label and industry label of the enterprise.

[0089] The similarity determination module 340 is used to determine the similarity between the enterprise information and the search information based on a preset matching model.

[0090] The recommended user determination module 350 is used to select target users whose similarity is greater than a preset similarity threshold as recommended users.

[0091] In some preferred embodiments of the present invention, the search information collection module 310 is used to respond to the user's search request and collect the search text input by the user; output a marketing interface based on the search text; the marketing interface includes at least one marketing information; respond to the user's request to enter the target marketing information, collect the user's address information and the promotional keywords of the target marketing information; use the search text, user address information and promotional keywords as the user's search information.

[0092] In some preferred embodiments of the present invention, the enterprise information acquisition module 330 is also used to query the contact information of the recommended user based on a preset data system.

[0093] In some preferred embodiments of the present invention, the business recommendation device further includes: a data system building module for capturing enterprise information from public web pages; storing the enterprise information in a database to build a data system.

[0094] In some preferred embodiments of the present invention, the business recommendation device also includes: a matching model establishment module, which is used to determine a training set and a verification set; both the training set and the verification set include the enterprise's business label, industry label, the enterprise's corresponding search text and promotion keywords; wherein, one enterprise corresponds to one business label, one industry label and one promotion keyword, and one enterprise corresponds to multiple search texts; the matching model is trained based on the training set and the verification set.

[0095] In some preferred embodiments of the present invention, a matching model establishment module is used to input the training set into the basic model for model training; determine whether the trained basic model converges based on the verification set; if converged, use the trained basic model as the matching model; if not converged, input the training set into the basic model for training until the basic model converges.

[0096] The embodiment of the present invention provides a business recommendation device, which includes: a search information collection module, which is used to respond to a user's search request and obtain the user's search information through a preset collection program; a target user determination module, which is used to determine at least one target user based on the user address information included in the search information; an enterprise information acquisition module, which is used to query the enterprise information of the target user based on a preset data system; wherein the enterprise information includes: the business label and industry label of the enterprise; a similarity determination module, which is used to determine the similarity between the enterprise information and the search information based on a preset matching model; a recommended user determination module, which is used to take the target user whose similarity is greater than a preset similarity threshold as a recommended user; by actively obtaining the user's public information, determining the user's identity based on the public information, and delivering targeted advertisements, the method does not require the user to fill in information, improves the user's experience of browsing marketing web pages, and can reduce the acquisition of malicious or invalid information, reduce the marketing party's waste of resources for invalid follow-up, and further, in the case where the user does not actively leave contact information, the user can be actively contacted for follow-up, thereby improving the customer conversion rate.

[0097] Embodiment 4

[0098] The embodiment of the present invention also provides an electronic device for executing the above service recommendation method; see Figure 4 The illustrated embodiment of the present invention provides a structural diagram of an electronic device, which includes a memory 400 and a processor 401, wherein the memory 400 is used to store one or more computer instructions, and the one or more computer instructions are executed by the processor 401 to implement the above-mentioned business recommendation method.

[0099] Further, Figure 4 The electronic device shown further includes a bus 402 and a communication interface 403 , and the processor 401 , the communication interface 403 and the memory 400 are connected via the bus 402 .

[0100] The memory 400 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 403 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used. The bus 402 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0101] The processor 401 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 401. The above processor 401 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiment of the present invention can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module may be located in a storage medium mature in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 400, and the processor 401 reads the information in the memory 400 and completes the steps of the method of the above embodiment in combination with its hardware.

[0102] An embodiment of the present invention further provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the above-mentioned business recommendation method. The specific implementation can be found in the method embodiment, which will not be repeated here.

[0103] The computer program product of the business recommendation method, device and electronic device provided in the embodiments of the present invention includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the method in the previous method embodiment. The specific implementation can be found in the method embodiment and will not be repeated here.

[0104] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system and / or device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0105] In addition, in the description of the embodiments of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0106] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0107] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A business recommendation method, characterized in that: The service recommendation method comprises: Responding to a user's search request, obtaining the user's search information through a pre-set collection program; Determine at least one target user based on the user address information included in the search information; Querying the target user's enterprise information based on a pre-set data system; wherein the enterprise information includes: the business label and industry label of the enterprise; Determine the similarity between the enterprise information and the search information based on a preset matching model; The target users whose similarity is greater than a preset similarity threshold are taken as recommended users.

2. The service recommendation method according to claim 1, characterized in that: In response to a user's search request, the step of obtaining the user's search information through a preset collection program includes: Respond to the user's search request and collect the search text entered by the user; Outputting a marketing interface based on the search text; the marketing interface includes at least one piece of marketing information; In response to the user's request to access target marketing information, collecting the user's address information and promotional keywords of the target marketing information; The search text, the user address information and the promotion keyword are used as the user's search information.

3. The service recommendation method according to claim 1, characterized in that: The enterprise information also includes: contact information; After the step of taking the target user whose similarity is greater than a preset similarity threshold as a recommended user, the method further includes: The contact information of the recommended user is systematically queried based on the preset data.

4. The service recommendation method according to any one of claims 1 to 3, characterized in that: The data system is established through the following steps: Crawl corporate information from public web pages; The enterprise information is stored in a database to construct the data system.

5. The service recommendation method according to claim 1, characterized in that: The matching model is established by the following steps: Determine a training set and a validation set; the training set and the validation set both include the business label, the industry label, the search text corresponding to the enterprise, and the promotion keyword; wherein one enterprise corresponds to one business label, one industry label, and one promotion keyword, and one enterprise corresponds to multiple search texts; The matching model is trained based on the training set and the validation set.

6. The service recommendation method according to claim 5, characterized in that: The step of training the matching model based on the training set and the validation set comprises: Inputting the training set into a basic model for model training; Determining whether the basic model that has completed training has converged based on the verification set; If convergence occurs, the basic model that has completed training is used as the matching model; If it does not converge, the training set is input into the basic model for training until the basic model converges.

7. A business recommendation device, characterized in that: The business recommendation device comprises: A search information collection module, used to respond to a user's search request and obtain the user's search information through a preset collection program; a target user determination module, configured to determine at least one target user based on the user address information included in the search information; An enterprise information acquisition module is used to query the enterprise information of the target user based on a pre-set data system; wherein the enterprise information includes: business tags and industry tags of the enterprise; A similarity determination module, used to determine the similarity between the enterprise information and the search information based on a preset matching model; The recommended user determination module is used to select the target user whose similarity is greater than a preset similarity threshold as a recommended user.

8. The service recommendation device according to claim 7, characterized in that: A search information collection module, used to respond to a user's search request and collect a search text input by the user; output a marketing interface based on the search text; the marketing interface includes at least one piece of marketing information; In response to the user's request to enter the target marketing information, the user's address information and the promotion keywords of the target marketing information are collected; and the search text, the user's address information and the promotion keywords are used as the user's search information.

9. An electronic device, characterized in that: It comprises a processor and a memory, wherein the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement the business recommendation method according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are called and executed by the processor, the computer-executable instructions prompt the processor to implement the business recommendation method described in any one of claims 1 to 6.

Images