An intelligent consulting service method

Abstract

The present invention relates to the field of communication technologies, and specifically discloses an intelligent consultation service method, including the following: S1 Establish a communication window between the server side and the enterprise side, collect the characters sent by the server side in the communication window during the communication process and perform keyword matching with a pre-set trigger word library. If the matching is successful, establish an identification label for conditional matching, then collect the characters sent by the enterprise side in the communication window as a sequence to be processed, and then collect the characters sent by the server side in the communication window and perform keyword matching with an ending word library. If the matching is successful, establish a unique mapping relationship between the sequence to be processed and the identification label, and aggregate several mapping relationships into a demand matching library; S2 After selecting and confirming the corresponding relationship between the candidate side and the enterprise side on the server side, establish a communication window between the server side and the candidate side. It can solve the problem that when a headhunting company communicates with a candidate, it is easy to miss matching conditions due to human error.

Description

Technical Field

[0001] The present invention relates to the field of communication technologies, and particularly to an intelligent consulting service method. Background Art

[0002] With the development of the Internet, more and more job seekers tend to obtain recruitment information on recruitment websites, and enterprises with recruitment intentions are also more willing to post recruitment requirements on recruitment websites. As online recruitment gradually replaces offline recruitment as the most popular recruitment method, the problems existing in online recruitment have gradually emerged in everyone's vision. Specifically, currently, most job recommendation systems generally rely on technologies such as retrieval, collaborative filtering, or timed push to recommend positions to job seekers. This method not only fails to respond in a timely manner to the latest job search trends of job seekers but also performs poorly in terms of personalization and accurate recommendation. This makes it difficult for some job seekers without precise job search goals to obtain desired job recruitment information through existing job recommendation systems. It is also difficult for some enterprises with precise talent needs to invite desired talents to join through existing job recommendation systems.

[0003] Therefore, headhunting companies (commonly known as executive search agencies) have also achieved significant development in recent years as a supplement to online recruitment / job hunting. Starting from the most primitive point-to-point communication, they have now gradually developed into communicating through online means. However, compared with ordinary recruitment websites, there are still significant differences. The main reason is that recruitment websites mainly play an intermediary role, may charge both enterprises and individuals, and achieve relatively low-end talent recruitment work. Headhunting companies are organizations that search for senior management talents and key technical position talents for organizations (enterprises or demand parties). The recruitment organization pays the corresponding commissions required for searching and recommending candidates. The advantages are that they can provide professional and targeted services, have high confidentiality, and save time. Headhunting companies need to provide consulting services such as talent evaluation, investigation, and assistance in communication.

[0004] Especially in terms of consulting services, headhunting companies often need to arrange dedicated personnel to communicate with enterprises (demand parties) to clarify the needs. Enterprises (demand parties) may not be able to accurately express their own needs and require full guidance from the dedicated personnel of headhunting companies. Moreover, this process often requires multiple communications. After the headhunting company clarifies the needs, it then selects from the talent pool it has mastered. After the selection is completed, it conducts multiple communications with specific candidates. In the above process, all are point-to-point communications. The needs put forward by enterprises are usually relatively complex. When headhunting companies communicate with candidates, there are often situations where matching conditions are omitted, resulting in the selected candidates not satisfying the enterprises. Therefore, in view of the problem that headhunting companies are prone to omitting matching conditions due to human errors when communicating with candidates, there is an urgent need for an intelligent consulting service method. Summary of the Invention

[0005] The present invention provides an intelligent consulting service method, which can solve the problem that when headhunting companies communicate with candidates, matching conditions are easily omitted due to human errors.

[0006] To solve the above technical problems, the present application provides the following technical solutions:

[0007] An intelligent consulting service method includes the following:

[0008] S1: Establish a communication window between the server and the enterprise side, collect the characters sent by the server in the communication window during the communication process and perform keyword matching with a pre-set trigger word library. If the matching is successful, establish an identification label for condition matching. Then collect the characters sent by the enterprise side in the communication window as a sequence to be processed. Then collect the characters sent by the server in the communication window and perform keyword matching with a completion word library. If the matching is successful, establish a unique mapping relationship between the sequence to be processed and the identification label, and aggregate several mapping relationships into a demand matching library;

[0009] S2: After selecting and confirming the corresponding relationship between the candidate side and the enterprise side on the server, establish a communication window between the server and the candidate side, collect the characters sent by the server in the communication window during the communication process and perform keyword matching with a pre-set trigger word library. If the matching is successful, wake up the demand matching library and the corresponding identification label, and collect the characters sent by the candidate side in the communication window, and compare them with the sequence to be processed corresponding to the identification label according to the comparison rules;

[0010] S3: If the comparison is passed, process the identification label as a passed sequence; if the comparison fails, process the label as a failed sequence; then bind the passed sequence and the failed sequence to the candidate side and push them to the server. After the server confirms, when the enterprise side logs in next time, push them to the enterprise side.

[0011] The principle and beneficial effects of the basic solution are as follows: Establishing a communication window between the server and the enterprise side actually mainly refers to the interface of the server. Then the server collects the characters in the communication window during the communication process and performs keyword matching with a pre-set trigger word library. That is, if the server actively asks for requirements during the communication between the enterprise and the server, after recognizing this keyword, an identification label for condition matching is established. Then the reply from the enterprise side is used as the requirement under this identification label, that is, the sequence to be processed, waiting to be compared with the actual conditions provided by the candidate side.

[0012] Then comes the basically same logic. After establishing a communication window between the server and the candidate side, if the server collects conditions from the candidate side, it will match the keywords in the trigger thesaurus, then collect information again, and compare it with the requirements under the recognition label to achieve the purpose of checking the candidate's conditions. The above method can make the collection of requirements (enterprise side) and candidate conditions more convenient, without the need to fill in special forms (to complete the collection of structured data), and the whole process is more natural, which can improve the communication experience between the enterprise and the candidate. At the same time, for the server side, it can reduce the workload of staff and avoid the situation of missing or misrecording. In addition, it reduces the communication cost under multi-threaded operations, that is, there are two independent server sides, respectively docking with the enterprise and the candidate, which can improve the communication efficiency.

[0013] In S3, it is equivalent to automatically establishing a recognition label after collecting the enterprise's requirements after communicating with the enterprise side. Then, when communicating between the server side and the candidate side, it collects the actual condition information feedback from the candidate side and conducts intelligent matching, which can achieve multi-threaded communication (communication between different server sides), and solves the problem that it is easy to miss matching conditions due to human errors when headhunting companies communicate with candidates.

[0014] Further, the comparison rule is to define category attributes for the recognition label. The category attributes include general attributes and hierarchical attributes. The general attributes include several mutually equal sub-attributes, and the hierarchical attributes include sub-levels arranged in order. Then, the to-be-processed sequence and the characters sent by the candidate side in the collected communication window are respectively compared with the category attributes to determine the association between the to-be-processed sequence and the characters sent by the candidate side in the collected communication window with the sub-attributes or sub-levels, and obtain whether the characters sent by the candidate side in the collected communication window meet the requirement information of the to-be-processed sequence.

[0015] Such a method can accurately identify various requirements of general attributes and hierarchical attributes.

[0016] Further, it also includes S4, which collects the characters in the communication window between the server side and the candidate side and conducts keyword matching with the pre-set closing remarks thesaurus. If the matching is successful, it judges whether the recognition label has been processed. If it has been processed, it is executed when receiving the communication window closing instruction. If it has not been processed, a prompt window for uncompleted processing will pop up when receiving the communication window closing instruction.

[0017] Such a method can avoid the discontinuity of work caused by accidentally closing the window.

[0018] Further, in the above S3, the unprocessed recognition label is processed as a progress gray bar. If it fails to pass the comparison, the progress gray bar is filled with a progress red bar. If it passes the comparison, the progress gray bar is filled with a progress green bar.

[0019] This way can be more prominent and convenient for users to use.

[0020] Furthermore, the communication windows are all display interfaces of the server.

[0021] This way can reduce the development cost.

[0022] Furthermore, it also includes S5. Before the server sends a completed message, when the server receives a new message from the enterprise side or the candidate side and then receives a message sending instruction, it sends the message. If it receives a message sending instruction again within the preset time, it switches the communication window of the server to the communication window of the new message. If the characters in the current communication window match the pre-set closing word library successfully, it closes the current communication window and then makes the switch.

[0023] This way can facilitate the user's operation after the end, facilitate switching or closing, save the user's time, and improve work and communication efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a logic block diagram of Embodiment 1 of an intelligent consulting service method. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0025] The following is a more detailed description through specific embodiments:

[0026] Embodiment 1

[0027] An intelligent consulting service method in this embodiment (as Figure 1 described), includes the following content:

[0028] S1 Establish a communication window between the server and the enterprise side, collect the characters sent by the server in the communication window during the communication process and perform keyword matching with the pre-set trigger word library. If the matching is successful, establish an identification label for conditional matching. Then collect the characters sent by the enterprise side in the communication window as the sequence to be processed. Then collect the characters sent by the server in the communication window and perform keyword matching with the ending word library. If the matching is successful, establish a unique mapping relationship between the sequence to be processed and the identification label, and aggregate several mapping relationships into a demand matching library;

[0029] S2 After the server selects and confirms the corresponding relationship between the candidate side and the enterprise side, establish a communication window between the server and the candidate side, collect the characters sent by the server in the communication window during the communication process and perform keyword matching with the pre-set trigger word library. If the matching is successful, wake up the demand matching library and the corresponding identification label, collect the characters sent by the candidate side in the communication window, and compare them with the sequence to be processed corresponding to the identification label according to the comparison rules;

[0030] If it passes the comparison, the recognition label is processed as a passed sequence; if it fails the comparison, the label is processed as a failed sequence. Then, the passed sequence and the failed sequence are bound to the candidate side and pushed to the server side. After the server side confirms, it is pushed to the enterprise side when the enterprise side logs in next time.

[0031] S4. Collect the characters in the communication window between the server side and the candidate side and perform keyword matching with the pre-set closing word library. If the matching is successful, determine whether the recognition label has been processed. If it has been processed, execute when receiving the communication window closing instruction. If it has not been processed, pop up an unprocessed completion prompt window when receiving the communication window closing instruction.

[0032] Among them, the comparison rule is to define category attributes for the recognition label. The category attributes include a general attribute and a hierarchical attribute. The general attribute includes several mutually equal sub-attributes, and the hierarchical attribute includes sub-levels arranged in order. Then, the sequence to be processed and the characters sent by the candidate side in the collected communication window are respectively compared with the category attributes to determine the association between the sequence to be processed and the characters sent by the candidate side in the collected communication window and the sub-attributes or sub-levels, so as to obtain whether the characters sent by the candidate side in the collected communication window meet the required information of the sequence to be processed. The communication window is the display interface of the server side.

[0033] In specific use, the staff of the headhunting company establish a communication window between the server side and the enterprise side. The specific communication software can rely on existing instant messaging software to complete (such as WeChat, QQ, DingTalk, etc. In this embodiment, the WeChat communication window is taken as an example). After establishing the communication window, both sides exchange information in the communication window, and the characters that appear in the communication window are the characters for communication. By collecting the characters in the communication process (the characters in the communication window interface of the server side, which does not involve privacy collection and analysis, belongs to the non-private information record analysis in the chat process, and does not involve sensitive privacy information).

[0034] The server side takes the initiative to conduct a demand inquiry. After recognizing this keyword, a recognition label for conditional matching is established. Then, the reply from the enterprise side serves as the requirement under this recognition label, that is, the sequence to be processed, and waits to be compared with the actual conditions provided by the candidate side.

[0035] Then comes the basically same logic. After establishing a communication window between the server and the candidate side, if the server collects conditions from the candidate side, it will match the keywords in the trigger word library, then collect information again, and compare it with the requirements under the recognition tags to achieve the purpose of checking the candidate's conditions. The above method can make the collection of requirements (enterprise side) and candidate conditions more convenient, without the need to fill in special forms (to complete the collection of structured data), and the whole process is more natural, which can improve the communication experience between enterprises and candidates. At the same time, for the server side, it can reduce the workload of staff and avoid the situation of missing or misrecording. In addition, it reduces the communication cost under multi-threaded operations. That is, there are two independent server sides, respectively docking enterprises and candidates, which can improve the communication efficiency.

[0036] In S3, it is equivalent to automatically establishing recognition tags after collecting the requirements of the enterprise after communicating with the enterprise side. Then, when communicating between the server side and the candidate side, it collects the actual condition information feedback from the candidate side and conducts intelligent matching, which can achieve multi-threaded communication (communication between different server sides), solving the problem that it is easy to miss matching conditions due to human errors when headhunting companies communicate with candidates.

[0037] In S4, when both sides tend to end the communication, it can remind the staff on the server side whether they have completed the relevant matters entrusted by the enterprise, especially when the staff on the server side wants to close the communication window.

[0038] The general attribute is that the description of some capabilities is general, but the candidate's ability description is specific, so association is required. For example, the requirements for ability / experience are mostly described in a general way, and the candidate's expression is usually specific, so they can be associated through a binary tree. The level attribute is the specific educational background or certificate requirements. For example, the requirement is a bachelor's degree or above, and the candidate expresses it as a master's degree. Although the keywords are different, they are in line with the educational level.

[0039] Embodiment 2

[0040] The difference between this embodiment and Embodiment 1 is that in this embodiment, in S3, the unprocessed recognition tags are processed as progress grey bars. If the comparison fails, the progress grey bars are filled with progress red bars. If the comparison passes, the progress grey bars are filled with progress green bars.

[0041] When used specifically, it is equivalent to having a progress bar-like prompt above the communication window, which can make it more convenient for users to know the communication progress.

[0042] Embodiment 3

[0043] Compared with the first embodiment, the difference lies only in that it further includes S5. Before the server sends the completed message, when the server receives a new message from the enterprise side or the candidate side and also receives a message sending instruction, it sends this piece of information. If it receives a message sending instruction again within the preset time, it switches the communication window of the server to the communication window of the new message. If the characters in the current communication window match the pre-set closing phrase library successfully, it closes the current communication window before switching.

[0044] In specific use, the existing communication window does not support quick switching and closing, and only operations can be performed through the mouse. The information sending of the communication window is usually by clicking the send button at the lower right of the communication window with the left mouse button or pressing the ENTER key. Usually, the efficient way to send information is to press the ENTER key, but there is no more convenient way to switch the communication window. Therefore, this embodiment can switch to the latest communication window after the ENTER key is double-clicked (the existing instant messaging software will have a list sorting on the left, and it can be achieved by simulating a right mouse click at a fixed coordinate). At the same time, if there is a relevant closing phrase, then the current communication window is closed, which is convenient for users to use and switch.

[0045] The above are only the embodiments of the present invention. The invention is not limited to the fields involved in this embodiment. Common knowledge such as the specific structures and characteristics known to the public in the solution is not described in detail here. Those of ordinary skill in the art know all the common general technical knowledge in the technical field to which the invention belongs before the application date or the priority date, can know all the existing technologies in this field, and have the ability to apply the conventional experimental means before this date. Those of ordinary skill in the art can, under the inspiration given in this application, combine their own abilities to improve and implement this solution. Some typical well-known structures or well-known methods should not become obstacles for those of ordinary skill in the art to implement this application. It should be noted that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can still be made, and these should also be regarded as the protection scope of the present invention, and these will not affect the implementation effect of the present invention and the practicality of the patent. The protection scope required by this application should be based on the content of its claims, and the specific implementation manners and the like recorded in the specification can be used to interpret the content of the claims.

Claims

1. An intelligent consulting service method, characterized in that: It includes the following contents: S1. Establish a communication window between the server and the enterprise side, collect the characters sent by the server in the communication window during the communication process and perform keyword matching with a pre-set trigger word library. If the matching is successful, establish an identification label for conditional matching. Then collect the characters sent by the enterprise side in the communication window as the sequence to be processed. Then collect the characters sent by the server in the communication window and perform keyword matching with the completion word library. If the matching is successful, establish a unique mapping relationship between the sequence to be processed and the identification label, and aggregate several mapping relationships into a demand matching library; S2. After selecting and confirming the corresponding relationship between the candidate side and the enterprise side on the server, establish a communication window between the server and the candidate side, collect the characters sent by the server in the communication window during the communication process and perform keyword matching with a pre-set trigger word library. If the matching is successful, wake up the demand matching library and the corresponding identification label, and collect the characters sent by the candidate side in the communication window, and compare them with the sequence to be processed corresponding to the identification label according to the comparison rule; S3. If the comparison is passed, process the identification label as a passed sequence; if the comparison fails, process the label as a failed sequence; then bind the passed sequence and the failed sequence to the candidate side and push them to the server. After the server confirms, when the enterprise side logs in next time, push them to the enterprise side.

2. An intelligent consulting service method according to claim 1, characterized in that: The comparison rule is to define category attributes for the identification label. The category attributes include a general attribute and a hierarchical attribute. The general attribute includes several mutually equal sub-attributes, and the hierarchical attribute includes sub-levels arranged in order. Then compare the sequence to be processed and the characters sent by the candidate side in the collected communication window with the category attributes respectively to determine the association between the sequence to be processed and the characters sent by the candidate side in the collected communication window and the sub-attributes or sub-levels, and obtain whether the characters sent by the candidate side in the collected communication window meet the demand information of the sequence to be processed.

3. An intelligent consulting service method according to claim 2, characterized in that: It further includes S4, collect the characters in the communication window between the server and the candidate side and perform keyword matching with a pre-set conclusion word library. If the matching is successful, judge whether the identification label has been processed. If it has been processed, execute when receiving the communication window closing instruction. If it has not been processed, pop up an unprocessed completion prompt window when receiving the communication window closing instruction.

4. An intelligent consulting service method according to claim 3, characterized in that: In S3, process the unprocessed identification label as a progress gray bar. If the comparison fails, fill the progress gray bar with a progress red bar. If the comparison is passed, fill the progress gray bar with a progress green bar.

5. An intelligent consulting service method according to claim 4, characterized in that: All the communication windows are the display interfaces of the server.

6. An intelligent consulting service method according to claim 5, characterized in that: It also includes S5. Before the server sends the completed message, when the server receives a new message from the enterprise side or the candidate side and also receives a message sending instruction, it sends the message. If it receives a message sending instruction again within the preset time, it switches the communication window of the server to the communication window of the new message. If the characters in the current communication window match the pre-set closing phrase library successfully, it closes the current communication window and then makes the switch.

Images