Group and position recommendation method and device based on chat tool, equipment and medium

Abstract

The invention discloses a chat tool-based group and position recommendation method and device, equipment and a medium. The method comprises the following steps: creating a plurality of group categories; setting the group attribute of each initial group for a plurality of initial groups created in the chat tool; the group attribute comprises a group attribute name, a target group category to which the group attribute belongs, a matching priority and a matching screening item; according to the matching priority, matching the portrait data of the target user with the group attribute of each initial group in sequence; in the matching process, if the ith initial group is successfully matched and the target user does not join the ith initial group, classifying the ith initial group or a subgroup thereof into a recommendation list; if the target user joins the ith initial group, continuing to match the next matching priority; recommending the group in the recommendation list to the target user; and pushing the target position to the target initial group and / or subgroup successfully matched with the target position. The group recommendation efficiency, the recruitment efficiency and the success rate can be improved.

Description

Technical Field

[0001] The present application relates to the field of big data service technology, and in particular to a chat tool-based group and position recommendation method, device, electronic device, computer-readable storage medium and computer program product. Background Art

[0002] With the continuous development of Internet technology, technical means such as personalized customization and accurate recommendation have gradually matured, enabling enterprises to better utilize their accumulated user data for refined operations. At the same time, users' demand for personalized services and experiences is also growing. The private traffic established by enterprises through some channels (such as social media, WeChat groups, public accounts or APPs, etc.) will become an important means for enterprises to acquire users, retain users, and improve user loyalty. Private traffic will pay more attention to the establishment and maintenance of user relationships, and achieve user growth and commercial realization through refined operations. In the face of a highly competitive market environment, enterprises need to establish their own private traffic pools to reduce user acquisition costs, improve user retention rates, and achieve sustained growth.

[0003] At present, the main way to establish private domain traffic is for operators to actively invite users to join the group. The disadvantage of this method is that for a large number of users, operators need to bear a huge workload and the efficiency is low. There are also some methods that directly display all group chats and users can choose to join them on their own. The disadvantages of this method are: (1) When the number of group chats is large, users may feel overwhelmed and their willingness to join the group is reduced; (2) When the number of group members reaches the upper limit, it is impossible to create a new group in time, resulting in the inability of new members to join; (3) The quality of users joining the group cannot be guaranteed. Summary of the invention

[0004] In view of this, an embodiment of the present application provides a chat tool-based group and position recommendation method, device, electronic device, computer-readable storage medium and computer program product, which are used to solve at least one of the above technical problems.

[0005] In a first aspect, an embodiment of the present application provides a method for recommending groups and positions based on a chat tool, comprising: creating multiple group categories, each group category including a group category name, a position tag combination, and a weight of each position tag in the position tag combination; wherein the position tag combination includes at least one position tag; for multiple initial groups created in the chat tool, setting group attributes of each initial group; wherein the group attributes include a group attribute name, a target group category to which it belongs, a matching priority, and at least one matching filter item, wherein at least one matching filter item corresponds to n position tags in the target group category, and the matching priority is determined based on the weights of the n position tags in the target group category, where n is a positive integer; and in order of matching priority from high to low, the portraits of the target users are sequentially sorted. The data is matched with the group attributes of each initial group; during the matching process, if the i-th initial group is matched successfully and the target user has not joined the i-th initial group, the i-th initial group or its subgroup is included in the recommendation list, where i is a positive integer; if the i-th initial group is matched successfully and the target user has joined the i-th initial group, the portrait data of the target user is matched with the group attributes of the initial group of the next matching priority, until the number of groups in the recommendation list reaches a preset number or all initial groups are matched; the groups in the recommendation list are recommended to the target user; in order of matching priority from high to low, the target positions to be pushed are matched with the group attributes of each initial group in turn, and the target positions are pushed to the target initial group and / or the subgroup of the target initial group that has successfully matched it.

[0006] According to some embodiments of the present application, optionally, the i-th initial group or its subgroup is included in the recommendation list, including: based on the ID of the i-th initial group, calling the interface of the chat tool to query the upper limit of the number of people in the i-th initial group and whether there is a subgroup in the i-th initial group; if the i-th initial group has not reached the upper limit of people, the i-th initial group is included in the recommendation list; if the i-th initial group has reached the upper limit of people and the i-th initial group has no subgroup, a subgroup of the i-th initial group is generated, and the newly generated subgroup of the i-th initial group is included in the recommendation list; if the i-th initial group has reached the upper limit of people and the i-th initial group has a subgroup, and the subgroup has not reached the upper limit of people, the subgroup of the i-th initial group is included in the recommendation list.

[0007] According to some embodiments of the present application, optionally, the position label includes the highest educational level, the name of the school of highest educational level, the year of graduation of the highest educational level, the type label of the highest school, the function, location, job type, nature of company or industry; the matching filter items include the highest educational level, the name of the school of highest educational level, the year of graduation of the highest educational level, the type label of the highest school, the most recent function, the expected function, the function preference, the expected work location, the expected job type, the most recent company nature, the expected industry, the most recent industry or industry preference; the portrait data of the target user includes at least one of the target user's highest educational level, the name of the school of highest educational level, the year of graduation of the highest educational level, the type label of the highest school, the most recent function, the expected function, the function preference, the expected work location, the expected job type, the most recent company nature, the expected industry, the most recent industry and industry preference.

[0008] According to some embodiments of the present application, optionally, the chat tool-based group and position recommendation method also includes: creating a fallback group in the chat tool; setting group attributes of the fallback group, wherein the matching priority in the group attributes of the fallback group is less than the matching priority in the group attributes of each initial group; if the portrait data of the target user fails to match the group attributes of all the initial groups, and the target user has not joined the fallback group, pushing the fallback group to the target user; if the portrait data of the target user fails to match the group attributes of all the initial groups, and the target user has joined the fallback group, not pushing any group to the target user.

[0009] According to some embodiments of the present application, optionally, the target position to be pushed is matched with the group attributes of each initial group in order from high to low matching priority, and the target position is pushed to the target initial group and / or the subgroup of the target initial group that has successfully matched it, including: extracting features from the position data of the target position, and converting the extracted features into a first feature vector; for any j-th initial group, extracting features from the matching filter items in the group attributes of the j-th initial group, and converting the extracted features into a second feature vector, where j is a positive integer; calculating the similarity between the first feature vector and the second feature vector based on a target similarity algorithm or a trained similarity calculation model; when the similarity is greater than or equal to a preset threshold, pushing the target position to the j-th initial group and / or the subgroup of the j-th initial group.

[0010] According to some embodiments of the present application, optionally, the group and position recommendation method based on the chat tool also includes: obtaining a unique identifier corresponding to the group attributes of each initial group; based on the unique identifier, calling the interface of the chat tool to query the IDs of multiple groups associated with the unique identifier; based on the ID of each group, calling the interface of the chat tool to query the dynamic information of each group, and storing the dynamic information of each group, wherein the dynamic information includes at least one of the group members, the number of people who join the group in the target time period, the number of people who leave the group, the number of job pushes and the number of chat items.

[0011] According to some embodiments of the present application, optionally, a preset number of groups in the recommendation list are sorted in order of matching priority from high to low.

[0012] In a second aspect, an embodiment of the present application provides a group and job recommendation device based on a chat tool, including: a creation module, used to create multiple group categories, each group category includes a group category name, a job label combination and a weight of each job label in the job label combination; wherein the job label combination includes at least one job label; a setting module, used to set the group attributes of each initial group created in the chat tool; wherein the group attributes include the group attribute name, the target group category to which it belongs, the matching priority and at least one matching filter item, wherein at least one matching filter item corresponds to n job labels in the target group category, and the matching priority is determined based on the weights of the n job labels in the target group category, where n is a positive integer; a matching module, used to sort the target users in order of matching priority from high to low. The portrait data of the target user is matched with the group attributes of each initial group; during the matching process, if the i-th initial group is matched successfully and the target user has not joined the i-th initial group, the i-th initial group or its subgroup is included in the recommendation list, where i is a positive integer; if the i-th initial group is matched successfully and the target user has joined the i-th initial group, the portrait data of the target user is matched with the group attributes of the initial group of the next matching priority, until the number of groups in the recommendation list reaches a preset number or all initial groups are matched; a recommendation module is used to recommend the groups in the recommendation list to the target user; a push module is used to match the target positions to be pushed with the group attributes of each initial group in order of matching priority from high to low, and push the target positions to the target initial group and / or the subgroup of the target initial group that has successfully matched it.

[0013] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, the steps of the chat tool-based group and position recommendation method as described above are implemented.

[0014] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having computer program instructions stored thereon, and when the computer program instructions are executed by a processor, the steps of the chat tool-based group and position recommendation method as described above are implemented.

[0015] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes computer program instructions. When the computer program instructions are executed by a processor, the steps of the chat tool-based group and job recommendation method as described above are implemented.

[0016] The chat tool-based group and job recommendation method, device, electronic device, computer-readable storage medium and computer program product provided by the embodiments of the present application, on the one hand, by creating multiple group categories and setting group attributes for each initial group, and then matching the target user's portrait data with the group attributes of each initial group, it is possible to achieve automatic matching between the user and the initial group, and to quickly and accurately recommend a group suitable for the target user, which is conducive to improving the user experience, increasing user participation, making group management more efficient, reducing the workload of operators, and improving the efficiency of group recommendation; on the other hand, it is possible to intelligently match the target position to be pushed with the group attributes of each initial group, and push the target position to the target initial group and / or its subgroup that successfully matches it, which is conducive to providing more accurate group position matching services for recruiting companies and improving recruitment efficiency and success rate. On the other hand, by setting the weight of each job label and the matching priority in the group attributes, the target user can be preferentially matched with the group that meets the recruitment needs of the recruiting company, which is conducive to improving the success rate of job recommendation and the success rate of job hunting for the target user. This application integrates group recommendation with job recommendation, realizes user stratification through group division, and implements targeted operations and job recommendation plans for users at different levels, providing job-seeking user groups and recruiting companies with smarter and more efficient group management and recruitment solutions, promoting the development of recruitment business and improving user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following briefly introduces the drawings in the embodiments of the present application.

[0018] Figure 1 A schematic diagram of a system architecture of an embodiment of the present application is shown.

[0019] Figure 2 A flowchart of a chat tool-based group and job recommendation method provided in an embodiment of the present application.

[0020] Figure 3 A diagram of the interface for creating a group category for the Custom Configure Group Category and Group Properties tool.

[0021] Figure 4 A schematic diagram of an interface for setting group properties of an initial group for a custom configuration group category and group property tool.

[0022] Figure 5 Another flowchart of the chat tool-based group and job recommendation method provided in an embodiment of the present application.

[0023] Figure 6 A structural diagram of a chat tool-based group and job recommendation device provided in an embodiment of the present application.

[0024] Figure 7 A schematic diagram of the hardware structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] The principles and spirit of the present application will be described below with reference to several exemplary embodiments. It should be understood that the purpose of providing these embodiments is to make the principles and spirit of the present application clearer and more thorough, so that those skilled in the art can better understand and implement the principles and spirit of the present application. The exemplary embodiments provided herein are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments herein, all other embodiments obtained by ordinary technicians of the art without creative work are within the scope of protection of this application.

[0026] Embodiments of the present application relate to terminal devices and / or servers. Those skilled in the art will appreciate that the embodiments of the present application may be implemented as a system, apparatus, device, method, computer-readable storage medium, or computer program product. Therefore, the present disclosure may be specifically implemented as at least one of the following forms: complete hardware, complete software, or a combination of hardware and software. According to the embodiments of the present application, the present application claims protection for a method, apparatus, electronic device, computer-readable storage medium, and computer program product for group and position recommendations based on a chat tool. Figure 1 A schematic diagram of a system architecture of an embodiment of the present application is shown. Figure 1As shown, the system includes a terminal device 102 and a server 104. Among them, the terminal device 102 may include at least one of the following: a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart TV, various wearable devices, an augmented reality AR device, a virtual reality VR device, etc. A client can be installed on the terminal device 102. For example, the client can be a client that specifically performs a specific function (such as an application app), or a client with multiple application applets (different functions) embedded in it, or a client logged in through a browser. The user can operate on the terminal device 102. For example, the user can open the client installed on the terminal device 102 and input instructions through the client operation, or the user can open the browser installed on the terminal device 102 and input instructions through the browser operation. After the terminal device 102 receives the instruction input by the user, the request information containing the instruction is sent to the server 104. After receiving the request information, the server 104 performs corresponding processing and then returns the processing result information to the terminal device 102. The user instruction is completed through a series of data processing and information interaction.

[0027] In this document, terms such as first, second, third, etc. are only used to distinguish one entity (or operation) from another entity (or operation), but not to require or imply any order or relationship between these entities (or operations).

[0028] Before describing the technical solutions provided by the embodiments of the present application, in order to facilitate the understanding of the embodiments of the present application, the present application first specifically describes the problems existing in the related art:

[0029] With the continuous development of Internet technology, technical means such as personalized customization and accurate recommendation have gradually matured, enabling enterprises to better utilize their accumulated user data for refined operations. At the same time, users' demand for personalized services and experiences is also growing. The private traffic established by enterprises through some channels (such as social media, WeChat groups, public accounts or APPs, etc.) will become an important means for enterprises to acquire users, retain users, and improve user loyalty. Private traffic will pay more attention to the establishment and maintenance of user relationships, and achieve user growth and commercial realization through refined operations. In the face of a highly competitive market environment, enterprises need to establish their own private traffic pools to reduce user acquisition costs, improve user retention rates, and achieve sustained growth.

[0030] At present, the main way to establish private domain traffic is for operators to actively invite users to join the group. The disadvantage of this method is that for a large number of users, operators need to bear a huge workload and the efficiency is low. There are also some methods that directly display all group chats and users can choose to join them on their own. The disadvantages of this method are: (1) When the number of group chats is large, users may feel overwhelmed and their willingness to join the group is reduced; (2) When the number of group members reaches the upper limit, it is impossible to create a new group in time, resulting in the inability of new members to join; (3) The quality of users joining the group cannot be guaranteed.

[0031] In addition, for the recruitment industry, the current job recommendations are inaccurate and have low accuracy. In addition, when recommending jobs, it is usually necessary to recommend different users one by one, which has low recommendation efficiency and poor user experience.

[0032] In view of the above research findings of the inventors, the embodiments of the present application provide a group and position recommendation method, device, electronic device, computer-readable storage medium and computer program product based on a chat tool, which can solve at least one of the above technical problems existing in the related art.

[0033] The following first introduces the group and job recommendation method based on the chat tool provided in the embodiment of the present application.

[0034] Figure 2 A flow chart of a chat tool-based group and job recommendation method provided in an embodiment of the present application. Figure 2 As shown, the chat tool-based group and position recommendation method provided in the embodiment of the present application may include the following steps S201 to S205.

[0035] S201: Create multiple group categories, each of which includes a group category name, a job tag combination, and a weight of each job tag in the job tag combination.

[0036] The group category can be used to group the groups. A group category can be regarded as a large group, and a group attribute can be regarded as a small group. A group category can include or correspond to one or more group attributes, and a group attribute can correspond to one or more initial groups.

[0037] In some embodiments, multiple group categories can be created through a pre-established custom configuration group category and group attribute tool. The custom configuration group category and group attribute tool can be used to custom configure group categories and group attributes according to user needs. Figure 3 A diagram of an interface for creating group categories for the Custom Configuration Group Category and Group Attributes tool. Figure 3As shown in FIG. 1 , each group category may include a group category name, a job tag combination, and a weight of each job tag in the job tag combination. The group category name may be used to distinguish and find the group category. The job tag combination may also be called a dimension combination, which may include at least one job tag. Figure 3 For example, in some examples, the job tag combination may include three different job tags, namely, city, highest education graduation year, and highest education tag. Each job tag may be configured with a weight, for example, the weight corresponding to the city is 10, the weight corresponding to the highest education graduation year is 8, and the weight corresponding to the highest education tag is 3. The weight corresponding to each job tag can be flexibly adjusted according to actual conditions, and this application does not limit this.

[0038] For example, the weight corresponding to each job tag can be flexibly adjusted according to actual recruitment needs. For example, when recruiting, if the city (i.e., the work location) is more important, then the city can be assigned a relatively high weight. If the company type is not very important, then the company type can be assigned a relatively low weight.

[0039] It should be noted that the position tag combination may include a position tag, such as a city, or may include a position tag. The above three position tags are only examples and do not constitute a limitation to this application.

[0040] S202: For multiple initial groups created in the chat tool, set group attributes of each initial group.

[0041] Specifically, multiple groups can be created in the chat tool, and the group created for the first time in the chat tool is called the initial group. When the number of people in the initial group reaches the upper limit, a subgroup of the initial group can be generated through the chat tool.

[0042] In some embodiments, the chat tool may be WeChat for Business, and the group created by the chat tool is WeChat for Business group. Compared with other chat tool groups, WeChat for Business group has some obvious advantages, which are mainly reflected in the following aspects:

[0043] (1) Enterprise customization: It is an office communication tool that can be seamlessly connected with the internal organizational structure, employee information, etc. of the enterprise, and is more suitable for internal communication and collaboration needs of the enterprise.

[0044] (2) Security: It provides a more stringent security control mechanism, including data encryption and identity authentication, which is more suitable for the dissemination and management of sensitive information within the enterprise.

[0045] (3) Management functions: Enterprise WeChat groups support richer management functions, such as group member management, message approval, data statistics, etc., making it easier for enterprise administrators to manage and monitor groups.

[0046] (4) Integration: It can be integrated with other systems within the enterprise, such as OA system (Office Automation System) and CRM system (Customer Relationship Management), to achieve seamless connection of information sharing and business processes and improve work efficiency.

[0047] (5) Professional services: It provides professional customer service support and can customize solutions according to enterprise needs to meet the company's specific communication and collaboration needs.

[0048] Of course, the chat tool may also be other chat tools, and this application does not limit this.

[0049] In some embodiments, after the chat tool creates multiple initial groups, the group attributes of each initial group can be set through the custom configuration group category and group attribute tool. Each initial group has a permanent group active code (referred to as the group active code). When setting the group attributes, the group attributes of each initial group can be directly set through the custom configuration group category and group attribute tool, or the group attributes of the group active code of each initial group can be set through the custom configuration group category and group attribute tool.

[0050] Figure 4 A schematic diagram of an interface for setting the group attributes of an initial group for a custom configuration group category and group attribute tool. Figure 4 As shown, the group attribute may include a group attribute name, a target group category to which it belongs, a matching priority, and at least one matching filter item. The group attribute name may be used to distinguish and find the corresponding group attribute. The matching priority may be used to set the order of matching with the target user's portrait data. The higher the priority, the earlier the target user's portrait data is matched. The matching filter item may be used to match with the target user's portrait data. In some examples, if the target user's portrait data meets the requirements of at least one matching filter item, the match is considered successful; otherwise, the match is considered failed.

[0051] In the group attributes, one or more matching filter items can be set. The matching filter items in the group attributes can be determined according to the position labels in the target group category to which it belongs, or the matching filter items can be regarded as the refinement of the position labels. For example, taking the position label as the city and there is only one matching filter item, the matching filter item can be a refinement of the city, such as City A. If the target user's workplace is also City A, the match is considered successful. Taking the position label as the highest educational level label and there is only one matching filter item as an example, the matching filter item can be a refinement of the highest educational level label, such as an ordinary undergraduate college. If the target user's graduate school is also an ordinary undergraduate college, the match is considered successful.

[0052] When multiple matching filter items are set in the group attributes, the multiple matching filter items can be connected with "and", and "and" means that they are met at the same time. That is, the target user's portrait data needs to meet the requirements of multiple matching filter items before it is considered a successful match. Multiple matching filter items can be connected with "or", and "or" means that one of them is met. That is, as long as the target user's portrait data meets the requirements of one of the matching filter items, it is considered a successful match. "And" and "or" can be flexibly selected and matched, and this application does not limit this.

[0053] At least one matching filter item in the group attribute may correspond to n job tags in the target group category, that is, it may be a refinement of the n job tags in the target group category, where n is a positive integer. Accordingly, the matching priority in the group attribute may be determined based on the weights of the n job tags in the target group category. For example, in some examples, the matching priority in the group attribute may be the sum of the weights of the n job tags in the target group category.

[0054] For example, if the target group category includes three different job tags, namely city, highest degree graduation year, and highest degree graduation tag, n can be equal to 1, 2, or 3. Assuming n = 2, corresponding to the two job tags of city and highest degree graduation year, the group attribute can include two matching filter items, namely, city is city A, and highest degree graduation year is 2024. If the weight corresponding to the city is 10 and the weight corresponding to the highest degree graduation year is 8, the matching priority in the group attribute can be 18.

[0055] In this way, through the pre-established custom configuration group category and group attribute tool, operators can easily customize the required group category and group attribute.

[0056] It should be noted that the group attributes of different initial groups can be different or the same. That is, one group attribute can correspond to one initial group or multiple initial groups. For example, taking the two matching filter items whose group attributes include the city A and the highest academic degree graduation year 2024 as an example, the initial groups corresponding to this group attribute may include "2024 A City Fresh Graduates Group", "2024 A City Software Development Fresh Graduates Group", "A City Internship School Recruitment Group" and "A City Part-time Group".

[0057] S203: Match the target user's portrait data with the group attributes of each initial group in order from high to low matching priority.

[0058] During the matching process, for any i-th initial group, when the number of groups in the recommendation list does not reach the preset number, if the i-th initial group is matched successfully and the target user has not joined the i-th initial group before, the i-th initial group or its subgroup will be included in the recommendation list, where i is a positive integer.

[0059] According to the settings of the matching filter items "and" and "or" in the group attributes, if the portrait data of the target user meets the requirements of some or all matching filter items, the i-th initial group is considered to be matched successfully. Otherwise, the i-th initial group is considered to have failed to match. After determining that the i-th initial group is matched successfully, it can be checked whether the target user has joined the i-th initial group before. If the target user has not joined the i-th initial group before, the i-th initial group or its subgroup can be included in the recommendation list. The subgroup of the i-th initial group can be automatically generated through the chat tool when the i-th initial group has reached the upper limit of the number of people. The group attributes of the subgroup of the i-th initial group can be the same as the group attributes of the i-th initial group.

[0060] If the i-th initial group is matched successfully, and the target user has previously joined the i-th initial group, the target user's portrait data will continue to be matched with the group attributes of the initial group of the next matching priority until the number of groups in the recommendation list reaches the preset number or all initial groups are matched. The size of the preset number can be flexibly adjusted according to actual conditions, and this application does not limit this. For example, the preset number can be equal to 3, 5 or other values.

[0061] S204: Recommend the groups in the recommendation list to the target user.

[0062] After obtaining the recommendation list, the initial group and / or subgroup in the recommendation list may be recommended to the target user through a chat tool, a recruitment platform or other communication methods, so that the target user can join the recommended initial group and / or subgroup.

[0063] S205: Match the target positions to be pushed with the group attributes of each initial group in order from high to low matching priorities, and push the target positions to the successfully matched target initial group and / or subgroups of the target initial group.

[0064] In S205, the target positions to be pushed can be matched with the group attributes of each initial group in order of matching priority from high to low. Then, the target position is pushed to the target initial group and / or the subgroup of the target initial group that successfully matches it, so as to achieve accurate recommendation of the target position.

[0065] The chat tool-based group and job recommendation method provided by the embodiment of the present application, on the one hand, by creating multiple group categories and setting group attributes for each initial group, and then matching the target user's portrait data with the group attributes of each initial group, it is possible to achieve automatic matching between the user and the initial group, and the target user can quickly and accurately recommend a group suitable for him, which is conducive to improving user experience, increasing user participation, making group management more efficient, reducing the workload of operators, and improving the efficiency of group recommendation; on the other hand, it is possible to intelligently match the target position to be pushed with the group attributes of each initial group, and push the target position to the target initial group and / or its subgroup that successfully matches it, which is conducive to providing more accurate group position matching services for recruiting companies and improving recruitment efficiency and success rate. On the other hand, by setting the weight of each job label and the matching priority in the group attributes, the target user can be preferentially matched with the group that meets the recruitment needs of the recruiting company, which is conducive to improving the success rate of job recommendation and the success rate of job hunting for the target user. This application integrates group recommendation with job recommendation, realizes user stratification through group division, and implements targeted operations and job recommendation plans for users at different levels, providing job-seeking user groups and recruiting companies with smarter and more efficient group management and recruitment solutions, promoting the development of recruitment business and improving user experience.

[0066] According to some embodiments of the present application, optionally, in S203, the i-th initial group or its subgroup is included in the recommendation list, which may include the following steps 1 to 4.

[0067] Step 1: Based on the ID of the i-th initial group, call the chat tool interface to query the upper limit of the number of people in the i-th initial group and whether there is a subgroup in the i-th initial group.

[0068] Specifically, based on the ID of the ith initial group, the interface of the chat tool can be called to query the current number of people in the ith initial group, the upper limit of the number of people in the ith initial group, and whether there are subgroups in the ith initial group.

[0069] Step 2: If the i-th initial group has not reached the upper limit of the number of people, the i-th initial group will be included in the recommendation list.

[0070] After querying, if the current number of people in the i-th initial group has not reached the upper limit, it means that the i-th initial group is not full and new users can still join, then the i-th initial group can be included in the recommendation list.

[0071] Step 3: If the i-th initial group has reached the upper limit of its number of members and the i-th initial group has no subgroup, a subgroup of the i-th initial group is generated and the newly generated subgroup of the i-th initial group is included in the recommendation list.

[0072] If the current number of people in the i-th initial group has reached the upper limit, it means that the i-th initial group is full. At this time, if the i-th initial group has no subgroup, a subgroup of the i-th initial group can be generated, and the newly generated subgroup of the i-th initial group can be included in the recommendation list, so that the target user can join the newly generated subgroup of the i-th initial group.

[0073] Step 4: If the i-th initial group has reached the upper limit of its population, and the i-th initial group has a subgroup that has not reached the upper limit of its population, then the subgroup of the i-th initial group is included in the recommendation list.

[0074] If the current number of people in the i-th initial group has reached the upper limit, it means that the i-th initial group is full. At this time, if the i-th initial group has a subgroup and the subgroup has not reached the upper limit, the subgroup of the i-th initial group can be included in the recommendation list.

[0075] In this way, after the i-th initial group is successfully matched, if the current number of people in the i-th initial group has reached the upper limit, a subgroup of the i-th initial group can be automatically created, and a subgroup of the i-th initial group suitable for the target user can be recommended, so that the appropriate group chat can be intelligently selected based on the matching results of the target user's portrait data and group attributes, and subgroups can be dynamically created according to needs, ensuring that users can quickly and accurately join groups that meet their interests and needs. Such a strategy can improve user experience, increase user participation, and ensure efficient group management.

[0076] According to some embodiments of the present application, optionally, the position tag may include the highest educational level, the name of the school of the highest educational level, the graduation year of the highest educational level, the type tag of the highest school, the function, the location, the type of work, the nature of the company or the industry. The position tag combination may include at least one of the above position tags. Exemplarily, the highest educational level may be divided into junior college, undergraduate, master's and doctoral degrees, etc. The job type may be divided into full-time, internship and part-time, etc.

[0077] Accordingly, the matching filter items may include the highest education level, the name of the school of the highest education, the graduation year of the highest education, the type label of the highest school, the most recent function, the expected function, the function preference, the expected work location, the expected job type, the nature of the most recent company, the expected industry, the most recent industry, or the industry preference. Among them, a position label can be subdivided into one or more matching filter items. For example, the position label "function" can be subdivided into three matching filter items: the most recent function, the expected function, and the function preference, and the position label "industry" can be subdivided into three matching filter items: the expected industry, the most recent industry, and the industry preference. For example, the matching filter items may be that the highest education level is a bachelor's degree, the name of the school of the highest education is xxx University, the graduation year of the highest education is 2024, etc.

[0078] Accordingly, the portrait data of the target user may include at least one of the target user's highest educational level, the name of the school of highest educational level, the graduation year of the highest educational level, the type label of the highest school, the most recent function, the expected function, the function preference, the expected work location, the expected job type, the nature of the most recent company, the expected industry, the most recent industry and the industry preference.

[0079] For any i-th initial group, according to the setting of the matching filter items in the group attributes, if the target user's profile data meets the requirements of some or all matching filter items, the i-th initial group is considered to be matched successfully. Otherwise, the i-th initial group is considered to have failed to match.

[0080] Figure 5 Another flow chart of the chat tool-based group and job recommendation method provided in the embodiment of the present application. Figure 5 As shown, according to some embodiments of the present application, optionally, the chat tool-based group and position recommendation method provided in the embodiments of the present application may also include the following steps S501 to S504.

[0081] S501: Create a backup group in the chat tool.

[0082] In the chat tool, you can create a backup group, which is a backup group used for group recommendation. For example, if the target user's profile data fails to match the group attributes of all initial groups, you can recommend a backup group to the target user to improve the user experience.

[0083] S502: Set the group attributes of the backup group.

[0084] In some embodiments, for example, the group attributes of the catch-all group can be set by customizing the group category and group attribute tool. Among them, the matching priority in the group attributes of the catch-all group can be lower than the matching priority in the group attributes of each initial group, so that the portrait data of the target user is preferentially matched with each initial group. No matching filter items may be set in the group attributes of the catch-all group. Of course, a small number of matching filter items may also be set, such as less than 3 matching filter items.

[0085] S503: If the target user's portrait data fails to match the group attributes of all initial groups, and the target user has not joined the fallback group, the fallback group is pushed to the target user.

[0086] If the target user's profile data fails to match the group attributes of all initial groups, it can be checked whether the target user has joined the backup group before. If the target user has not joined the backup group before, the backup group can be pushed to the target user so that the target user can join at least one group to achieve the backup.

[0087] S504: If the target user's portrait data fails to match the group attributes of all initial groups, and the target user has joined the backup group, no group will be pushed to the target user.

[0088] If the target user's profile data fails to match the group attributes of all initial groups, and the target user has already joined the backup group, it is meaningless to push the backup group to the target user, and no group can be pushed to the target user. In other words, neither the initial group nor the backup group is pushed to the target user.

[0089] According to some embodiments of the present application, optionally, S205: match the target position to be pushed with the group attributes of each initial group in order of matching priority from high to low, and push the target position to the target initial group and / or subgroup of the target initial group that has successfully matched it, including the following steps five to eight.

[0090] Step 5: Extract features of the target position's position data and convert the extracted features into a first feature vector.

[0091] The position data of the target position refers to the position requirements of the target position, such as the location, function, industry, educational requirements and / or school requirements of the target position. In step 5, target features in the position data of the target position can be extracted, such as key fields such as the location, function, industry, educational requirements and / or school requirements of the target position. Then, the extracted features are converted into computable feature vectors. For ease of distinction, the feature vector obtained based on the position data of the target position is called the first feature vector.

[0092] Step 6: For any j-th initial group, perform feature extraction on the matching filter items in the group attributes of the j-th initial group, and convert the extracted features into a second feature vector, where j is a positive integer.

[0093] Specifically, the matching filter items in the group attributes of each initial group can be subjected to feature extraction in descending order of matching priority, and the extracted features can be converted into computable feature vectors. For the sake of distinction, the feature vector obtained based on the matching filter items in the group attributes is referred to as the second feature vector.

[0094] Step 7: Based on the target similarity algorithm or the trained similarity calculation model, calculate the similarity between the first feature vector and the second feature vector.

[0095] For any j-th initial group, based on a target similarity algorithm or a trained similarity calculation model, the similarity between the first feature vector and the second feature vector corresponding to the j-th initial group can be calculated. Exemplarily, the target similarity algorithm includes but is not limited to a cosine similarity algorithm or a Jaccard similarity algorithm. The similarity calculation model can be constructed based on a machine learning algorithm such as a decision tree or a random forest, or based on a deep learning algorithm such as a neural network.

[0096] In some embodiments, according to user feedback and data changes, parameters in the target similarity algorithm or model parameters in the similarity calculation model can be updated regularly to improve the accuracy and real-time performance of job matching and recommendation.

[0097] Step 8: When the similarity is greater than or equal to a preset threshold, the target position is pushed to the jth initial group and / or a subgroup of the jth initial group.

[0098] For any j-th initial group, when the similarity between the first feature vector and the second feature vector corresponding to the j-th initial group is greater than or equal to a preset threshold, the target position can be pushed to the j-th initial group and / or a subgroup of the j-th initial group. The size of the preset threshold can be flexibly adjusted according to actual conditions, and this application does not limit this.

[0099] In this way, according to the similarity between the position data of the target position and the group attributes, the appropriate group can be intelligently matched, which can provide more accurate group-job matching services for recruiting companies, improve recruitment efficiency and success rate, effectively optimize the recruitment process, improve matching accuracy, and provide better recruitment solutions for recruiting companies.

[0100] According to some embodiments of the present application, optionally, the chat tool-based group and position recommendation method may also include the following steps nine to eleven.

[0101] Step 9: Obtain the unique identifier corresponding to the group attribute of each initial group.

[0102] Specifically, each initial group has a permanent group activation code (referred to as group activation code). Based on the group activation code link of each initial group, the unique identifier (configId) of each initial group can be parsed. configId is a unique identifier used to identify and manage initial groups (such as corporate WeChat groups). Each initial group is assigned a configId value when it is created, which can be used for group management, message push, interface call and other operations.

[0103] Step 10: Based on the unique identifier, call the chat tool interface to query the IDs of multiple groups associated with the unique identifier.

[0104] For each parsed configId, the API interface of the chat tool can be called based on the configId to query the IDs of multiple groups associated with the configId. Among them, the IDs of multiple groups associated with the configId may include the ID of the initial group associated with the configId, and may also include the ID of the subgroup of the initial group associated with the configId. Because the subgroup is automatically generated after the initial group reaches a certain number of people, it cannot be created manually. Therefore, by executing step 10, the group ID list can be obtained in time to ensure the accuracy and real-time nature of the group information.

[0105] Step 11: Based on the ID of each group, call the interface of the chat tool to query the dynamic information of each group, and store the dynamic information of each group.

[0106] Based on the ID of each group, the API interface of the chat tool can be called to query the dynamic information of each group, and the dynamic information of each group can be stored in the local system. The local system can be a terminal device or a server. The dynamic information can include at least one of the group members, the number of people who join the group in the target time period, the number of people who leave the group, the number of job pushes, and the number of chats.

[0107] In this way, based on the above steps 9 to 11, the problem that the chat tool does not provide data support can be effectively solved, and the automatic acquisition and management of group information can be realized, providing a more convenient and efficient solution for group configuration and operation. In addition, using the interface provided by the chat tool, group details, group joining and leaving, group member changes and / or job push data are stored in the local system, which is conducive to the subsequent in-depth analysis of the group and group members, as well as the evaluation of the grouping and stratification effect.

[0108] According to some embodiments of the present application, optionally, a preset number of groups in the recommendation list can be sorted in descending order of matching priority. In this way, it is convenient for the target user to distinguish which part of the groups has a relatively high matching degree with him / herself and which part of the groups has a relatively low matching degree with him / herself, so that the target user can add the recommended group chat more flexibly according to his / her own needs.

[0109] Based on the same technical concept as the chat tool-based group and job recommendation method provided in the above embodiment, the present application also provides a chat tool-based group and job recommendation device. Please refer to the following embodiment.

[0110] Figure 6 A schematic diagram of a chat tool-based group and job recommendation device provided in an embodiment of the present application. Figure 6 As shown, the chat tool-based group and job recommendation device 60 provided in the embodiment of the present application may include the following modules:

[0111] A creation module 601 is used to create multiple group categories, each of which includes a group category name, a job tag combination, and a weight of each job tag in the job tag combination; wherein the job tag combination includes at least one job tag;

[0112] A setting module 602 is used to set group attributes of each of the multiple initial groups created in the chat tool; wherein the group attributes include a group attribute name, a target group category to which it belongs, a matching priority, and at least one matching filter item, wherein the at least one matching filter item corresponds to n job tags in the target group category, and the matching priority is determined based on the weights of the n job tags in the target group category, where n is a positive integer;

[0113] Matching module 603 is used to match the target user's portrait data with the group attributes of each initial group in order of matching priority from high to low; in the matching process, if the i-th initial group is matched successfully and the target user has not joined the i-th initial group, the i-th initial group or its subgroup is included in the recommendation list, where i is a positive integer; if the i-th initial group is matched successfully and the target user has joined the i-th initial group, the target user's portrait data is matched with the group attributes of the initial group of the next matching priority, until the number of groups in the recommendation list reaches a preset number or all initial groups are matched;

[0114] A recommendation module 604, used to recommend the groups in the recommendation list to the target user;

[0115] The push module 605 is used to match the target positions to be pushed with the group attributes of each initial group in order of matching priority from high to low, and push the target positions to the successfully matched target initial group and / or subgroup of the target initial group.

[0116] The chat tool-based group and job recommendation device provided by the embodiment of the present application, on the one hand, by creating multiple group categories and setting group attributes for each initial group, and then matching the target user's portrait data with the group attributes of each initial group, can realize automatic matching between the user and the initial group, and can quickly and accurately recommend a group suitable for the target user, which is conducive to improving user experience, increasing user participation, making group management more efficient, reducing the workload of operators, and improving the efficiency of group recommendation; on the other hand, it can intelligently match the target position to be pushed with the group attributes of each initial group, and push the target position to the target initial group and / or its subgroup that successfully matches it, which is conducive to providing more accurate group position matching services for recruiting companies and improving recruitment efficiency and success rate. On the other hand, by setting the weight of each job label and the matching priority in the group attributes, the target user can be preferentially matched with the group that meets the recruitment needs of the recruiting company, which is conducive to improving the success rate of job recommendation and the success rate of job hunting for the target user. This application integrates group recommendation with job recommendation, realizes user stratification through group division, and implements targeted operations and job recommendation plans for users at different levels, providing job-seeking user groups and recruiting companies with smarter and more efficient group management and recruitment solutions, promoting the development of recruitment business and improving user experience.

[0117] According to some embodiments of the present application, optionally, the matching module 603 can be specifically used to call the interface of the chat tool to query the upper limit of the number of people in the ith initial group and whether there is a subgroup in the ith initial group based on the ID of the ith initial group; if the ith initial group has not reached the upper limit of people, the ith initial group is included in the recommendation list; if the ith initial group has reached the upper limit of people and the ith initial group has no subgroup, a subgroup of the ith initial group is generated, and the newly generated subgroup of the ith initial group is included in the recommendation list; if the ith initial group has reached the upper limit of people and the ith initial group has a subgroup, and the subgroup has not reached the upper limit of people, the subgroup of the ith initial group is included in the recommendation list.

[0118] According to some embodiments of the present application, optionally, the position label includes the highest educational level, the name of the school of highest educational level, the graduation year of the highest educational level, the type label of the highest school, the function, location, job type, company nature or industry. The matching filter items include the highest educational level, the name of the school of highest educational level, the graduation year of the highest educational level, the type label of the highest school, the most recent function, the expected function, the function preference, the expected work location, the expected job type, the most recent company nature, the expected industry, the most recent industry or industry preference. The portrait data of the target user includes at least one of the target user's highest educational level, the name of the school of highest educational level, the graduation year of the highest educational level, the type label of the highest school, the most recent function, the expected function, the function preference, the expected work location, the expected job type, the most recent company nature, the expected industry, the most recent industry and industry preference.

[0119] According to some embodiments of the present application, optionally, the chat tool-based group and job recommendation device 60 may also include a fallback module for creating a fallback group in the chat tool; setting group attributes of the fallback group, wherein the matching priority in the group attributes of the fallback group is less than the matching priority in the group attributes of each initial group; if the portrait data of the target user fails to match the group attributes of all the initial groups, and the target user has not joined the fallback group, the fallback group is pushed to the target user; if the portrait data of the target user fails to match the group attributes of all the initial groups, and the target user has joined the fallback group, no group is pushed to the target user.

[0120] According to some embodiments of the present application, optionally, the push module 605 can be specifically used to extract features from the position data of the target position, and convert the extracted features into a first feature vector; for any j-th initial group, extract features from the matching filter items in the group attributes of the j-th initial group, and convert the extracted features into a second feature vector, where j is a positive integer; calculate the similarity between the first feature vector and the second feature vector based on a target similarity algorithm or a trained similarity calculation model; when the similarity is greater than or equal to a preset threshold, push the target position to the j-th initial group and / or a subgroup of the j-th initial group.

[0121] According to some embodiments of the present application, optionally, the chat tool-based group and position recommendation device 60 may also include a storage module for obtaining a unique identifier corresponding to the group attributes of each initial group; based on the unique identifier, calling the chat tool interface to query the IDs of multiple groups associated with the unique identifier; based on the ID of each group, calling the chat tool interface to query the dynamic information of each group, and storing the dynamic information of each group, wherein the dynamic information includes at least one of the group members, the number of people who join the group in the target time period, the number of people who leave the group, the number of position pushes and the number of chat items.

[0122] According to some embodiments of the present application, optionally, a preset number of groups in the recommendation list are sorted in order of matching priority from high to low.

[0123] Figure 6 Each module / unit in the device shown has the function of implementing each step in the chat tool-based group and position recommendation method provided in the above method embodiment, and can achieve its corresponding technical effect. For the sake of concise description, it will not be repeated here.

[0124] The electronic device in the embodiment of the present application may be a user terminal device, a server, other computing devices, or a cloud server. Figure 7 This is a hardware structure diagram of an electronic device of an embodiment of the present application. The electronic device may include a processor 701 and a memory 702 storing computer program instructions. When the processor 701 executes the computer program instructions, it implements the process or function of any of the above-mentioned embodiment methods.

[0125] Specifically, the processor 701 may include a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application. The memory 702 may include a large-capacity memory for data or instructions. For example, the memory 702 may be at least one of the following: a hard disk drive (HDD), a read-only memory (ROM), a random access memory (RAM), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a tape, a universal serial bus (USB) drive or other physical / tangible memory storage device. For another example, the memory 702 may include a removable or non-removable (or fixed) medium. For another example, the memory 702 may be inside or outside the integrated gateway disaster recovery device. The memory 702 may be a non-volatile solid-state memory. In other words, the memory 702 usually includes a tangible (non-transitory) computer-readable storage medium (such as a memory device) encoded with computer-executable instructions, and when the software is executed (such as executed by one or more processors), the operations described in the method of the embodiment of the present application can be performed. The processor 701 implements the process or function of any method in the above embodiments by reading and executing the computer program instructions stored in the memory 702.

[0126] In one example, Figure 7The electronic device shown may also include a communication interface 703 and a bus 710. Among them, the processor 701, the memory 702, and the communication interface 703 are connected through the bus 710 and complete the communication between each other. The communication interface 703 is mainly used to realize the communication between each module, device, unit and / or device in the embodiment of the present application. The bus 710 includes hardware, software or both, and can couple the components of the online data traffic billing device to each other. For example, the bus may include at least one of the following: an accelerated graphics port (AGP) or other graphics bus, an enhanced industrial standard architecture (EISA) bus, a front-end bus (FSB), a hypertransport (HT) interconnect, an industrial standard architecture (ISA) bus, an infinite bandwidth interconnect, a low pin count (LPC) bus, a memory bus, a micro channel architecture (MCA) bus, a peripheral component interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a serial advanced technology attachment (SATA) bus, a video electronics standard association local (VLB) bus or other suitable buses. The bus 710 may include one or more buses. Although the embodiments of the present application describe or illustrate a specific bus, the embodiments of the present application may consider any suitable bus or interconnection method.

[0127] In combination with the method in the above embodiments, an embodiment of the present application also provides a computer-readable storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the process or function of any method in the above embodiments is implemented.

[0128] In addition, an embodiment of the present application further provides a computer program product, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the process or function of any one of the methods in the above embodiments is implemented.

[0129] The above exemplarily describes the flowcharts and / or block diagrams of the methods, devices, systems and computer program products of the embodiments of the present application, and describes the relevant various aspects. It should be understood that each box or combination thereof in the flowchart and / or block diagram can be implemented by computer program instructions, or by dedicated hardware that performs a specified function or action, or by a combination of dedicated hardware and computer instructions. For example, these computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to form a machine that enables these instructions executed by such a processor to enable the implementation of the functions / actions specified in each box or combination thereof in the flowchart and / or block diagram. Such a processor can be a general-purpose processor, a special-purpose processor, a special application processor or a field programmable logic circuit.

[0130] The functional blocks shown in the structured block diagram of the embodiment of the present application can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application-specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc.; when implemented in software, it is a program or code segment used to perform the required task. The program or code segment can be stored in a memory, or transmitted on a transmission medium or a communication link via a data signal carried in a carrier. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0131] It should be noted that the present application is not limited to the specific configurations and processes described above or shown in the figures. The above is only a specific implementation mode of the present application. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process of the described system, device, module or unit can refer to the corresponding process in the method embodiment without further description. It should be understood that the scope of protection of the present application is not limited to this. Any technician familiar with the technical field can think of various equivalent modifications or substitutions within the technical scope disclosed in the present application, and these modifications or substitutions should be included in the scope of protection of the present application.

Claims

1. A group and job recommendation method based on a chat tool, characterized in that: include: Creating multiple group categories, each group category includes a group category name, a job tag combination, and a weight of each job tag in the job tag combination; wherein the job tag combination includes at least one job tag; For multiple initial groups created in the chat tool, set group attributes of each initial group; wherein the group attributes include a group attribute name, a target group category to which it belongs, a matching priority, and at least one matching filter item, wherein the at least one matching filter item corresponds to n position tags in the target group category, and the matching priority is determined based on the weights of the n position tags in the target group category, where n is a positive integer; In order of matching priority from high to low, the target user's portrait data is matched with the group attributes of each initial group in turn; during the matching process, if the i-th initial group is matched successfully and the target user has not joined the i-th initial group, the i-th initial group or its subgroup is included in the recommendation list, where i is a positive integer; if the i-th initial group is matched successfully and the target user has joined the i-th initial group, the target user's portrait data is matched with the group attributes of the initial group of the next matching priority, until the number of groups in the recommendation list reaches the preset number or all initial groups are matched; Recommend the groups in the recommendation list to the target users; In order of matching priority from high to low, the target positions to be pushed are matched with the group attributes of each initial group in turn, and the target positions are pushed to the target initial group and / or subgroup of the target initial group that has successfully matched it.

2. The method according to claim 1, characterized in that The i-th initial group or its subgroups are included in the recommendation list, including: Based on the ID of the i-th initial group, call the chat tool interface to query the upper limit of the number of people in the i-th initial group and whether there is a subgroup in the i-th initial group; If the i-th initial group has not reached the upper limit of the number of people, the i-th initial group will be included in the recommendation list; If the i-th initial group has reached the upper limit of its members and the i-th initial group has no subgroup, a subgroup of the i-th initial group is generated and the newly generated subgroup of the i-th initial group is included in the recommendation list; If the i-th initial group has reached the upper limit of its population, and the i-th initial group has a subgroup that has not reached the upper limit of its population, the subgroup of the i-th initial group will be included in the recommendation list.

3. The method according to claim 1, characterized in that Position tags include highest education level, name of the school where the highest education was obtained, graduation year of the highest education, type tag of the highest school, function, location, job type, company nature or industry; Matching filter items include highest education level, name of the school of highest education, graduation year of highest education, type label of the highest school, most recent function, expected function, function preference, expected work location, expected work type, most recent company nature, expected industry, most recent industry or industry preference; The target user's portrait data includes at least one of the target user's highest educational level, name of the school of highest educational level, graduation year of highest educational level, type label of the highest school, most recent function, expected function, function preference, expected work location, expected job type, nature of most recent company, expected industry, most recent industry and industry preference.

4. The method according to claim 1, characterized in that: The method further comprises: Create a backup group in the chat tool; Set the group attributes of the fallback group, where the matching priority in the group attributes of the fallback group is lower than the matching priority in the group attributes of each initial group; If the target user's profile data fails to match the group attributes of all initial groups, and the target user has not joined the backup group, the backup group will be pushed to the target user; If the target user's portrait data fails to match the group attributes of all initial groups, and the target user has joined the backup group, no group will be pushed to the target user.

5. The method according to claim 1, characterized in that In order of matching priority from high to low, the target positions to be pushed are matched with the group attributes of each initial group in turn, and the target positions are pushed to the target initial group and / or subgroups of the target initial group that have successfully matched the target positions, including: Extracting features from the position data of the target position and converting the extracted features into a first feature vector; For any j-th initial group, feature extraction is performed on the matching filter items in the group attributes of the j-th initial group, and the extracted features are converted into a second feature vector, where j is a positive integer; Calculate the similarity between the first feature vector and the second feature vector based on a target similarity algorithm or a trained similarity calculation model; When the similarity is greater than or equal to a preset threshold, the target position is pushed to the jth initial group and / or a subgroup of the jth initial group.

6. The method according to claim 1, characterized in that The method further comprises: Obtain the unique identifier corresponding to the group attribute of each initial group; Based on the unique identifier, calling the interface of the chat tool to query the IDs of multiple groups associated with the unique identifier; Based on the ID of each group, the interface of the chat tool is called to query the dynamic information of each group, and the dynamic information of each group is stored, wherein the dynamic information includes at least one of the group members, the number of people who join the group during the target time period, the number of people who leave the group, the number of job pushes and the number of chat items.

7. The method according to claim 1, characterized in that The preset number of groups in the recommendation list are sorted in order of matching priority from high to low.

8. A group and job recommendation device based on a chat tool, characterized in that: include: A creation module, used to create multiple group categories, each group category includes a group category name, a job tag combination and a weight of each job tag in the job tag combination; wherein the job tag combination includes at least one job tag; A setting module is used to set the group attributes of each of the multiple initial groups created in the chat tool; wherein the group attributes include a group attribute name, a target group category to which it belongs, a matching priority, and at least one matching filter item, wherein the at least one matching filter item corresponds to n position tags in the target group category, and the matching priority is determined based on the weights of the n position tags in the target group category, where n is a positive integer; A matching module is used to match the target user's portrait data with the group attributes of each initial group in order of matching priority from high to low; during the matching process, if the i-th initial group is matched successfully and the target user has not joined the i-th initial group, the i-th initial group or its subgroup is included in the recommendation list, where i is a positive integer; if the i-th initial group is matched successfully and the target user has joined the i-th initial group, the target user's portrait data is matched with the group attributes of the initial group of the next matching priority, until the number of groups in the recommendation list reaches a preset number or all initial groups are matched; The recommendation module is used to recommend the groups in the recommendation list to the target users; The push module is used to match the target positions to be pushed with the group attributes of each initial group in order from high to low matching priority, and push the target positions to the target initial group and / or subgroup of the target initial group that successfully matches it.

9. An electronic device, characterized in that: The electronic device comprises: a processor and a memory storing computer program instructions; when the electronic device executes the computer program instructions, the method for recommending groups and positions based on a chat tool as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, which, when executed by a processor, implement the chat tool-based group and position recommendation method as described in any one of claims 1-7.

Images