CN117278508A - Recommended methods, devices and electronic devices for 5G messaging chatbots - Google Patents

Abstract

The present disclosure provides a recommendation method, device and electronic device for a 5G message chat robot, and relates to 5G message chat robot recommendation algorithm technology. The specific technical solution is: obtain the multi-source data of the first object. The multi-source data includes browsing data, search data, location data and communication data; based on the browsing data, search data, location data and communication data, from the 5G message chat robot product library Obtain candidate chat robots of multiple recommendation categories; determine a 5G message chat robot recommendation list based on the candidate chat robots of multiple recommendation categories; and provide the 5G message chat robot recommendation list to the first object. Recommending 5G message chatbots based on browsing data, search data, location data and communication data improves the recommendation quality of 5G message chatbots, improves the consistency of 5G message chatbots with user preferences, user work or life scenarios, and improves recommendations The business value of the page.

Description

Recommended methods, devices and electronic devices for 5G messaging chatbots

Technical field

The present disclosure relates to the field of communication technology, and in particular to a recommendation method, device and electronic device for a 5G message chat robot.

Background technique

5G messaging is a new upgrade to traditional SMS messaging. It uses native SMS on smartphones as the entry point and can support a variety of rich media message forms such as text, pictures, audio, video, documents, business cards, geographical locations, etc., with a high reach rate. , rich media, strong interactivity, convenience and other characteristics. For industry customers, 5G messaging can provide enhanced messaging services between individuals and applications, and introduce a new message interaction mode - Chatbot (chat robot). Users can intuitively and conveniently enjoy payment and recharge, ticket ordering, hotel booking, etc. in the message window. Various 5G messaging application services such as logistics inquiries, restaurant reservations, and takeout orders.

Among related technologies, the recommendation of 5G messaging chatbots mainly relies on manual configuration by operators based on hot information, high-quality resources, and operational needs. Limited by the operator's sensitivity to current political hot spots and the speed of configuration updates, the recommendation quality of the 5G messaging chatbot cannot be guaranteed, which reduces the commercial value of the recommendation page and is not conducive to the construction of the 5G ecosystem.

Contents of the invention

In order to overcome problems existing in related technologies, the present disclosure provides a recommendation method, device and electronic device for a 5G message chat robot.

According to a first aspect of an embodiment of the present disclosure, a recommendation method for a 5G message chat robot is provided, including:

Obtain multi-source data of the first object, where the multi-source data includes browsing data, search data, location data and communication data;

Based on browsing data, search data, location data and communication data, obtain candidate chatbots for multiple recommended categories from the 5G messaging chatbot product library;

Based on candidate chatbots in multiple recommendation categories, determine the 5G messaging chatbot recommendation list;

Provide the 5G messaging chatbot recommendation list to the first object.

According to a second aspect of the embodiment of the present disclosure, a recommendation device for a 5G message chat robot is provided, including:

The first acquisition module is used to acquire multi-source data of the first object. The multi-source data includes browsing data, search data, location data and communication data;

The second acquisition module is used to obtain candidate chat robots of multiple recommendation categories from the 5G messaging chat robot product library based on browsing data, search data, location data and communication data;

A determination module for determining a 5G messaging chat robot recommendation list based on candidate chat robots in multiple recommendation categories;

The recommendation module is used to provide the 5G message chatbot recommendation list to the first object.

According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, including:

at least one processor; and

A memory communicatively connected to at least one processor; wherein,

The memory stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor, so that at least one processor can execute the method of the above-mentioned first aspect.

According to a fourth aspect of the embodiments of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions, which stores computer instructions, and the computer instructions are used to cause the computer to execute the method of the above-mentioned first aspect.

According to a fifth aspect of the embodiments of the present disclosure, a computer program product is provided, including a computer program. When executed by a processor, the computer program can implement the method of the first aspect.

The technical solution provided by the embodiments of the present disclosure can include the following beneficial effects: recommending 5G message chatbots based on browsing data, search data, location data, and communication data, improving the recommendation quality of 5G message chatbots, and improving the relationship between 5G message chatbots and The degree of compliance with user preferences and user work or life scenarios enhances the commercial value of the recommendation page and promotes the construction of the 5G ecosystem.

It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only, and do not limit the present disclosure.

Description of the drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description serve to explain the principles of the invention.

Figure 1 is a flow chart of a 5G message chat robot recommendation method provided according to an embodiment of the present disclosure.

Figure 2 is a flow chart of another 5G message chatbot recommendation method provided according to an embodiment of the present disclosure.

Figure 3 is a schematic diagram of a 5G messaging chatbot recommendation page provided according to an embodiment of the present disclosure.

Figure 4 is a flow chart of yet another 5G message chatbot recommendation method provided according to an embodiment of the present disclosure.

Figure 5 is a block diagram of a recommendation device for a 5G message chat robot provided according to an embodiment of the present disclosure.

FIG. 6 is a block diagram of an electronic device according to an embodiment of the present disclosure.

Detailed ways

Exemplary embodiments will be described in detail herein, examples of which are illustrated in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the invention. Rather, they are merely examples of apparatus and methods consistent with aspects of the invention as detailed in the appended claims.

It should be noted that in the technical solution of this disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information are in compliance with relevant laws and regulations and do not violate public order and good customs.

Figure 1 is a flow chart of a 5G message chat robot recommendation method provided according to an embodiment of the present disclosure. It should be noted that the recommendation method of the 5G message chat robot provided by the embodiment of the present disclosure can be applied to the recommendation device of the 5G message chat robot provided by the embodiment of the present disclosure. For example, the recommendation device can be configured on an electronic device.

As shown in Figure 1, the recommended method of the 5G messaging chatbot includes but is not limited to the following steps:

In step S101, multi-source data of the first object is obtained. The multi-source data includes browsing data, search data, location data and communication data.

As an example, the first object may be a user, or may be a terminal device held by the user (such as a mobile device such as a mobile phone or a tablet computer). For convenience of description, the following description will take the first object as the user as an example.

In some embodiments of the present disclosure, the multi-source data of the first object includes browsing data, search data, location data and communication data. For example, the browsing data can be the web pages and APP records that the first object has browsed in the past three days; the search data can be the keywords that the first object has actively searched for from the search portal in the past three days; the location data can be the real-time location of the first object. The data, that is, the longitude and latitude data of the base station with the strongest signal connected to the terminal held by the first subject, can also be the location data of the terminal held by the first subject in the last natural month, that is, the data of all base stations connected to the terminal held by the first subject in the last natural month. Longitude and latitude, the connection time and duration of each base station; the communication data can be the call data of the first party in the past seven days, including the call partner, duration and frequency.

Optionally, the obtained multi-source data can be aggregated, cleaned, classified and stored by building a big data platform.

For example, the above-mentioned multi-source data of the first object can be stored on the terminal device held by the first object. When the recommendation event of the 5G message chat robot is triggered, the multi-source data of the first object is obtained from the terminal device. data.

For example, the multi-source data of the above-mentioned first object can be stored in the server. When the recommendation event of the 5G message chat robot is triggered, the multi-source data of the first object is obtained from the server side.

For example, an application is installed on the terminal device, and the application provides a search portal. When it is detected that the first object clicks to use the search portal, the recommendation event of the 5G message chat robot can be triggered. Alternatively, the application provides a recommendation button, and when it is detected that the first object clicks and uses the recommendation button, the recommendation event of the 5G messaging chatbot can be triggered. Or the recommendation event of the 5G message chat robot can be triggered in other ways. This disclosure does not limit this and will not be repeated.

In step S102, based on browsing data, search data, location data and communication data, candidate chat robots of multiple recommended categories are obtained from the 5G message chat robot product library.

In some embodiments of the present disclosure, based on browsing data and search data, a candidate chat robot related to the first object's preferences can be obtained from the 5G messaging chat robot product library, and the candidate chat robot can belong to a preference-related recommendation category; based on Based on the location data, a candidate chat robot related to the location of the first object can be obtained from the 5G message chat robot product library. The candidate chat robot can belong to a location-related recommendation category; based on the call data, a candidate chat robot related to the first object's location can be obtained from the 5G message chat robot product library. A candidate chat robot related to the preferences of relatives and friends of the first object is obtained, and the candidate chat robot may belong to a recommendation category related to the preferences of relatives and friends.

As an example, the names of the recommendation categories may be "Guess You Like", "Nearby Services", and "Following Friends and Family". Candidate chatbots based on browsing data and search data can belong to the "guess you like" category; candidate chatbots based on location data can belong to the "nearby services" category; candidate chatbots based on call data can belong to "family and friends attention" category.

In step S103, a 5G messaging chatbot recommendation list is determined based on the candidate chatbots in each of the multiple recommendation categories.

In some embodiments of the present disclosure, candidate chatbots in each recommendation category are deduplicated, and the chatbots obtained after deduplication are composed into a 5G message chatbot recommendation list.

In step S104, the 5G messaging chatbot recommendation list is provided to the first object.

Optionally, the 5G message chat robot recommendation list can be sent to the terminal held by the first object in the form of a recommendation page. The terminal displays the recommendation page to provide the 5G message chatbot recommendation list to the first object.

In embodiments of the present disclosure, the 5G message chatbot is recommended based on browsing data, search data, location data, and communication data, thereby improving the recommendation quality of the 5G message chatbot.

It should be noted that the 5G messaging chatbot is provided to the first object in the form of a recommendation page. Among them, the recommendation page is generated based on the layout of the recommendation page and the 5G message chat robot recommendation list. Optionally, FIG. 2 is a flow chart of another 5G message chat robot recommendation method provided according to an embodiment of the present disclosure.

As shown in Figure 2, the recommended method of the 5G messaging chatbot includes the following steps:

In step S201, multi-source data of the first object is obtained. The multi-source data includes browsing data, search data, location data and communication data.

In the embodiments of the present disclosure, step S201 can be implemented in any manner in the embodiments of the present disclosure. The embodiments of the present disclosure do not limit this and will not be described again.

In step S202, based on browsing data, search data, location data and communication data, multiple candidate chat robots of each recommendation category are obtained from the 5G message chat robot product library.

In the embodiments of the present disclosure, step S202 can be implemented in any manner in the embodiments of the present disclosure. The embodiments of the present disclosure do not limit this and will not be described again.

In step S203, a 5G message chat robot recommendation list is determined based on the candidate chat robots in each of the multiple recommendation categories.

In the embodiments of the present disclosure, step S203 can be implemented in any manner in the embodiments of the present disclosure. The embodiments of the present disclosure do not limit this and will not be described again.

In step S204, recommended page layout information is determined.

In some embodiments of the present disclosure, the recommended page layout information corresponding to different terminals is different. Therefore, the specific implementation method of determining the recommended page layout information may be as follows: obtaining the identification information of the terminal held by the first object; according to the identification information, determining the information related to the terminal Corresponding recommended page layout information.

It should be noted that the layout information of the recommendation page includes multiple recommendation categories. For example, the layout information of the recommendation page may include three recommendation categories, and the names of the recommendation categories may be "Guess You Like", "Nearby Services" and "Follow Friends and Family".

In step S205, the recommended page information is generated based on the 5G message chat robot recommendation list, combined with the recommended page layout information and the order of multiple recommended categories in the recommended page.

In some embodiments of the present disclosure, each chatbot in the 5G messaging chatbot recommendation list has a recommendation category to which it belongs. Based on the recommendation category it belongs to, the chatbot's position on the recommendation page can be determined.

In some embodiments of the present disclosure, the terminal held by the first object is mainly a mobile terminal, and its recommended page can display information and has limited information processing capabilities. Therefore, the recommended page layout information generally includes three recommendation categories, and each recommendation category can include three A chatbot.

In step S206, the recommended page information is sent to the terminal held by the first object. The recommended page information is used by the terminal to display the 5G message chat robot recommendation list in order based on the recommended page layout information.

Optionally, FIG. 3 is a schematic diagram of a 5G messaging chatbot recommendation page provided according to an embodiment of the present disclosure. Figure 3 takes the recommendation page layout information including three recommendation categories, and each recommendation category includes three chat robots as an example. As shown in Figure 3, the recommendation page can include a search bar and recommended content. Among them, the recommended content part includes three recommendation categories arranged from top to bottom. Below each recommendation category are the chatbots belonging to that recommendation category in the three 5G messaging chatbot recommendation lists.

Optionally, the terminal held by the first object may be the user's mobile phone or other mobile communication terminal.

In embodiments of the present disclosure, the 5G message chatbot is recommended based on browsing data, search data, location data and communication data, which improves the recommendation quality of the 5G message chatbot and enhances the commercial value of the recommended page.

It should be noted that based on browsing data, search data, location data and communication data, candidate chatbots for different recommendation categories can be obtained from the 5G messaging chatbot product library for different recommendation categories. Figure 4 is a flow chart of yet another 5G message chatbot recommendation method provided according to an embodiment of the present disclosure. As shown in Figure 4, the recommended method of the 5G messaging chatbot includes the following steps:

In step S401, multi-source data of the first object is obtained, where the multi-source data includes browsing data, search data, location data and communication data.

In the embodiments of the present disclosure, step S401 can be implemented in any manner in the embodiments of the present disclosure. The embodiments of the present disclosure do not limit this and will not be described again.

In step S402, based on the browsing data and search data, the preference tag of the first object is determined, and the first candidate chat robot associated with the preference tag is obtained from the 5G messaging chat robot product library.

In some embodiments of the present disclosure, the specific implementation method of determining the preference tag of the first object based on browsing data and search data is to count the number of views of each tag based on multiple preset tags and browsing data; based on multiple tags and search data, count the number of searches for each tag; determine the browsing coefficient of each tag based on the browsing mode coefficient and the number of views of each tag; determine the search for each tag based on the search mode coefficient and the number of searches for each tag Coefficient; determine the preferred label of the first object from multiple labels based on the browsing coefficient and search coefficient of each label.

In some embodiments of the present disclosure, based on multiple preset tags and browsing data, the specific implementation method of counting the number of views of each tag may be to count the number of views of each tag in the first object in the third time period; based on multiple tags and the search data, and the specific implementation method of counting the number of searches for each tag may be to count the number of searches for each tag within the third time period of the first object.

As an example of a possible implementation, count the number of views of each tag of the first object in the past three days. Based on the number of views of each tag, the browsing weight of each tag can be determined. Based on the browsing weight and browsing mode coefficient of each tag, the browsing coefficient of each tag can be determined. Among them, the calculation formula of the browsing weight of each tag can be shown as the following formula (1):

Among them, wb _i refers to the browsing weight of the i-th tag; m _i refers to the number of views of the i-th tag; n refers to the number of preferred tags. Generally speaking, preferred tags include catering, culture and tourism, current affairs, entertainment, Novel, music and parent-child, that is, n is generally 7.

Among them, the calculation formula of the browsing coefficient of each tag can be shown as the following formula (2):

vb _i ＝wb _i *r _b (2)

Among them, vb _i refers to the browsing coefficient of the i-th tag; wb _i refers to the browsing weight of the i-th tag; r _b refers to the browsing mode coefficient, and its default initial value is 0.

As an example of a possible implementation, count the number of searches for each tag of the first object in the past three days, and based on the number of searches for each tag, the search weight of each tag can be determined. Based on the search weight and search mode coefficient of each tag, the search coefficient of each tag can be determined. in,

The calculation formula of the search weight of each tag can be shown as the following formula (3):

Among them, ws _i refers to the search weight of the i-th tag; m _i refers to the number of searches for the i-th tag; n refers to the number of preferred tags. Generally speaking, preferred tags include catering, culture and tourism, current affairs, entertainment, Novel, music and parent-child, that is, n is generally 7.

Among them, the calculation formula of the search coefficient of each tag can be shown as the following formula (4):

vs _i ＝ws _i *r _s (4)

Among them, vs _i refers to the search coefficient of the i-th tag; ws _i refers to the search weight of the i-th tag; r _s refers to the search method coefficient, and its default initial value is 1.

In some embodiments of the present disclosure, the specific implementation method of adjusting the browsing mode coefficient and the search mode coefficient may be to obtain the conversion rate of the 5G message chat robot in the 5G message chat robot recommendation list; determine that the conversion rate is less than or equal to the first predetermined Set a threshold; based on the conversion rate and the first preset threshold, adjust the browsing mode coefficient and the search mode coefficient. Among them, the sum of the browsing mode coefficient and the search mode coefficient is 1, that is, r _s + r _b =1 needs to be satisfied.

In some embodiments of the present disclosure, after determining the browsing coefficient and search coefficient of each tag, the sum of the browsing coefficient and search coefficient of each tag is sorted from large to small. When the number of preference labels of the first object is one, the first label in the sorting result is determined as the preference label of the first object. When the number of preference tags of the first object is multiple, the tags in the sorting result are determined as the preference tags of the first object in sequence according to the number of preference tags of the first object.

In some embodiments of the present disclosure, after determining the preference tag of the first object, the specific implementation method of obtaining the first candidate chat robot associated with the preference tag from the 5G message chat robot product library may be to obtain the first candidate chat robot from the 5G message chat robot product library. , obtain the chat robot with the highest number of visits in the first time period in the preference tag; determine the chat robot with the highest number of visits in the first time period in the preference tag as the first candidate chat robot associated with the preference tag.

As an example of a possible implementation, take the first time period as the last month as an example. When the number of preference tags of the first object is one, the last month of the preference tags can be obtained from the 5G messaging chat robot product library. The chatbot with the highest number of visits is used as the first candidate chatbot associated with the preference tag. When the first object has multiple preference tags, the chatbot with the highest number of visits in each preference tag in the last month can be obtained from the 5G messaging chatbot product library as the first candidate associated with the preference tag. Chatbot.

For example, the first object's preference tags are catering, cultural tourism, and current affairs. The chatbot with the most visits in the past month under the Catering tab is the No.1 Catering Chatbot; the chatbot with the most visits in the past month under the Culture and Tourism tab is the No.1 Culture and Tourism chatbot; under the Current Affairs tab in the past month The chatbot with the largest number of internal visits is the first current affairs chatbot. Therefore, the first catering chatbot, the first cultural tourism chatbot and the first current affairs chatbot are identified as the first candidate chatbots.

In step S403, a second candidate chat robot is obtained from the 5G messaging chat robot product library based on the location data and preference tags.

In some embodiments of the present disclosure, based on location data and preference tags, the specific implementation method of obtaining the second candidate chat robot from the 5G messaging chat robot product library is to determine the real-time area of the first object based on the real-time location data in the location data. ; According to the location data of the first object in the second time period in the location data, determine the working area and living area of the first object; determine the current recommended time, based on the current recommended time, from the real-time area, working area and living area, Select the first area that matches the current recommended time; based on the first area and the preference tag, obtain the chat robot associated with the first area from the 5G message chat robot product library, wherein the chat robot is different from the preference tag The associated first candidate chatbot; the chatbot associated with the first region is determined as the second candidate chatbot.

In some embodiments of the present disclosure, the above-mentioned real-time location data may include the longitude and latitude of the base station with the strongest signal connection at the current moment of the terminal held by the first object. The above-mentioned specific implementation method of determining the real-time area of the first object based on the real-time location data among the location data It can be as follows: the area with the longitude and latitude of the base station with the strongest signal connection at the current moment as the center of the circle and the first length as the radius is determined as the real-time area of the first object.

For example, if the first length is two hundred meters, then the real-time area of the first object is a circular area with the longitude and latitude of the base station with the strongest signal connection at the current moment as the center and a radius of two hundred meters.

In some embodiments of the present disclosure, according to the position data of the first object in the second time period in the position data, the specific implementation method of determining the working area of the first object may be: according to the position data of the first object in the position data. For location data in two time periods, the statistical connection time is the longitude and latitude of the base stations in the first time period and with the top N connection durations; where N is a positive integer; the working area of the first object is determined based on the statistically obtained longitude and latitude of N base stations. .

Optionally, the first time period can be the last month, and the second time period can be from 9:00 to 18:00 on working days.

As an example of a possible implementation, based on the location data of the first object in the location data between 9:00 and 18:00 on weekdays, count the longitude and latitude of the base stations whose connection time is the last month and whose connection duration is ranked among the top 4; The working area of the first object is determined based on the statistically obtained longitude and latitude of the four base stations.

In some embodiments of the present disclosure, the specific implementation method of determining the working area of the first object based on the statistically obtained longitude and latitude of N base stations may be: based on the longitude and latitude of the N base stations, calculate the distance between each base station and other base stations among the N base stations. Spatial distance; average the N-1 spatial distances of each base station among the N base stations to obtain the average spatial distance of each base station among the N base stations; according to the average spatial distance of each base station among the N base stations value, connection duration, and eliminate isolated base stations from N base stations.

As an example of a possible implementation, when the average spatial distance of one of the N base stations is greater than 50 km, the base station with the shortest connection time among the N base stations is eliminated. Repeat the step "Eliminate isolated base stations from the N base stations based on the average spatial distance and connection duration of each base station among the N base stations" until the average spatial distance of the remaining base stations is less than or equal to 50km.

After eliminating isolated base stations from the N base stations, determine the working area of the first object based on the number of remaining base stations and the longitude and latitude of the remaining base stations, including at least one of the following:

(1) Determine the number of remaining base stations as 1, and determine the area with the longitude and latitude of the remaining base stations as the center and the second length as the radius as the working area of the first object.

As an example of a possible implementation, calculate the spatial distance between each base station and other base stations based on the longitude and latitude of the two base stations; average the spatial distance of each base station among the two base stations, and get The average spatial distance of each base station among the 2 base stations. Among them, the connection time of the two base stations in descending order is the first base station and the second base station. The spatial distance between the first base station and the second base station is greater than 50km. Therefore, based on the connection time sorting of the two base stations, the second base station is determined to be an isolated base station, and the second base station is eliminated. After eliminating the isolated base stations, the number of remaining base stations is 1, which is the first base station. When there is one base station left and the second length is two hundred meters, the working area of the first object is a circular area with the longitude and latitude of the remaining base station as the center and a radius of two hundred meters.

(2) Determine the number of remaining base stations to be 2, and determine the area with the longitude and latitude of the midpoint between the two remaining base stations as the center of the circle and half the distance between the two remaining base stations as the radius, as the working area of the first object.

As an example of a possible implementation, calculate the spatial distance between each base station and other base stations based on the longitude and latitude of the two base stations; average the spatial distance of each base station among the two base stations, and get The average spatial distance of each base station among the 2 base stations. Since N is 2, the average spatial distance of each base station is the spatial distance of the two base stations. The spatial distance between the two base stations is less than or equal to 50km, so neither base station is an isolated base station, and the number of remaining base stations is 2. The working area of the first object is a circular area with the midpoint longitude and latitude of the two remaining base stations as the center and half the distance between the two remaining base stations as the radius.

(3) Determine that the number of remaining base stations is greater than or equal to 3, and determine the working area of the first object based on the longitude and latitude of the three remaining base stations.

It should be noted that when the number of remaining base stations is greater than or equal to 3, the specific implementation method of determining the polygon area based on the longitude and latitude of the remaining base stations can be to sort the remaining base stations according to their longitude and latitude coordinates, and add them to the polygon coordinate set in sequence according to the sorting results; The polygon area is the area surrounded by each coordinate point in the polygon coordinate set. Among them, a specific implementation method of sorting the remaining base stations according to longitude and latitude coordinates may be to first sort them according to longitude/latitude, and coordinates with the same longitude/latitude are arranged according to latitude/longitude coordinates. The sorting rule can be ascending or descending order.

As an example of a possible implementation, N is 3. Based on the longitude and latitude of the three base stations, calculate the spatial distance between each base station and other base stations among the three base stations; average the two spatial distances of each base station among the three base stations to obtain the spatial distance of each base station among the three base stations. Spatial distance average. Among them, the average spatial distance of each base station is less than or equal to 50km, so the three base stations are not isolated base stations, and the number of remaining base stations is three. The working area of the first object is the polygonal area surrounded by the longitude and latitude coordinates of the remaining three base stations.

In some embodiments of the present disclosure, according to the location data of the first object in the second time period in the location data, the specific implementation method of determining the living area of the first object may be: according to the location data of the first object in the location data. For location data within two time periods, the statistical connection time is the longitude and latitude of the base stations at the second time point with the top N connection durations; where N is a positive integer; the living area of the first object is determined based on the statistically obtained N base station longitudes and latitudes. .

Optionally, the first time period may be the last month, and the second time period may be from 21:00 to 6:00 on working days.

It should be noted that the specific implementation method of determining the living area of the first object based on the longitude and latitude of N base stations obtained by statistics is similar to the above-mentioned steps of determining the working area of the first object based on the longitude and latitude of N base stations obtained by statistics, and will not be repeated here. Repeat.

In some embodiments of the present disclosure, after determining the first area that matches the current recommended time, the chat robot associated with the first area is obtained from the 5G messaging chat robot product library based on the first area and the preference tag, wherein, chat The bot is different from the first candidate chat bot associated with the preference tag; the chat bot associated with the first region is determined to be the second candidate chat bot.

For example, when the chatbot with the third most visits in the first subject's living area in the past week is the first candidate chatbot, in order to avoid duplication of recommendation results, the chatbot with the fourth most visits in the past week is selected as the second candidate chatbot. robot.

In step S404, based on the communication data and location data, a candidate chat robot associated with the preference tag of the second object is obtained, and a third candidate chat robot is determined based on the candidate chat robot associated with the preference tag of the second object; wherein, the second The intimacy level between the object and the first object is the first level.

In some embodiments of the present disclosure, based on the communication data and location data, the specific implementation method of obtaining the candidate chat robot associated with the preference tag of the second object is to determine, based on the communication data, the candidate whose conversation behavior with the first object satisfies the first condition. object; determine the living area of the first object according to the location data, and obtain the living area of the candidate object; determine that the coincidence degree between the living area of the first object and the living area of the candidate object is greater than or equal to the second preset threshold; determine the third object according to the candidate object Second Object; Gets the candidate chatbot associated with the second object's preference tag. The first condition may be that the number of calls to the first party in the past week is greater than or equal to 5 times and the call duration is no less than 30 seconds. The second preset threshold is typically 80%.

It should be noted that there are many ways to determine the second object based on the candidate object. Two examples will be given below:

As an example, the number of candidate objects may be one or multiple. When the number of candidate objects is one, the candidate object is determined as the second object. When the number of candidate objects is multiple, all candidate objects are determined as second objects.

As another example, the specific implementation of determining the second object based on the candidate object may also be to select the candidate objects whose coincidence degree between the living area of the first object and the living area of the candidate object is greater than or equal to the second preset threshold according to the number of calls by Sort from most to least, and determine the mobile phone numbers with the top three calls as the second object.

For example, according to the communication data of the first object, the mobile phone number with which the number of calls to the first object is greater than or equal to 5 times in the past week and the call duration is no less than 30 seconds is determined as a candidate that meets the first condition. Candidates whose living area coincides with the living area of the first object greater than or equal to 80% are sorted in descending order according to the number of calls, and the mobile phone numbers with the top three calls are determined as the second object, and the information related to the first object is obtained. Bi-object preference label association for candidate chatbots.

In this embodiment, the above-mentioned first candidate chat robot, the above-mentioned second candidate chat robot, and the above-mentioned third candidate chat robot may be determined as candidate chat robots for each of multiple recommendation categories.

In step S405, a 5G messaging chatbot recommendation list is determined based on the candidate chatbots in each of the multiple recommendation categories.

In the embodiments of the present disclosure, step S405 can be implemented in any manner in the embodiments of the present disclosure. The embodiments of the present disclosure do not limit this and will not be described again.

In step S406, the 5G messaging chatbot recommendation list is provided to the first object.

In the embodiments of the present disclosure, step S406 can be implemented in any manner in the embodiments of the present disclosure. The embodiments of the present disclosure do not limit this and will not be described again.

In embodiments of the present disclosure, 5G message chatbots are recommended based on browsing data, search data, location data and communication data, which improves the recommendation quality of 5G message chatbots and improves the relationship between 5G message chatbots and user preferences, user work or life. The degree of compliance with the scenario enhances the commercial value of the recommendation page and promotes the construction of the 5G ecosystem.

It is worth noting that the first candidate chatbot in this embodiment of the present disclosure can be obtained by building a preference recommendation model; the second candidate chatbot in this embodiment of the present disclosure can be obtained by building a location recommendation model; the third candidate chatbot in this embodiment of the present disclosure can be obtained by building a location recommendation model. Three candidate chatbots can be obtained by building intimacy recommendation models.

For example, the first candidate chatbot can be obtained by building a preference recommendation model. The preference recommendation model takes the browsing data and search data of the first object as input, and uses the preference tag and the first candidate chatbot as output. Among them, the preference tags can be catering, culture and tourism, current affairs, entertainment, novels, music, and parent-child. In order to facilitate the understanding of the preference recommendation model, an example is given.

Classify the first object's browsing records in the past three days into catering, culture and travel, current affairs, entertainment, novels, music, and parent-child, and record the number of views for each tag, labeled m1, m2, m3, m4, m5, m6, m7, and set the browsing mode coefficient to the initial value 0; classify the search records of the first object in the past three days into catering, cultural tourism, current affairs, entertainment, novels, music, and parent-child, and record the number of searches for each tag , marked as n1, n2, n3, n4, n5, n6, n7 respectively, and set the search mode coefficient to the initial value 1. The browsing mode coefficient and the search mode coefficient are adjusted according to the conversion rate of the 5G messaging chatbot in the 5G messaging chatbot recommendation list. Among them, the sum of the browsing mode coefficient and the search mode coefficient is fixed to 1.

Based on the number of views of each tag, the browsing weight of each tag is calculated through the above formula (1); based on the browsing mode coefficient and the browsing weight of each tag, the browsing coefficient of each tag is determined through the above formula (2). Based on the number of searches for each tag, the search weight of each tag is determined through the above equation (3); based on the search method coefficient and the number of searches for each tag, the search coefficient of each tag is determined through the above equation (4).

After obtaining the browsing coefficient and search coefficient of each tag, add the browsing coefficient and search coefficient of each tag, and sort the tags from large to small according to the added values. Based on the sorting results, select the top three labels in the sorting results. According to the selected three tags, the 5G message chatbot with the highest number of visits in each tag category in the past week is obtained from the 5G message chatbot product library, and the three selected tags and the three 5G messages corresponding to the selected tags are obtained. Messaging chatbot as output of preference recommendation model.

For example, the second candidate chatbot can be obtained by building a location recommendation model. The location recommendation model takes location data and preference labels output by the preference recommendation model as inputs, and uses the second candidate chatbot as output. In order to facilitate the understanding of the location recommendation model, an example is provided.

A real-time area of the first object is determined based on the real-time location data of the first object. Among them, the real-time area is a circular area with the latitude and longitude of the base station with the strongest connection signal at the current moment as the center and a radius of two hundred meters.

Based on the location data of the first object in the past month, count the longitude and latitude of the five base stations with the longest connection duration between 9:00 and 18:00 on working days, and calculate the working area of the first object based on the latitude and longitude of the base station.

Specifically, the working area of the first object can be calculated as follows: calculating the spatial distance between each base station and the other base stations, and calculating the average of the spatial distances between each base station and the other base stations. When the average spatial distance between a base station and other base stations is greater than 50 kilometers, the base station with the shortest connection duration is determined as an isolated base station, and the isolated base station is eliminated. After all isolated base stations are eliminated, a method for calculating the working area of the first object is determined based on the number of remaining base stations.

When the number of remaining base stations is 1, the working area of the first object is a circular area with the longitude and latitude of the remaining base stations as the center and a radius of 50 kilometers. When the number of remaining base stations is 2, the working area of the first object is a circular area with the midpoint longitude and latitude of the two base stations as the center and half the distance between the two base stations as the radius. When the number of remaining base stations is greater than or equal to 3, the remaining base stations are arranged in ascending order of longitude and latitude. When the longitudes are the same, they are arranged in ascending order of latitude. The base stations are added to the polygon coordinate set in order according to the sorting results, and the working area of the first object is the area surrounded by the longitude and latitude coordinates of the base station in the polygon coordinate set.

Based on the location data of the first object in the past month, count the longitude and latitude of the top five base stations where the first object has been connected for most time between 21:00 and 6:00 on working days, and calculate the living area of the first object based on the longitude and latitude of the base station. The calculation method of the living area of the first object is similar to the calculation method of the above-mentioned working area.

Determine the current recommended time based on the current date and time, and select the first area that matches the current recommended time from the real-time area, work area, and living area. From 9 to 18 o'clock on working days, the first area is the work area. Get the top three most visited chatbots in the work area in the past week; between 21 and 6 o'clock on working days, the first area is the living area. , get the top three chatbots with the most visits in the living area in the past week; during other working days and non-working days, get the top three chatbots with the most visits in the real-time area in the past week. When the obtained chatbots with the top three visits in the first area in the past week appear to be the same chatbots in the output results of the preference recommendation model, in order to prevent duplication with the output of the preference recommendation model, the chatbots are ranked in order by the number of visits. Chatbots later. The chatbot associated with the first region is determined as the second candidate chatbot, and the location recommendation model uses the second candidate chatbot as an output.

For example, the third candidate chatbot can be obtained by building an intimacy recommendation model. The intimacy recommendation model takes communication data and location data as input, and uses the third candidate chatbot as output. In order to facilitate the understanding of the location recommendation model, an example is provided.

Based on the communication data, the mobile phone number that has called the first target no less than 5 times in the past week and the call duration is no less than 30 seconds is determined as a candidate. Based on the location data, it is determined that the coincidence degree between the living area of the first object and the living area of the candidate object is greater than or equal to 80%, and the candidate object is determined as the second object. The second objects are sorted in descending order by the number of calls, and the output results of the preference recommendation models of the second objects with the top three calls are determined as the third candidate chatbot.

Figure 5 is a block diagram of a recommendation device for a 5G message chat robot provided according to an embodiment of the present disclosure. As shown in FIG. 5 , the recommendation device includes a first acquisition module 501 , a second acquisition module 502 , a determination module 503 and a recommendation module 504 .

The first acquisition module 501 is used to acquire multi-source data of the first object. The multi-source data includes browsing data, search data, location data and communication data.

The second acquisition module 502 is used to acquire candidate chat robots of multiple recommendation categories from the 5G messaging chat robot product library based on browsing data, search data, location data and communication data.

The determination module 503 is configured to determine a 5G message chat robot recommendation list based on the candidate chat robots in each of the multiple recommendation categories.

The recommendation module 504 is used to provide the 5G message chat robot recommendation list to the first object.

As an example, the recommendation module 505 provides the 5G message chat robot recommendation list to the first object in an implementation manner as follows: determining the recommended page layout information; based on the 5G message chat robot recommendation list, combining the recommended page layout information and multiple recommendation categories The recommended page information is generated in the order of arrangement in the recommended page; the recommended page information is sent to the terminal held by the first object, and the recommended page information is used by the terminal to display the 5G message chat robot recommendation list in the order of arrangement based on the recommended page layout information.

As an example, the recommendation module 505 may determine the recommended page layout information in the following manner: obtain the identification information of the terminal held by the first object; and determine the recommended page layout information corresponding to the terminal based on the identification information.

As an example, the second acquisition module 502 acquires candidate chatbots for multiple recommended categories from the 5G messaging chatbot product library based on browsing data, search data, location data and communication data as follows: Based on browsing data and search data, determine the preference label of the first object, and obtain the first candidate chat robot associated with the preference label from the 5G message chat robot product library; based on the location data and preference label, obtain the first candidate chat robot from the 5G message chat robot product library Two candidate chat robots; based on the communication data and location data, obtain the candidate chat robot associated with the preference tag of the second object, and determine the third candidate chat robot based on the candidate chat robot associated with the preference tag of the second object; wherein, the second The intimacy level between the object and the first object is the first level.

As an example, the second acquisition module 502 determines the preference tag of the first object based on the browsing data and search data in the following manner: based on multiple preset tags and browsing data, counting the number of views of each tag; Multiple tags and search data, count the number of searches for each tag; determine the browsing coefficient of each tag based on the browsing mode coefficient and the number of searches for each tag; determine the browsing coefficient of each tag based on the search mode coefficient and the number of searches for each tag The search coefficient of the tag; based on the browsing coefficient and the search coefficient of each tag, the preferred tag of the first object is determined from multiple tags.

As an example, the second acquisition module 502 can also be used to: obtain the conversion rate of the 5G message chatbot in the 5G message chatbot recommendation list; determine that the conversion rate is less than or equal to the first preset threshold; based on the conversion rate and the first The threshold is preset to adjust the browsing mode coefficient and the search mode coefficient; where the sum of the browsing mode coefficient and the search mode coefficient is 1.

As an example, the second acquisition module 502 may obtain the first candidate chat robot associated with the preference tag from the 5G message chat robot product library as follows: obtain the first candidate chat robot with the preference tag from the 5G message chat robot product library. The chatbot with the most visits within the time period; determine the chatbot with the most visits within the first time period in the preference tag as the first candidate chatbot associated with the preference tag.

As an example, the second acquisition module 502 acquires the second candidate chat robot from the 5G messaging chat robot product library based on the location data and preference tags in the following manner: determine the first object based on the real-time location data in the location data. the real-time area; determine the working area and living area of the first object according to the location data of the first object in the second time period in the location data; determine the current recommended time, and select the real-time area, working area and living area based on the current recommended time. In the area, select the first area that matches the current recommended time; based on the first area and the preference tag, obtain the chat robot associated with the first area from the 5G message chat robot product library, where the chat robot is different from the preference tag association the first candidate chatbot; determine the chatbot associated with the first region as the second candidate chatbot. Regarding the devices in the above embodiments, the specific manner in which each module performs operations has been described in detail in the embodiments related to the method, and will not be described in detail here.

As an example, the second acquisition module 502 determines the real-time area of the first object based on the real-time location data in the location data in the following manner: taking the longitude and latitude of the base station with the strongest signal connection at the current moment as the center of the circle, the first length is The area of the radius is determined as the real-time area of the first object.

As an example, the second acquisition module 502 determines the working area of the first object according to the position data of the first object in the second time period in the position data as follows: according to the position data of the first object in the position data. For the location data in the second time period, the statistical connection time is the longitude and latitude of the base stations at the first time point with the top N connection durations; where N is a positive integer; the work of the first object is determined based on the statistically obtained longitude and latitude of the N base stations. area.

As an example, when N is multiple, the second acquisition module 502 determines the working area of the first object based on the statistically obtained longitude and latitude of the N base stations in the following manner: based on the longitude and latitude of the N base stations, calculate each of the N base stations. The spatial distance between one base station and other base stations; average the N-1 spatial distances of each base station among the N base stations to obtain the average spatial distance of each base station among the N base stations; according to the average spatial distance among the N base stations Based on the average spatial distance and connection duration of each base station, isolated base stations are eliminated from the N base stations; based on the number of remaining base stations after eliminating the isolated base stations from the N base stations and the longitude and latitude of the remaining base stations, the working area of the first object is determined.

Optionally, the second acquisition module 502 determines the working area of the first object based on the number of remaining base stations after excluding isolated base stations from the N base stations and the longitude and latitude of the remaining base stations. The implementation method of determining the working area of the first object can be as follows: determining the number of remaining base stations as 1. Determine the area with the longitude and latitude of the remaining base stations as the center of the circle and the second length as the radius as the working area of the first object; determine the number of remaining base stations as 2, and use the midpoint longitude and latitude between the two remaining base stations as the center of the circle. The area where the distance between the two remaining base stations is half the radius is determined as the working area of the first object; it is determined that the number of remaining base stations is greater than or equal to 3, and the working area of the first object is determined based on the longitude and latitude of the three remaining base stations.

As an example, the second acquisition module 502 acquires the candidate chatbot associated with the preference tag of the second object based on the communication data and the location data in an implementation manner as follows: based on the communication data, it is determined that the call behavior with the first object satisfies the first requirement. Candidate object of the condition; determine the living area of the first object according to the location data, and obtain the living area of the candidate object; determine that the coincidence degree of the living area of the first object and the living area of the candidate object is greater than or equal to the second preset threshold; according to the candidate The object determines a second object; and obtains candidate chatbots associated with the preference tag of the second object.

As an example, the determination module 503 determines the 5G message chat robot recommendation list based on the candidate chat robots of multiple recommendation categories. The implementation method can be as follows: perform deduplication processing on the candidate chat robots of multiple recommendation categories, and then remove the duplicates. The chatbots obtained after reprocessing form the 5G message chatbot recommendation list.

According to embodiments of the present disclosure, the present disclosure also provides an electronic device and a non-transitory computer-readable storage medium.

As shown in FIG. 6 , FIG. 6 is a block diagram of an electronic device according to an embodiment of the present disclosure. Electronic devices are intended to refer to various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are examples only and are not intended to limit the implementation of the present application as described and/or claimed herein.

As shown in Figure 6, the electronic device includes: at least one processor 601, a memory 602 communicatively connected to the at least one processor 601, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses and can be mounted on a common motherboard or otherwise mounted as desired. The processor may process instructions executed within the electronic device, including instructions stored in or on memory to display graphical information of the GUI on an external input/output device, such as a display device coupled to the interface. In other embodiments, multiple processors and/or multiple buses may be used with multiple memories and multiple memories, if desired. Likewise, multiple electronic devices can be connected, each device providing part of the necessary operation (eg, as a server array, a set of blade servers, or a multi-processor system). In Figure 6, a processor 601 is taken as an example.

The memory 602 is the non-transitory computer-readable storage medium provided by the present disclosure. Wherein, the memory stores instructions executable by at least one processor, so that the at least one processor executes the recommendation method of the 5G messaging chatbot provided by the present disclosure. The non-transitory computer-readable storage medium of the present disclosure stores computer instructions, which are used to cause the computer to execute the recommended method of the 5G messaging chatbot provided by this application.

As a non-transient computer-readable storage medium, the memory 602 can be used to store non-transient software programs, non-transient computer executable programs and modules, such as program instructions/modules corresponding to the recommendation method of the 5G messaging chatbot in the embodiment of the present disclosure. (For example, the first acquisition module 501, the second acquisition module 502, the determination module 503 and the recommendation module 504 shown in Figure 5). The processor 501 executes various functional applications and data processing of the server by running non-transient software programs, instructions and modules stored in the memory 502, that is, implementing the recommended method of the 5G messaging chatbot in the above method embodiment.

The memory 602 may include a storage program area and a storage data area, wherein the storage program area may store an operating system and an application program required for at least one function; the storage data area may store information required for use of the electronic device according to the recommendation method of the 5G messaging chatbot. Created data, etc. In addition, memory 602 may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 602 optionally includes memories remotely located relative to the processor 601, and these remote memories can be connected to electronic devices of the recommendation method of the 5G messaging chatbot through a network. Examples of the above-mentioned networks include but are not limited to the Internet, intranets, local area networks, mobile communication networks and combinations thereof.

The electronic device of the 5G message chat robot recommendation method may also include: an input device 603 and an output device 604. The processor 601, the memory 602, the input device 603 and the output device 604 can be connected through a bus or other means. In Figure 6, connection through a bus is taken as an example.

The input device 603 can receive input numeric or character information, and generate key signal input related to user settings and function control of the electronic device, such as a touch screen, a keypad, a mouse, a trackpad, and a touch pad. , indicator stick, one or more mouse buttons, trackball, joystick and other input devices. Output devices 604 may include display devices, auxiliary lighting devices (eg, LEDs), tactile feedback devices (eg, vibration motors), and the like. The display device may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display, and a plasma display. In some implementations, the display device may be a touch screen.

The present disclosure also provides a computer program product, which, when executed by a computer, implements the functions of any of the above method embodiments.

Various implementations of the systems and techniques described herein may be implemented in digital electronic circuitry, integrated circuit systems, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include implementation in one or more computer programs executable and/or interpreted on a programmable system including at least one programmable processor, the programmable processor The processor, which may be a special purpose or general purpose programmable processor, may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device. An output device.

These computing programs (also referred to as programs, software, software applications, or code) include machine instructions for programmable processors, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine language Calculation program. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or means for providing machine instructions and/or data to a programmable processor ( For example, magnetic disks, optical disks, memories, programmable logic devices (PLD)), including machine-readable media that receive machine instructions as machine-readable signals. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.

To provide interaction with a user, the systems and techniques described herein may be implemented on a computer having a display device (eg, a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user ); and a keyboard and pointing device (eg, a mouse or a trackball) through which a user can provide input to the computer. Other kinds of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and may be provided in any form, including Acoustic input, voice input or tactile input) to receive input from the user.

The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., A user's computer having a graphical user interface or web browser through which the user can interact with implementations of the systems and technologies described herein), or including such backend components, middleware components, or any combination of front-end components in a computing system. The components of the system may be interconnected by any form or medium of digital data communication (eg, a communications network). Examples of communication networks include: local area network (LAN), wide area network (WAN), the Internet, and blockchain networks.

Computer systems may include clients and servers. Clients and servers are generally remote from each other and typically interact over a communications network. The relationship of client and server is created by computer programs running on corresponding computers and having a client-server relationship with each other. The server can be a cloud server, also known as cloud computing server or cloud host. It is a host product in the cloud computing service system to solve the problem of traditional physical host and VPS service ("Virtual Private Server", or "VPS" for short) Among them, there are defects such as difficult management and weak business scalability. The server can also be a distributed system server or a server combined with a blockchain.

Other embodiments of the invention will be readily apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary technical means in the technical field that are not disclosed in the present disclosure. . It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.

It is to be understood that the present invention is not limited to the precise construction described above and illustrated in the accompanying drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the invention is limited only by the appended claims.

Claims (18)

1. A recommendation method for a 5G message chat robot, comprising:

acquiring multi-source data of a first object, wherein the multi-source data comprises browsing data, searching data, position data and communication data;

based on the browsing data, the searching data, the position data and the communication data, obtaining candidate chat robots of a plurality of recommendation categories from a 5G message chat robot product library;

determining a recommendation list of the 5G message chat robot based on the candidate chat robots of the recommendation categories;

and providing the 5G message chat robot recommendation list to the first object.

2. The method of claim 1, wherein said providing the 5G message chat robot recommendation list to the first object comprises:

determining recommended page layout information;

generating recommended page information by combining the recommended page layout information and the arrangement sequence of the plurality of recommended categories in a recommended page based on the 5G message chat robot recommendation list;

And sending the recommended page information to a terminal held by the first object, wherein the recommended page information is used for displaying the 5G message chat robot recommended list according to the arrangement sequence by the terminal based on the recommended page layout information.

3. The method of claim 2, wherein the determining recommended page layout information comprises:

acquiring the identification information of the terminal held by the first object;

and determining recommended page layout information corresponding to the terminal according to the identification information.

4. The method of claim 1, wherein the obtaining candidate chat robots for each of a plurality of recommendation categories from a 5G message chat robot product library based on the browsing data, the search data, the location data, and the communication data comprises:

determining a preference tag of the first object based on the browsing data and the searching data, and acquiring a first candidate chat robot associated with the preference tag from the 5G message chat robot product library;

acquiring a second candidate chat robot from the 5G message chat robot product library based on the location data and the preference tag;

Acquiring a candidate chat robot associated with the preference tag of the second object based on the communication data and the position data, and determining a third candidate chat robot according to the candidate chat robot associated with the preference tag of the second object; wherein the affinity level of the second object with the first object is a first level.

5. The method of claim 4, wherein the determining a preference tag for the first object based on the browsing data and the search data comprises:

counting the browsing times of each tag based on a plurality of preset tags and the browsing data;

counting the searching times of each tag based on the plurality of tags and the searching data;

determining the browsing coefficient of each tag based on the browsing mode coefficient and the browsing times of each tag;

determining a search coefficient of each tag based on the search mode coefficient and the search times of each tag;

and determining the preference label of the first object from the labels based on the browsing coefficient and the searching coefficient of each label.

6. The method of claim 5, wherein the method further comprises:

Acquiring the conversion rate of the 5G message chat robot in the recommendation list of the 5G message chat robot;

determining that the conversion rate is less than or equal to a first preset threshold;

based on the conversion rate and the first preset threshold, adjusting the browsing mode coefficient and the searching mode coefficient; wherein, the sum of the browsing mode coefficient and the searching mode coefficient is 1.

7. The method of any of claims 4-6, wherein the retrieving the first candidate chat robot associated with the preference tag from the 5G message chat robot product library comprises:

obtaining the chat robot with the largest access amount in the first time period in the preference tag from the 5G message chat robot product library;

and determining the chat robot with the largest access amount in the first time period in the preference label as a first candidate chat robot associated with the preference label.

8. The method of claim 4, wherein the obtaining a second candidate chat robot from the 5G message chat robot product library based on the location data and the preference tag comprises:

determining a real-time area of the first object according to real-time position data in the position data;

Determining a working area and a living area of the first object according to the position data of the first object in the second time period in the position data;

determining a current recommended time, and selecting a first area matched with the current recommended time from the real-time area, the working area and the living area based on the current recommended time;

acquiring chat robots associated with the first region from the 5G message chat robot product library based on the first region and the preference tag, wherein the chat robots are different from first candidate chat robots associated with the preference tag;

a chat robot associated with the first zone is determined to be the second candidate chat robot.

9. The method of claim 8, wherein the real-time location data comprises a longitude and latitude of a base station with a strongest signal connection at a current time of a terminal held by the first object; the determining the real-time area of the first object according to the real-time position data in the position data comprises the following steps:

and determining an area with the first length as a radius as a real-time area of the first object by taking the longitude and latitude of the base station with the strongest signal connection at the current moment as a circle center.

10. The method of claim 8, wherein the position data of the first object in the second time period includes longitude and latitude corresponding to a plurality of base stations connected to the terminal held by the first object in the second time period, and connection time and connection duration of each base station; determining a working area of the first object according to the position data of the first object in the second time period in the position data, wherein the working area comprises the following steps:

according to the position data of the first object in the second time period in the position data, counting the longitude and latitude of the base station with the connection time being at the first time point and the connection time length being arranged at the front N; wherein, N is a positive integer;

and determining the working area of the first object based on N base stations obtained through statistics.

11. The method of claim 10, wherein N is a plurality; the determining the working area of the first object based on the N base stations obtained through statistics comprises the following steps:

based on the longitude and latitude of the N base stations, calculating the space distance between each base station in the N base stations and other base stations;

averaging the N-1 space distances of each base station in the N base stations to obtain a space distance average value of each base station in the N base stations;

Removing isolated base stations from the N base stations according to the average value of the space distance of each base station in the N base stations and the connection time length;

and determining the working area of the first object based on the number of the residual base stations and the longitude and latitude of the residual base stations after the isolated base stations are removed from the N base stations.

12. The method of claim 11, wherein the determining the working area of the first object based on the number of remaining base stations of the N base stations from which the orphan base station is eliminated and the latitude and longitude of the remaining base stations comprises at least one of:

determining the number of the remaining base stations to be 1, and determining an area with the longitude and latitude of the remaining base stations as a circle center and the second length as a radius as a working area of the first object;

determining the number of the remaining base stations as 2, and determining an area with the middle-point longitude and latitude among 2 remaining base stations as a circle center and the distance between 2 remaining base stations as a half of the radius as a working area of the first object;

and determining that the number of the residual base stations is greater than or equal to 3, and determining the working area of the first object based on the longitudes and latitudes of the 3 residual base stations.

13. The method of claim 8, wherein determining a living area of the first subject based on the location data of the first subject within a second time period from among the location data comprises:

according to the position data of the first object in the second time period in the position data, counting the longitude and latitude of the base station with the connection time being at the second time point and the connection time length being arranged in the front N; wherein, N is a positive integer;

and determining the living area of the first object based on N base stations obtained through statistics.

14. The method of claim 4, wherein the obtaining a candidate chat robot associated with a preference tag of a second object based on the communication data and the location data comprises:

determining a candidate object which meets a first condition with the conversation behavior of the first object based on the communication data;

determining a living area of the first object according to the position data, and acquiring the living area of the candidate object;

determining that the coincidence degree of the living area of the first object and the living area of the candidate object is larger than or equal to a second preset threshold;

determining the second object according to the candidate object;

A candidate chat robot associated with a preference tag of the second object is obtained.

15. The method of claim 1, wherein the determining a list of 5G message chat robot recommendations based on candidate chat robots for each of the plurality of recommendation categories comprises:

and performing de-duplication processing on the candidate chat robots of each of the plurality of recommendation categories, and forming the chat robots obtained after the de-duplication processing into the recommendation list of the 5G message chat robot.

16. A recommendation device for a 5G message chat robot, comprising:

the first acquisition module is used for acquiring multi-source data of the first object, wherein the multi-source data comprises browsing data, searching data, position data and communication data;

the second acquisition module is used for acquiring candidate chat robots of each of a plurality of recommendation categories from a 5G message chat robot product library based on the browsing data, the searching data, the position data and the communication data;

a determining module, configured to determine a recommendation list of the 5G message chat robot based on the candidate chat robots of each of the plurality of recommendation categories;

and the recommending module is used for providing the recommending list of the 5G message chat robot for the first object.

17. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 15.

18. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1 to 15.