CN114840658A

CN114840658A - Evaluation reply method, electronic device, and computer storage medium

Info

Publication number: CN114840658A
Application number: CN202210789719.2A
Authority: CN
Inventors: 赖健勋; 刘畅; 徐昊; 王雪飞; 刘良友
Original assignee: Zhejiang Koubei Network Technology Co Ltd
Current assignee: Zhejiang Koubei Network Technology Co Ltd
Priority date: 2022-07-06
Filing date: 2022-07-06
Publication date: 2022-08-02
Anticipated expiration: 2042-07-06
Also published as: CN114840658B

Abstract

The embodiment of the application discloses an evaluation reply method, electronic equipment and a computer storage medium. Wherein, the method comprises the following steps: receiving target evaluation information; determining target keywords in the target evaluation information according to a preset keyword lexicon; the preset keyword lexicon comprises a plurality of keywords; and determining target reply information corresponding to the target evaluation information according to the target keywords, so that the target reply information corresponding to the customer evaluation is pertinently recommended according to the customer evaluation, namely the target keywords in the target evaluation information, and the quality and efficiency of manually replying the customer evaluation by the merchant are greatly improved.

Description

Evaluation reply method, electronic device, and computer storage medium

Technical Field

The present application relates to the field of information technologies, and in particular, to an evaluation reply method, an electronic device, and a computer storage medium.

Background

The return evaluation is an operation frequently performed in the daily business of the merchant. Some users can see the customer evaluation before ordering, and the content replied by the merchant can be seen by other customers who have not ordered, so the file quality replied by the merchant can also influence the ordering conversion rate of the shop. When a merchant carries out manual reply on customer evaluation, certain writing ability is needed, especially poor evaluation which needs to be manually replied, and the evaluation manual reply time length reaches more than 1min and greatly exceeds the average reply time length.

Disclosure of Invention

The embodiment of the application provides an evaluation reply method, electronic equipment and a computer storage medium, and the quality and the efficiency of manually replying customer evaluation by a merchant are greatly improved by determining and recommending target reply information corresponding to the customer evaluation according to keywords in the customer evaluation. The technical scheme is as follows:

in a first aspect, an embodiment of the present application provides an evaluation reply method, including:

receiving target evaluation information;

determining a target keyword in the target evaluation information according to a preset keyword lexicon; the preset keyword lexicon comprises a plurality of keywords;

and determining target reply information corresponding to the target evaluation information according to the target keywords.

In a possible implementation manner, the determining a target keyword in the target evaluation information according to a preset keyword lexicon includes:

matching keywords in a preset keyword lexicon with the target evaluation information to obtain the matching degree of the keywords and the target evaluation information;

and determining the keywords with the matching degree larger than or equal to a preset threshold value as the target keywords in the target evaluation information.

In one possible implementation manner, the determining, according to the target keyword, target reply information corresponding to the target evaluation information includes:

determining a scene corresponding to the target keyword and an evaluation result corresponding to the scene; the scene is used for representing the evaluation dimension corresponding to the target keyword;

and determining target reply information corresponding to the target evaluation information according to the scene and the evaluation result corresponding to the scene.

In a possible implementation manner, after determining the scene corresponding to the target keyword and the evaluation result corresponding to the scene, the method further includes:

and displaying scene information and a target reply strategy corresponding to the target evaluation information according to the scene corresponding to the target keyword and the evaluation result corresponding to the scene.

In a possible implementation manner, the number of the target keywords is at least two, and the at least two target keywords include a first type of target keywords and a second type of target keywords; the first type of target keywords are used for representing positive evaluation results; the second category target keywords are used for representing non-positive evaluation results;

the determining of the target reply information corresponding to the target evaluation information according to the target keyword includes:

determining scenes corresponding to the first type of target keywords and scenes corresponding to the second type of target keywords; the scene is used for representing the evaluation dimension corresponding to the target keyword;

and determining first target reply information corresponding to the target evaluation information according to the scene corresponding to the first type of target keywords, and determining second target reply information corresponding to the target evaluation information according to the scene corresponding to the second type of target keywords.

In a possible implementation manner, after determining the target reply information corresponding to the target evaluation information according to the target keyword, the method further includes:

determining an evaluation result corresponding to the target evaluation information;

determining a recommendation sequence of the first target reply message and the second target reply message according to an evaluation result corresponding to the target evaluation message;

and recommending the first target reply information and the second target reply information according to the recommendation sequence.

determining the third target reply message according to the first target reply message and the second target reply message; and the third target reply message is obtained by splicing the first target reply message and the second target reply message according to a preset rule.

In a possible implementation manner, the preset keyword lexicon further includes a mapping relationship between each keyword and a scene;

the determining of the scene corresponding to the target keyword includes:

and determining a scene corresponding to the target keyword according to the target keyword and the mapping relation.

In a possible implementation manner, after receiving the target evaluation information, the method further includes:

recommending general reply information according to the evaluation result corresponding to the target evaluation information; the general reply information corresponds to an evaluation result corresponding to each of the target evaluation information.

In a second aspect, an embodiment of the present application provides another evaluation reply method, including:

receiving target evaluation information;

responding to preset operation, and acquiring target reply information; the target reply information is determined by the target keywords in the target evaluation information; the target keyword is determined according to a preset keyword lexicon and the target evaluation information; the preset keyword lexicon comprises a plurality of keywords.

In a third aspect, an embodiment of the present application provides an evaluation response device, where the device includes:

the receiving module is used for receiving target evaluation information;

the first determining module is used for determining the target keywords in the target evaluation information according to a preset keyword lexicon; the preset keyword lexicon comprises a plurality of keywords;

and the second determining module is used for determining target reply information corresponding to the target evaluation information according to the target keyword.

In a fourth aspect, an embodiment of the present application provides another evaluation response apparatus, including:

the receiving module is used for receiving target evaluation information;

the acquisition module is used for responding to preset operation and acquiring target reply information; the target reply information is determined by the target keywords in the target evaluation information; the target keyword is determined according to a preset keyword lexicon and the target evaluation information; the preset keyword lexicon comprises a plurality of keywords.

In a fifth aspect, an embodiment of the present application provides an electronic device, including: a processor and a memory;

the processor is connected with the memory;

the memory is used for storing executable program codes;

the processor reads the executable program code stored in the memory to execute a program corresponding to the executable program code, so as to execute the method provided by the first aspect or any one of the possible implementation manners of the first aspect or the second aspect of the embodiments of the present application.

In a sixth aspect, embodiments of the present application provide a computer storage medium storing a plurality of instructions adapted to be loaded by a processor and to perform the method steps provided in the first aspect of the present application or any one of the possible implementations of the first aspect or the second aspect.

In one or more embodiments of the application, the target reply information corresponding to the target evaluation information can be determined according to the target keywords matched with the preset keyword lexicon in the target evaluation information, and the target reply information is recommended to the merchant, so that the target reply information can be recommended to the target evaluation information (customer evaluation) in a very targeted manner, the quality and the efficiency of the merchant for manually writing a file to reply the customer evaluation are greatly improved, and the order placing conversion rate of the merchant is improved. In one or more embodiments of the present application, the target reply information corresponding to the target evaluation information may be determined only according to a scene corresponding to the target keyword matched with the preset keyword lexicon in the target evaluation information and an evaluation result corresponding to the scene, so that while the target reply information required to be stored in the server is reduced, the quality and efficiency of a merchant for manually writing a document to reply to the evaluation of a customer may also be improved, the merchant is guided to improve the service quality, efficient and high-quality evaluation reply is provided for the customer, and the satisfaction and use stickiness of the user (the merchant and the customer) are improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.

Fig. 1 is a schematic structural diagram of an evaluation reply system according to an exemplary embodiment of the present application;

fig. 2 is a schematic flowchart of an evaluation reply method according to an exemplary embodiment of the present application;

fig. 3A is a schematic diagram of a page of a second user (merchant) end according to an exemplary embodiment of the present application;

fig. 3B is a schematic structural diagram of a first preset mapping table according to an exemplary embodiment of the present application;

fig. 3C is a schematic diagram of another second user (merchant) side page provided in an exemplary embodiment of the present application;

fig. 4 is a schematic flowchart of an evaluation reply method according to an exemplary embodiment of the present application;

fig. 5 is a schematic structural diagram of a preset keyword lexicon according to an exemplary embodiment of the present application;

fig. 6A is a schematic diagram of another second user (merchant) end page provided in an exemplary embodiment of the present application;

fig. 6B is a schematic structural diagram of a second preset mapping table according to an exemplary embodiment of the present application;

fig. 6C is a schematic diagram of another second user (merchant) end page provided in an exemplary embodiment of the present application;

fig. 6D is a schematic structural diagram of a third preset mapping table according to an exemplary embodiment of the present application;

fig. 7A is a schematic flowchart of another evaluation reply method according to an exemplary embodiment of the present application;

fig. 7B is a flowchart illustrating a method for recommending a target reply message according to an exemplary embodiment of the present application;

fig. 8 is a schematic structural diagram of a fourth preset mapping table according to an exemplary embodiment of the present application;

fig. 9A-9B are schematic views of another second user (merchant) end page provided in an exemplary embodiment of the present application;

fig. 10 is a schematic flow chart of another evaluation reply method according to an exemplary embodiment of the present application;

fig. 11 is a schematic structural diagram of a fifth preset mapping table according to an exemplary embodiment of the present application;

12A-12B are schematic views of another second user (merchant) end page provided by an exemplary embodiment of the present application;

13A-13C are schematic views of another second user (merchant) end page provided by an exemplary embodiment of the present application;

fig. 14 is a schematic flow chart of another evaluation reply method according to an exemplary embodiment of the present application;

fig. 15 is a schematic structural diagram of an evaluation response device according to an exemplary embodiment of the present application;

fig. 16 is a schematic structural diagram of another evaluation response device according to an exemplary embodiment of the present application;

fig. 17 is a schematic structural diagram of an electronic device according to an exemplary embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.

The terms "first," "second," "third," and the like in the description and in the claims, and in the drawings described above, are used for distinguishing between different objects and not necessarily for describing a particular sequential order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.

Referring to fig. 1, fig. 1 is a schematic diagram illustrating an architecture of an evaluation reply system according to an exemplary embodiment of the present application. As shown in fig. 1, the evaluation reply system may include: a first terminal cluster, a server 120 and a second terminal cluster. Wherein:

the first terminal cluster may be a first user (customer) terminal, and specifically includes one or more first user terminals, where the plurality of first user terminals may include a first user terminal 110a, a first user terminal 110b, a first user terminal 110c …, and the like. A first user (customer) version of software may be installed in the first terminal cluster to implement functions such as online input of customer evaluation, i.e., target evaluation information, by the first user (customer). Any one first user end in the first terminal cluster can establish a data relationship with the network, and establish a data connection relationship with the server 120 and any one second user end in the second terminal cluster through the network, so that the functions of submitting customer evaluation, namely target evaluation information, to the server 120 through the network, receiving target reply information sent by the second user (merchant) end in the second terminal cluster corresponding to the target evaluation information through the network, and the like are realized. Any one of the first user (customer) terminals in the first terminal cluster may be, but is not limited to, a mobile phone, a tablet computer, a notebook computer, and the like, in which the first user (customer) version software is installed.

The server 120 may be a server capable of recommending multiple reply messages, and may implement functions of receiving, through a network, target evaluation information, which is customer evaluation submitted by any one of first user (customer) terminals in a first terminal cluster, sending, through the network, the target evaluation information to a second user (merchant) terminal in a second terminal cluster corresponding to the target evaluation information, and recommending target reply information and a target reply policy corresponding to the target evaluation information. The server 120 may be, but is not limited to, a hardware server, a virtual server, a cloud server, and the like.

The second terminal cluster may be a second user (merchant) terminal, and specifically includes one or more second user (merchant) terminals, where the plurality of second user terminals may include a second user terminal 130a, a second user terminal 130b, a second user terminal 130c …, and the like. And second user (merchant) version software can be installed in the second terminal cluster and is used for realizing the functions of inputting reply information corresponding to customer evaluation and selecting target reply information corresponding to target evaluation information on line by the second user (merchant). Any one second user end in the second terminal cluster can establish a data relationship with the network, and establish a data connection relationship with the server 120 and any one first user end in the first terminal cluster through the network, so that the functions of receiving target reply information corresponding to the customer evaluation (target evaluation information) recommended by the server 120 through the network, sending the target reply information to the first user end (customer) in the first terminal cluster corresponding to the target evaluation information, and the like are realized. Any second user (merchant) end in the second terminal cluster may be, but is not limited to, a mobile phone, a tablet computer, a notebook computer, and the like, which are installed with second user (merchant) version software.

The network may be a medium providing a communication link between any one first user (customer) end in the first terminal cluster and the server 120 or between any one second user (business) end in the second terminal cluster and the server 120 or between any one first user (customer) end in the first terminal cluster and any one second user (business) end in the second terminal cluster, and may also be an internet including a network device and a transmission medium, which is not limited thereto. The transmission medium may be a wired link (such as, but not limited to, coaxial cable, fiber optic cable, and Digital Subscriber Line (DSL), etc.) or a wireless link (such as, but not limited to, wireless fidelity (WIFI), bluetooth, and mobile device network, etc.).

It is to be understood that the number of the first terminal cluster, the second terminal cluster, and the server 120 in the evaluation reply system shown in fig. 1 is merely an example, and any number of the first user (customer) end, the second user (merchant) end, and the server may be included in the evaluation reply system in a specific implementation. The embodiment of the present application is not particularly limited to this. For example, but not limiting of, server 120 may be a server cluster of multiple servers.

Because a certain writing capacity is needed when a traditional merchant manually replies to customer evaluation, if the writing capacity of the merchant is weak and the platform has no guidance, the problems of poor manual reply quality and low reply efficiency of the merchant on the customer evaluation can be caused; meanwhile, the problem of feedback of the customer can not be effectively replied, so that the transaction is influenced, namely the ordering conversion rate of the shop is influenced. In order to solve the above problem, an evaluation response method according to an embodiment of the present application is described below with reference to fig. 1. Specifically, refer to fig. 2, which is a flowchart illustrating an evaluation reply method according to an exemplary embodiment of the present application. As shown in fig. 2, the evaluation reply method includes the following steps:

step 201, receiving target evaluation information.

Specifically, when a customer inputs target evaluation information, which is customer evaluation, in a first user (customer) version of software installed on a first user (customer) side, the first user (customer) side transmits the target evaluation information to a server through a network, so that the server can receive the target evaluation information input by the customer in the first user (customer) version of software through the network.

Illustratively, as shown in fig. 3A, the server can receive target evaluation information 310 "spicy crayfish is not fresh, and the feeling is done by shrimp which is dead for a long time, and is really bad" which is input by a first user (customer) version software by a customer a and sent by a first user (customer) through a network.

Step 202, determining a target keyword in the target evaluation information according to a preset keyword lexicon.

Specifically, after receiving target evaluation information input by a customer at a first user (customer) end, the server determines a target keyword in the target evaluation information according to a plurality of keywords included in a preset keyword lexicon. The target evaluation information includes text information of customer evaluation. That is, the server may calculate semantic correlations between a plurality of keywords included in the preset keyword lexicon and target keywords in the target evaluation information, and then determine M keywords having the highest semantic correlations or keywords having semantic correlations greater than a preset correlation threshold as the target keywords in the target evaluation information. M is a positive integer. The number of the target keywords in the target evaluation information determined according to the preset keyword lexicon may be one or more, which is not limited in the present application.

Optionally, after receiving the target evaluation information input by the customer at the first user (customer) end, the server may further match each keyword in a preset keyword lexicon with the target evaluation information to obtain a matching degree of each keyword with the target evaluation information, and then determine N keywords with the highest matching degree as the target keywords in the target evaluation information. The preset keyword lexicon comprises a plurality of keywords. The keywords may include freshness, smell, attitude difference, and the like, and may be preset according to actual conditions, which is not limited in this application. The above N is a positive integer.

Optionally, after receiving the target evaluation information input by the customer at the first user (customer) end, the server may further match keywords in a preset keyword lexicon with the target evaluation information to obtain a matching degree between the keywords and the target evaluation information, and then determine keywords with the matching degree greater than or equal to a preset threshold as the target keywords in the target evaluation information. That is, the server may sequentially match the keywords in the preset keyword lexicon with the target evaluation information until a keyword having a matching degree with the target evaluation information greater than or equal to a preset threshold is matched, end the matching, and determine the keyword having the matching degree greater than or equal to the preset threshold as the target keyword in the target evaluation information, where the number of the target keywords in the target evaluation information is 1. In order to more comprehensively reply the target evaluation information of the customer, the server may also match each keyword in a preset keyword lexicon with the target evaluation information to obtain a matching degree of each keyword with the target evaluation information, and then determine the keyword with the matching degree greater than or equal to a preset threshold as the target keyword in the target evaluation information, so as to more comprehensively determine all the target keywords in the target evaluation information, and further improve the quality of the merchant manually writing the document to reply the evaluation of the customer. The preset keyword lexicon comprises a plurality of keywords. The keywords may include freshness, smell, attitude difference, and the like, and may be preset according to actual conditions, which is not limited in this application. The preset threshold may be 0.1, 0.6, 0.99, etc., which is not limited in this application.

For example, if the target evaluation information 310 "spicy crayfish is not fresh, the shrimp is dead for a long time and the feeling is too bad" as shown in fig. 3A is received, and the preset threshold is 0.15 and the preset keyword lexicon includes 4 keywords of fresh, not fresh, fishy smell and attitude difference, the 4 keywords in the preset keyword lexicon can be respectively matched with the target evaluation information 310, so as to obtain the matching degrees "0.1, 0.15, 0, and 0.005" of the 4 keywords "fresh, not fresh, fishy smell and attitude difference" respectively corresponding to the target evaluation information 310, and the keyword "not fresh" with the matching degree greater than or equal to 0.15 is determined as the target keyword in the target evaluation information 310.

And step 203, determining target reply information corresponding to the target evaluation information according to the target keywords.

Specifically, reply information corresponding to the target keyword may be queried from the first preset mapping table according to the target keyword, and the reply information may be determined as target reply information corresponding to the target evaluation information. The first preset mapping table is used for representing the corresponding relation between each target keyword and each reply message. The server can also send (recommend) the target reply information to a second user (merchant) end, and the second user (merchant) end displays and recommends the target reply information to the merchant so that the merchant corresponding to the second user (merchant) end can refer to the target reply information or directly select the target reply information to use for manual reply without high writing capacity and excessive thinking time when manually replying customer evaluation.

For example, if the target evaluation information 310 shown in fig. 3A is received, that is, "spicy crayfish is stale," shrimp that died for a long time is sensed to be too bad, "and it is determined that the target keyword in the target evaluation information 310 is" stale, "it may be determined that the target reply information corresponding to the target evaluation information 310 is" sorry with relatives, and the material problem store that you feed back places a lot of importance, xxxxxxxx, according to the first preset mapping table shown in fig. 3B. And (4) obtaining a satisfied result. Then, the server may further send (recommend) the target reply information to a second user (merchant) end, and after the second user (merchant) end receives the target reply information, as shown in fig. 3C, the target reply information 320 may be displayed and recommended to the merchant, so that when a merchant corresponding to the second user (merchant) end manually replies the customer evaluation, the merchant may refer to the target reply information 320 or directly click the "use" control to select the target reply information 320 for manual reply.

Optionally, the number of the target keywords includes at least two. The server may also query the at least two pieces of reply information corresponding to the at least two target keywords from a first preset mapping table according to the at least two target keywords, and determine the at least two pieces of reply information as the target reply information corresponding to the target evaluation information. Namely, the determined target reply information corresponding to the target evaluation information comprises at least two pieces. The first preset mapping table is used for representing the corresponding relation between each target keyword and each reply message.

According to the embodiment of the application, the target keywords in the target evaluation information (customer evaluation) are determined according to the preset keyword lexicon, the target reply information corresponding to the target evaluation information is determined according to the target keywords, and then the target reply information is recommended to the merchant, so that the target reply information is recommended to the target evaluation information (customer evaluation) in a very targeted manner, the quality and the efficiency of the merchant for manually writing the file to reply the customer evaluation are greatly improved, the order placing conversion rate of the store is improved, the merchant can be guided to improve the service quality, the efficient and high-quality evaluation reply is realized for the customer, and the satisfaction degree and the use viscosity of the user (the merchant and the customer) are improved.

In the process of recommending the target reply information to the merchant, if each keyword corresponds to at least one reply information, since the keywords are multiple, developers need to prepare a large amount of reply information according to different keywords, which will cause the problems of overlarge workload of the developers, slow operation speed caused by overlarge reply information needing to be stored in the server, and the like. In order to solve the above problem, another evaluation recovery method provided in the embodiments of the present application is described next. Specifically, refer to fig. 4, which is a schematic flow chart of another evaluation reply method according to an exemplary embodiment of the present application. As shown in fig. 4, the evaluation reply method includes the following steps:

step 401, receiving target evaluation information.

Specifically, step 401 is identical to step 201, and is not described herein again.

Step 402, determining a target keyword in the target evaluation information according to a preset keyword lexicon.

Specifically, step 402 is identical to step 202, and is not described herein again.

And step 403, determining a scene corresponding to the target keyword and an evaluation result corresponding to the scene.

Specifically, the preset keyword lexicon includes not only a plurality of keywords, but also a mapping relationship between each keyword and a scene. The target evaluation information not only includes text information of customer evaluation, but also includes evaluation results of the customer for each scene. The evaluation result may include 0, 1, 1.5, 5, etc., and may also include good score, medium score, bad score, etc., which is not limited in the present application.

Optionally, the number of the target keywords includes at least one, and the at least one target keyword corresponds to the same scene. The scene corresponding to at least one target keyword in the target evaluation information can be determined according to the at least one target keyword and the mapping relation, and an evaluation result corresponding to the scene can be inquired from the target evaluation information. And the scene is used for representing the evaluation dimension corresponding to the target keyword. The evaluation dimensions may include taste, service, cost/performance, packaging, richness, appearance, distribution, food safety, and are not limited in this respect.

Exemplarily, as shown in fig. 5, it is a schematic structural diagram of a preset keyword lexicon according to an exemplary embodiment of the present application. The preset keyword word library not only comprises a plurality of keywords, but also comprises a mapping relation between each keyword and a scene. If the target keyword in the target evaluation information is "fresh", the scene corresponding to the target keyword "fresh" may be determined as "food safety" according to the mapping relationship between each keyword and the scene as shown in fig. 5, and the evaluation result corresponding to "food safety" may be queried from the target evaluation information.

Optionally, the number of the target keywords includes at least two, and is not limited to a case where a plurality of target keywords correspond to the same scene, and the scenes corresponding to the at least two target keywords may also include at least two. That is, at least two scenes corresponding to at least two target keywords may be determined according to the at least two target keywords in the target evaluation information and the mapping relationship, and an evaluation result corresponding to each scene may be queried from the target evaluation information. The number of the target keywords is greater than or equal to the number of scenes corresponding to the target keywords, that is, one scene may correspond to at least one target keyword.

Step 404, determining the target reply information corresponding to the target evaluation information according to the scene and the evaluation result corresponding to the scene.

Specifically, the server may search, according to a scene corresponding to a target keyword in the target evaluation information and an evaluation result corresponding to the scene, reply information corresponding to the scene and the evaluation result from a second preset mapping table, and determine the reply information as the target reply information corresponding to the target evaluation information. The second preset mapping table is used for representing each scene and the corresponding relationship between the evaluation result corresponding to each scene and at least one piece of reply information. That is, the number of the reply information corresponding to each scene and the evaluation result corresponding to the scene may be one or multiple according to the second preset mapping table, and specifically, the number of the reply information preset by the developer needs to be referred to, that is, the developer may store one or at least two reply information corresponding to each scene and the evaluation result corresponding to the scene in the second preset mapping table, which is not limited in the present application.

Illustratively, if the received target rating information 610 as shown in FIG. 6A includes a text message 611 rated by customer B that "the sauerkraut fish is too difficult to eat", and an evaluation result 612 of the customer B for each scene, wherein the target evaluation information 610 includes a scene "taste" corresponding to the target keyword "stubborn" of the text information 611 evaluated by the customer B, and it can be seen from the target evaluation information 610 in fig. 6A that the evaluation result 612 corresponding to the scene "taste" is "1 star", the server may find the reply information "that is sorry and that is a relative, xxxxxxxxxx, according to the second preset mapping table shown in fig. 6B, and that corresponds to the scene" taste "and the evaluation result 612" 1 star ", and we may subsequently make a taste improvement, and may write a remark to tell you a taste preference —" when eating next time, and determine the reply information as the target reply information corresponding to the target evaluation information. After the merchant clicks the reply control 620 shown in fig. 6A, the server may receive a reply instruction triggered by the merchant at the second user end through the network, so as to send (recommend) the target reply information to the second user (merchant) end, and after the second user (merchant) end receives the target reply information, as shown in fig. 6C, the server may display and recommend the target reply information 630 to the merchant, so that when the merchant corresponding to the second user (merchant) end manually replies to the customer evaluation, the target reply information 630 may be referred to or the "use" control is directly clicked to select the target reply information 630 for manual reply.

Optionally, when at least two scenes are determined according to at least two target keywords, the server may search, according to each scene and the evaluation result corresponding to each scene, the reply information corresponding to each scene and the evaluation result corresponding to each scene from a second preset mapping table, and determine the reply information as the target reply information corresponding to the target evaluation information. The second preset mapping table is used for representing each scene and the corresponding relationship between the evaluation result corresponding to each scene and at least one piece of reply information. At this time, the number of the target reply messages is greater than or equal to the number of the scenes.

And 405, displaying scene information and a target reply strategy corresponding to the target evaluation information according to the scene corresponding to the target keyword and the evaluation result corresponding to the scene.

Specifically, after determining a scene corresponding to a target keyword in target evaluation information and an evaluation result corresponding to the scene, the server may also determine scene information corresponding to the target evaluation information according to the scene and the evaluation result corresponding to the scene according to a preset relationship, search for a target reply strategy corresponding to the target evaluation information from a third preset mapping table according to the scene and the evaluation result, and then display the scene information and the target reply strategy corresponding to the target evaluation information, that is, send the scene information and the target reply strategy to a second user (merchant) for display, so that when a merchant performs manual reply on customer evaluation, the platform may provide corresponding prompts and guidance for the merchant, thereby improving the quality and efficiency of manual writing of a document by the merchant to a certain extent. The third preset mapping table is used for representing each scene and a corresponding relationship between each evaluation result corresponding to each scene and at least one target reply strategy. The scene information includes each scene and expression information corresponding to an evaluation result corresponding to the each scene.

For example, the preset relationship may include that when the evaluation result corresponding to the scene is a good evaluation, the scene information corresponding to the target keyword may be determined as "the customer may be in a quartic store × (scene)", and when the evaluation result corresponding to the scene is a medium evaluation or a poor evaluation, the scene information corresponding to the target keyword may be determined as "the customer may be in a feedback × (scene) question".

Exemplarily, as shown in fig. 6D, it is a schematic structural diagram of a third preset mapping table according to an exemplary embodiment of the present application. If the target evaluation information 610 shown in fig. 6A is received, the server may determine that the scene information corresponding to the target evaluation information 610 is the "customer feedback taste problem" according to the scene "taste" corresponding to the target keyword of the text information 611 and the evaluation result 612 "1 star" corresponding thereto, and find the target reply policy corresponding to the target evaluation information 610 as "expression apology, explanation reason, improvement measure" from the third preset mapping table shown in fig. 6D. After the merchant clicks the reply control 620 shown in fig. 6A, the server may receive a reply instruction triggered by the merchant at the second user end through the network, so that the scenario information "customer feedback taste problem" and the target reply policy "express apology, explanation reason, and improvement measure" may be sent (recommended) to the second user (merchant) end, as shown in fig. 6C, so that when the merchant performs manual reply customer evaluation, the second user (merchant) end can display that the scenario information 640 "customer feedback taste problem" corresponding to the received target evaluation information 610 and the target reply policy 650 "express apology, explanation reason, and improvement measure" corresponding to the received target evaluation information 610.

According to the embodiment of the application, the target reply information and/or the scene information and the target reply strategy corresponding to the target evaluation information are determined through the scene corresponding to the target keyword in the target evaluation information (customer evaluation) and the evaluation result corresponding to the scene, so that the target reply information corresponding to the target evaluation information (customer evaluation) is recommended to a merchant corresponding to a second user (merchant) and/or the scene information and the target reply strategy corresponding to the target evaluation information (customer evaluation) are displayed, developers are not required to prepare a large amount of reply information according to different target keywords, the operation speed of a server is not influenced, certain guidance and selection can be improved for the merchant to manually reply the customer evaluation, and the reply quality and efficiency of the merchant are improved.

In the process of recommending the target reply information to the merchant, in order to avoid the problems that a developer needs to prepare a large amount of reply information according to different keywords, the workload of the developer is too large, and the like, in addition to recommending the target reply information according to different scenes corresponding to the target keywords in the target evaluation information and evaluation results corresponding to the scenes, the recommendation can be performed according to different scenes corresponding to the target keywords in the target evaluation information and the attributes (categories) of the target keywords, such as positive (first-class) keywords, non-positive (second-class) keywords, and the like. Specifically, refer to fig. 7A, which is a schematic flow chart of another evaluation reply method according to an exemplary embodiment of the present application. As shown in fig. 7A, the evaluation reply method includes the following steps:

step 701, receiving target evaluation information.

Specifically, step 701 is identical to step 201, and is not described herein again.

Step 702, determining a target keyword in the target evaluation information according to a preset keyword lexicon.

Specifically, the number of the target keywords is at least two, and the at least two target keywords include a first type of target keywords and a second type of target keywords. The first type of target keywords are used for representing positive evaluation results. The second category of target keywords characterizes non-positive evaluation results. The first type of target keywords may be positive keywords, and may include fresh, good eating, good attitude, good service, high cost performance, and the like, and the second type of target keywords may be non-positive keywords, and may include stale, bad eating, general attitude, poor service, and the like, which is not limited in the present application. The implementation process of determining the target keyword in the target evaluation information according to the preset keyword lexicon in step 702 is consistent with that in step 202, and is not described herein again.

Step 703, determining a scene corresponding to the first type of target keyword and a scene corresponding to the second type of target keyword.

Specifically, the first type of target keywords include at least one first target keyword corresponding to at least one scene. The first target keyword may be a positive keyword, such as fresh, good eating, good attitude, good service, high cost performance, and the like, which is not limited in the present application. The second type target keywords comprise at least one second target keyword corresponding to at least one scene. The second target keyword may be a non-positive keyword, such as stale, bad taste, general attitude, poor service, and the like, which is not limited in the present application. The scene corresponding to the first target keyword in the first category of target keywords and the scene corresponding to the second target keyword in the second category of target keywords may be the same scene or different scenes. And the scene is used for representing the evaluation dimension corresponding to the target keyword.

Specifically, the determination of the scenes corresponding to the first type of target keywords in step 703 and the specific implementation process of the scenes corresponding to the second type of target keywords in step 403 are consistent, and details are not repeated here.

Step 704, determining first target reply information corresponding to the target evaluation information according to the scene corresponding to the first type of target keywords, and determining second target reply information corresponding to the target evaluation information according to the scene corresponding to the second type of target keywords.

Specifically, the server may find the corresponding reply information according to the scene corresponding to the first type of target keyword from a fourth preset mapping table, determine the reply information as the first target reply information corresponding to the target evaluation information, find the corresponding reply information according to the scene corresponding to the second type of target keyword from the fourth preset mapping table, and determine the reply information as the second target reply information corresponding to the target evaluation information. The fourth preset mapping table is used for representing the corresponding relation among the first type of target keywords, the second type of target keywords, the scene and the reply information.

Exemplarily, as shown in fig. 8, it is a schematic structural diagram of a fourth preset mapping table according to an exemplary embodiment of the present application. If the first type of target keywords in the target evaluation information include a first target keyword "good eating", and the corresponding scene is "taste", and the second type of target keywords in the target evaluation information include a second target keyword "relatively expensive", and the corresponding scene is "cost performance", the server may find the corresponding reply information "good taste of thank you yan zakao > | xxxxxxxx in the reply information" good taste of thank you yan zao zans "from the fourth preset mapping table shown in fig. 8 according to the first target keyword" good eating "and the corresponding scene is" taste ". Seeing your praise, feeling that everything is worth | all the day when the user is busy, and determining the reply information as first target reply information corresponding to the target evaluation information; meanwhile, the server searches corresponding reply information "sorry" from the fourth preset mapping table shown in fig. 8 according to the second target keyword "more expensive" and the scene corresponding to the second target keyword "cost performance", please take away gas till the dish raw materials of the store are delivered every day, and strictly controls the production link of each dish, so the comparison cost is relatively high, and xxxxx is used. And determining the reply information as second target reply information corresponding to the target evaluation information.

According to the embodiment of the application, at least two pieces of target reply information corresponding to the target evaluation information are determined and recommended according to different scenes corresponding to the target keywords in the target evaluation information and the attributes (categories) of the target keywords, such as positive (first-class) keywords, non-positive (second-class) keywords and the like, so that the problems that developers need to prepare a large amount of reply information according to different keywords, the workload of the developers is overlarge and the like can be solved, at least two pieces of different pieces of target reply information can be determined according to different types of target keywords and the scenes corresponding to the target keywords, the target reply information recommended to merchants is richer and more targeted, and the reply quality and the reply efficiency of the merchants when manually replying customer evaluations are improved are achieved.

Optionally, after step 704 is executed, after first target reply information corresponding to the target evaluation information is determined according to a scene corresponding to the first type of target keyword, and second target reply information corresponding to the target evaluation information is determined according to a scene corresponding to the second type of target keyword, the first target reply information and the second target reply information may be recommended to a second user (merchant) end, so that the merchant can select whether to reply the customer evaluation using the first target reply information and the second target reply information and refer to how to reply the customer evaluation, thereby improving the reply quality and the reply efficiency of the merchant in manually replying the customer evaluation. Specifically, as shown in fig. 7B, the evaluation reply method may further include the following steps:

step 705, determining an evaluation result corresponding to the target evaluation information.

Specifically, the evaluation result corresponding to the target evaluation information may be determined based on the target evaluation information. That is, the evaluation result corresponding to the target evaluation information can be found from the target evaluation information. The evaluation result may include 0, 1, 1.5, 5, etc., and may also include good score, medium score, bad score, etc., which is not limited in the present application.

Step 706, determining a recommendation sequence of the first target reply message and the second target reply message according to an evaluation result corresponding to the target evaluation message.

Specifically, the evaluation result corresponding to the target evaluation information includes a first type evaluation result and a second type evaluation result. The first type of evaluation is used to characterize that the evaluation is positive. The first evaluation result includes good evaluation, excellent evaluation, good evaluation, and the like, which is not limited in the present application. The second type of evaluation described above is used to characterize that the evaluation is not positive. The second evaluation result includes poor evaluation, medium evaluation, and medium evaluation, which are not limited in this application. If the evaluation result corresponding to the target evaluation information is the first-type evaluation result, it may be determined that the recommendation order is: first target reply information corresponding to the target evaluation information determined according to a scene corresponding to the first type of target keyword is ranked in front (upper) and second target reply information corresponding to the target evaluation information determined according to a scene corresponding to the second type of target keyword is ranked in back (lower). If the evaluation result corresponding to the target evaluation information is the second type evaluation result, it may be determined that the recommendation order is: second target reply information corresponding to the target evaluation information determined according to the scene corresponding to the second type of target keyword is ranked in front (above), and first target reply information corresponding to the target evaluation information determined according to the scene corresponding to the first type of target keyword is ranked in back (below).

And step 707, recommending the first target reply information and the second target reply information according to the recommendation order.

Specifically, the server may send the first target reply information and the second target reply information to a second user (merchant) according to the recommendation sequence, that is, recommend the first target reply information and the second target reply information to the second user (merchant) according to the recommendation sequence. That is, the server may send the first target reply information and the second target reply information to a second user (merchant) according to the recommendation sequence, so that the second user (merchant) recommends (displays) the first target reply information and the second target reply information to the merchant according to the recommendation sequence.

For example, if the server receives the target evaluation information 910 shown in fig. 9A, i.e. the text information "the pickled fish is too delicious or expensive" evaluated by the customer C, the evaluation result 920 "bad evaluation" corresponding to the target evaluation information 910 is obtained, and after the merchant clicks the reply control 930 shown in fig. 9A, the server may determine the first target reply information 940 "thank you for the good taste of the kokuaizawa. xxxx" corresponding to the target evaluation information 910. Seeing your good comment, feeling that everything is worth while a day is busy!and the second target reply message 950! "arrange in front (above) according to the second target reply information 950, and send the first target reply information 940 to the second user (merchant) end in the recommended order of behind (below), as shown in fig. 9B specifically, so that the second user (merchant) end recommends (displays) the first target reply information 940 and the second target reply information 950 to the merchant according to the recommended order.

Optionally, not limited to the manner of determining the recommendation order of the first target reply information and the second target reply information according to the evaluation result corresponding to the target evaluation information in step 706, in order to simplify the recommendation process, the server may randomly determine the recommendation order of the first target reply information and the second target reply information, that is, may randomly recommend the first target reply information and the second target reply information.

According to the method and the device, the target reply information which is preferentially recommended is selected according to the evaluation result corresponding to the target evaluation information, at least two pieces of target reply information can be recommended aiming at different types of target keywords and corresponding scenes, and the target reply information which is preferentially recommended can be selected aiming at the overall evaluation result corresponding to the target evaluation information, so that the target reply information recommended to the merchant is richer and more targeted, and the reply quality and the reply efficiency of the merchant when the merchant manually replies to the customer evaluation are improved.

Optionally, after step 703 is executed, after first target reply information corresponding to the target evaluation information is determined according to a scene corresponding to the first type of target keyword, and second target reply information corresponding to the target evaluation information is determined according to a scene corresponding to the second type of target keyword, the first target reply information and the second target reply information may be recommended to a second user (merchant) end after certain processing, so as to be selected and referred by the merchant, thereby improving the reply efficiency of the merchant in manually replying the customer evaluation, and further improving the reply quality of the merchant in manually replying the customer evaluation. The first target reply information and the second target reply information are spliced according to a preset rule to obtain third target reply information, so that the third target evaluation information comprises reply contents aiming at the first type of target keywords and the scenes thereof and reply contents aiming at the second type of target keywords and the scenes thereof. The preset rule may be that the first target reply message and the second target reply message are directly spliced according to a preset splicing sequence, or non-critical portions of the first target reply message and the second target reply message are filtered first, and then the first target reply message and the second target reply message are spliced according to the preset splicing sequence, and the like.

According to the embodiment of the application, the first target reply information and the second target reply information are spliced and then recommended to a second user (merchant) end for merchant selection and reference, so that the pertinence of the recommended target reply information is improved, the target reply information recommended to the merchant is richer, and the reply quality of manually replying customer evaluation by the merchant is further improved.

Next, another evaluation recovery method provided in the embodiments of the present application will be described. Specifically, refer to fig. 10, which is a flowchart illustrating another evaluation reply method according to an exemplary embodiment of the present application. As shown in fig. 10, the evaluation reply method includes the following steps:

step 1001 receives target evaluation information.

Specifically, step 1001 is identical to step 201, and is not described herein again.

Step 1002, determining an evaluation result corresponding to the target evaluation information.

Specifically, after receiving the target evaluation information input by the customer at the first user (customer) side, the server may determine an evaluation result corresponding to the target evaluation information according to the target evaluation information. That is, the evaluation result corresponding to the target evaluation information can be found from the target evaluation information. The evaluation result may include 0, 1, 1.5, 5, etc., and may also include good score, medium score, bad score, etc., which is not limited in the present application.

And 1003, recommending the general reply information according to the evaluation result corresponding to the target evaluation information.

Specifically, after determining the evaluation result corresponding to the target evaluation information, the server directly searches for corresponding general reply information from a fifth preset mapping table according to the evaluation result, and recommends the general reply information, that is, sends the recommended general reply information to the second user (merchant) end. The general reply information corresponds to the evaluation result corresponding to each target evaluation information, that is, the evaluation result corresponding to each target evaluation information corresponds to at least one piece of general reply information. The fifth preset mapping table is used for representing a relationship between the general reply information and the evaluation result corresponding to each target evaluation information.

Exemplarily, as shown in fig. 11, it is a schematic structural diagram of a fifth preset mapping table according to an exemplary embodiment of the present application. If the target evaluation information 1210 shown in fig. 12A is received, the server may determine the evaluation result 1211 included in the target evaluation information 1210 as the evaluation result corresponding to the target evaluation information 1210, and find the general reply information "sorry" corresponding to the target evaluation information 1210 from the fifth preset mapping table shown in fig. 11 according to the evaluation result 1211, for what reason you are so unsatisfied. And the user can be advised when the user is convenient. XX. ". After the merchant clicks the reply control 1220 in fig. 12A, the server may receive a reply instruction triggered by the merchant at the second user end through the network, so that the general reply information corresponding to the target evaluation information 1210 may be sent (recommended) to the second user (merchant) end, as shown in fig. 12B, so that when the merchant performs manual reply to the customer evaluation, the second user (merchant) end can show the merchant (recommendation) that the general reply information 1230 ″ corresponding to the target evaluation information 1210 is very sorry, which is why you are so unsatisfied. And the user can be advised when the user is convenient. And XX. ".

According to the embodiment of the application, the general reply information corresponding to the overall evaluation result is recommended to the merchant only according to the overall evaluation result of the target evaluation information, the workload of developers is greatly reduced, the process of recommending the reply information to the merchant is greatly reduced, the functions of providing reference and selection for the merchant when the merchant replies the customer evaluation by manually writing the text are also played, and the reply quality and efficiency of manually replying the customer evaluation by the merchant are improved.

Not limited to the manner of recommending only the general reply information or the target reply information in the above embodiments, the target reply information, the general reply information, the scenario information, and the target reply policy may also be recommended simultaneously in combination with the above embodiments, specifically as shown in fig. 13A, when the merchant clicks the view template or slides up the control 1310, the second user (merchant) will enter the page shown in fig. 13B, that is, the merchant may view the multiple pieces of target reply information and the general reply information recommended by the server. The merchant may slide up and down the floating layer in the page as shown in fig. 13B to view more reply templates. When the merchant wants to reply by using the first reply template, or modify and reply based on the first reply template, the merchant may click the use control corresponding to the first reply template in fig. 13A, so as to enter the page shown in fig. 13C, that is, fill the first template into the input box, call up the keyboard, and collect the template recommendation. When the merchant wants to view the evaluation reply template again, the keyboard can be retracted by clicking the template control 1320 in fig. 13C, and the page shown in fig. 13B is returned to when the merchant recalls the reply template. When the merchant has determined the content that needs to be replied, the user may also click the submit control in the keyboard in the page shown in fig. 13C, so that the second user (merchant) receives the input box and completes the manual reply to the customer rating.

When a merchant at a second user (merchant) wants to manually write a document to reply to a customer evaluation, the evaluation reply method provided by the embodiment of the application can provide high-quality reply information related to the customer evaluation for the merchant as a reference, so that the merchant is guided to improve the service quality, efficient and high-quality evaluation reply is provided for the customer, and the satisfaction and the use viscosity of the user (merchant and customer) are improved. Specifically, refer to fig. 14, which is a schematic flow chart illustrating another evaluation reply method according to an exemplary embodiment of the present application. As shown in fig. 14, the evaluation reply method includes the following steps:

step 1401, the customer end sends the target evaluation information to the merchant end.

Specifically, when a customer inputs target evaluation information, which is customer evaluation, into a customer version of software installed on a customer side, the customer side sends the target evaluation information to a merchant side through a network.

Step 1402, the merchant terminal responds to the preset operation and sends the target evaluation information to the server.

Specifically, after the merchant receives the target evaluation information from the customer end, if the merchant wants to manually write and reply the target evaluation information, the merchant may perform a preset operation (for example, but not limited to, an operation of clicking to reply the target evaluation information, and the like) in the merchant version software, so as to trigger the merchant to send the target evaluation information to the server through the network.

Alternatively, after the customer inputs the target evaluation information of the customer evaluation in the customer version software installed on the customer side, the customer side may directly transmit the target evaluation information to the server through the network, so that the server can receive the target evaluation information input by the customer in the customer version software through the network.

Step 1403, the server determines a target keyword in the target evaluation information according to a preset keyword lexicon.

Specifically, step 1403 is identical to step 202, and is not described here.

In step 1404, the server determines target reply information corresponding to the target evaluation information according to the target keyword.

Specifically, step 1404 is identical to step 203, and is not described herein again.

Step 1405, the server sends the target reply message to the merchant terminal.

Specifically, after determining the target reply information corresponding to the target evaluation information according to the target keyword, the server may directly send the target reply information to the merchant side through the network for display.

Specifically, after the merchant receives the target evaluation information from the customer end, if the merchant wants to manually write and reply the target evaluation information, the merchant may perform a preset operation (for example, but not limited to, an operation of clicking and replying the target evaluation information, and the like) in the merchant version software, so as to trigger a target reply instruction corresponding to the target evaluation information, which is sent from the merchant to the server through the network. After receiving the target reply instruction, the server can send the target reply information corresponding to the determined target evaluation information to the merchant end through the network, so that when a merchant at the merchant end wants to manually write a document to reply to the evaluation of a customer, high-quality reply information related to the evaluation of the customer is provided for the merchant end as a reference, the merchant is guided to improve the service quality, efficient and high-quality evaluation reply is provided for the customer, and the satisfaction degree and the use viscosity of the user (the merchant and the customer) are improved.

Please refer to fig. 15, which is a schematic structural diagram of an evaluation recovery apparatus according to an embodiment of the present application. The evaluation recovery device 1500 includes:

a receiving module 1510 configured to receive target evaluation information;

a first determining module 1520, configured to determine a target keyword in the target evaluation information according to a preset keyword lexicon; the preset keyword lexicon comprises a plurality of keywords;

the second determining module 1530 is configured to determine the target reply information corresponding to the target evaluation information according to the target keyword.

In a possible implementation manner, the first determining module 1520 includes:

the matching unit is used for matching the keywords in a preset keyword lexicon with the target evaluation information to obtain the matching degree of the keywords and the target evaluation information;

and the first determining unit is used for determining the keywords with the matching degree larger than or equal to a preset threshold as the target keywords in the target evaluation information.

In a possible implementation manner, the second determining module is specifically configured to: determining a scene corresponding to the target keyword and an evaluation result corresponding to the scene; the scene is used for representing the evaluation dimension corresponding to the target keyword;

In a possible implementation manner, the evaluation reply apparatus 1500 further includes:

and the display module is used for displaying the scene information and the target reply strategy corresponding to the target evaluation information according to the scene corresponding to the target keyword and the evaluation result corresponding to the scene.

In a possible implementation manner, the number of the target keywords is at least two, and the at least two target keywords include a first type of target keywords and a second type of target keywords; the first type of target keywords are used for representing positive evaluation results; the second category target keywords are used for representing non-positive evaluation results; the second determining module 1530 is specifically further configured to: determining scenes corresponding to the first type of target keywords and scenes corresponding to the second type of target keywords; the scene is used for representing the evaluation dimension corresponding to the target keyword; and determining first target reply information corresponding to the target evaluation information according to the scene corresponding to the first type of target keywords, and determining second target reply information corresponding to the target evaluation information according to the scene corresponding to the second type of target keywords.

a third determining module, configured to determine an evaluation result corresponding to the target evaluation information;

a fourth determining module, configured to determine, according to an evaluation result corresponding to the target evaluation information, a recommendation order of the first target reply information and the second target reply information;

and the recommending module is used for recommending the first target reply information and the second target reply information according to the recommending sequence.

a fifth determining module, configured to determine the third target reply message according to the first target reply message and the second target reply message; and the third target reply message is obtained by splicing the first target reply message and the second target reply message according to a preset rule.

In a possible implementation manner, the preset keyword lexicon further includes a mapping relationship between each keyword and a scene; when determining the scene corresponding to the target keyword, the second determining module is specifically configured to: and determining a scene corresponding to the target keyword according to the target keyword and the mapping relation.

In a possible implementation manner, the recommending module is further configured to: recommending general reply information according to the evaluation result corresponding to the target evaluation information; the general reply information corresponds to an evaluation result corresponding to each of the target evaluation information.

Please refer to fig. 16, which is a schematic structural diagram of another evaluation recovery apparatus according to an embodiment of the present application. The evaluation recovery device 1600 includes:

a receiving module 1610 configured to receive target evaluation information;

an obtaining module 1620, configured to obtain the target reply information in response to a preset operation; the target reply information is determined by the target keywords in the target evaluation information; the target keyword is determined according to a preset keyword lexicon and the target evaluation information; the preset keyword lexicon comprises a plurality of keywords.

The division of the modules in the evaluation recovery device is only for illustration, and in other embodiments, the evaluation recovery device may be divided into different modules as needed to complete all or part of the functions of the evaluation recovery device. The implementation of each module in the evaluation reply device provided in the embodiment of the present application may be in the form of a computer program. The computer program may be run on a terminal or a server. The program modules constituted by the computer program may be stored on the memory of the terminal or the server. The computer program, when executed by a processor, implements all or part of the steps of the evaluation reply method described in the embodiments of the present application.

Referring to fig. 17, fig. 17 is a schematic structural diagram of an electronic device according to an exemplary embodiment of the present application. As shown in fig. 17, the electronic device 1700 may include: at least one processor 1710, at least one network interface 1720, a user interface 1730, memory 1740, and at least one communication bus 1750.

A communication bus 1750 may be used to implement the connection communication of the above components, among others.

User interface 1730 may include a Display screen (Display) and a Camera (Camera), and optional user interfaces may include standard wired and wireless interfaces.

The network interface 1720 may optionally include a bluetooth module, a Near Field Communication (NFC) module, a Wireless Fidelity (Wi-Fi) module, and the like.

Among other things, the processor 1710 may include one or more processing cores. The processor 1710 interfaces with various components throughout the electronic device 1700 using various interfaces and circuitry to perform various functions and process data for the routing electronic device 1700 by executing or executing instructions, programs, code sets, or instruction sets stored within the memory 1740, and calling data stored within the memory 1740. Optionally, the processor 1710 may be implemented in at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). The processor 1710 may integrate one or more of a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a modem, and the like. Wherein, the CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for rendering and drawing the content required to be displayed by the display screen; the modem is used to handle wireless communications. It is to be understood that the modem may be implemented by a single chip without being integrated into the processor 1710.

The Memory 1740 may include a Random Access Memory (RAM) or a Read-Only Memory (ROM). Optionally, the memory 1740 includes non-transitory computer readable media. Memory 1740 may be used to store instructions, programs, code sets, or instruction sets. The memory 1740 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for at least one function (e.g., receiving target evaluation information, determining target reply information corresponding to the target evaluation information, etc.), instructions for implementing the various method embodiments described above, and the like; the storage data area may store data and the like referred to in the above respective method embodiments. The memory 1740 may alternatively be at least one memory device located remotely from the processor 1710. As shown in fig. 17, the memory 1740, which is one type of computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program.

In some possible embodiments, the electronic device 1700 may be the aforementioned evaluation reply device shown in fig. 15, and in the electronic device 1700 shown in fig. 17, the user interface 1730 is mainly used for providing an input interface for the user, such as a key on the evaluation reply device, and the like, and acquiring an instruction triggered by the user; the processor 1710 may be configured to call the application stored in the memory 1740 and specifically perform the following operations: receiving target evaluation information; determining a target keyword in the target evaluation information according to a preset keyword lexicon; the preset keyword lexicon comprises a plurality of keywords; and determining target reply information corresponding to the target evaluation information according to the target keywords.

In some possible embodiments, when the processor 1710 determines the target keyword in the target evaluation information according to a preset keyword lexicon, the processor is specifically configured to: matching keywords in a preset keyword lexicon with the target evaluation information to obtain the matching degree of the keywords and the target evaluation information; and determining the keywords with the matching degree larger than or equal to a preset threshold value as the target keywords in the target evaluation information.

In some possible embodiments, when the processor 1710 executes the target reply information corresponding to the target evaluation information determined according to the target keyword, the processor is specifically configured to execute: determining a scene corresponding to the target keyword and an evaluation result corresponding to the scene; the scene is used for representing the evaluation dimension corresponding to the target keyword; and determining target reply information corresponding to the target evaluation information according to the scene and the evaluation result corresponding to the scene.

In some possible embodiments, after the processor 1710 performs the determining of the scene corresponding to the target keyword and the evaluation result corresponding to the scene, the processor 1710 is further configured to perform: and displaying scene information and a target reply strategy corresponding to the target evaluation information according to the scene corresponding to the target keyword and the evaluation result corresponding to the scene.

In some possible embodiments, the number of the target keywords is at least two, and the at least two target keywords include a first type of target keywords and a second type of target keywords; the first type of target keywords are used for representing positive evaluation results; the second category target keywords are used for representing non-positive evaluation results;

the processor 1710 is specifically configured to, when executing the step of identifying the target response information corresponding to the target evaluation information according to the target keyword, execute: determining scenes corresponding to the first type of target keywords and scenes corresponding to the second type of target keywords; the scene is used for representing the evaluation dimension corresponding to the target keyword; and determining first target reply information corresponding to the target evaluation information according to the scene corresponding to the first type of target keywords, and determining second target reply information corresponding to the target evaluation information according to the scene corresponding to the second type of target keywords.

In some possible embodiments, after the processor 1710 performs determining, according to the target keyword, target reply information corresponding to the target evaluation information, the processor is further configured to perform: determining an evaluation result corresponding to the target evaluation information; determining a recommendation sequence of the first target reply message and the second target reply message according to an evaluation result corresponding to the target evaluation message; and recommending the first target reply information and the second target reply information according to the recommendation sequence.

In some possible embodiments, after the processor 1710 performs determining, according to the target keyword, target reply information corresponding to the target evaluation information, the processor is further configured to perform: determining the third target reply message according to the first target reply message and the second target reply message; and the third target reply message is obtained by splicing the first target reply message and the second target reply message according to a preset rule.

In some possible embodiments, the preset keyword lexicon further includes a mapping relationship between each keyword and a scene;

the processor 1710 is specifically configured to, when executing the determining of the scene corresponding to the target keyword, execute: and determining a scene corresponding to the target keyword according to the target keyword and the mapping relation.

In some possible embodiments, after the processor 1710 performs the receiving of the target evaluation information, the processor 1710 is further configured to perform: determining an evaluation result corresponding to the target evaluation information; recommending general reply information according to the evaluation result corresponding to the target evaluation information; the general reply information corresponds to an evaluation result corresponding to each of the target evaluation information.

In some possible embodiments, the electronic device 1700 may be the evaluation reply apparatus shown in fig. 16, and the processor 1710 may be configured to call an application program stored in the memory 1740, and specifically perform the following operations: receiving target evaluation information; responding to preset operation, and acquiring target reply information; the target reply information is determined by the target keywords in the target evaluation information; the target keyword is determined according to a preset keyword lexicon and the target evaluation information; the preset keyword lexicon comprises a plurality of keywords.

Embodiments of the present application also provide a computer-readable storage medium having stored therein instructions, which when executed on a computer or processor, cause the computer or processor to perform one or more of the steps of the above embodiments. The constituent modules of the evaluation reply device may be stored in the computer-readable storage medium if they are implemented in the form of software functional units and sold or used as independent products.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in or transmitted over a computer-readable storage medium. The computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)), or wirelessly (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., a floppy Disk, a hard Disk, a magnetic tape), an optical medium (e.g., a Digital Versatile Disk (DVD)), or a semiconductor medium (e.g., a Solid State Disk (SSD)), among others.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the program is executed. And the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks. The technical features in the present examples and embodiments may be arbitrarily combined without conflict.

The above-described embodiments are merely illustrative of the preferred embodiments of the present application, and are not intended to limit the scope of the present application, and various modifications and improvements made to the technical solutions of the present application by those skilled in the art without departing from the spirit of the present application should fall within the protection scope defined by the claims.

The foregoing description of specific embodiments of the present application has been presented. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

Claims

1. An evaluation reply method, characterized in that the method comprises:

receiving target evaluation information;

determining target keywords in the target evaluation information according to a preset keyword lexicon; the preset keyword lexicon comprises a plurality of keywords;

2. The method of claim 1, wherein the determining the target keyword in the target evaluation information according to a preset keyword lexicon comprises:

3. The method of claim 1, wherein the determining the target reply information corresponding to the target evaluation information according to the target keyword comprises:

determining a scene corresponding to the target keyword and an evaluation result corresponding to the scene; the scene is used for representing evaluation dimensions corresponding to the target keywords;

4. The method of claim 3, wherein after determining a scene corresponding to the target keyword and an evaluation result corresponding to the scene, the method further comprises:

5. The method of claim 1, wherein the number of the target keywords is at least two, at least two of the target keywords comprising a first type of target keyword and a second type of target keyword; the first type of target keywords are used for representing positive evaluation results; the second type of target keywords are used for representing non-positive evaluation results;

the determining of the target reply information corresponding to the target evaluation information according to the target keyword comprises:

determining scenes corresponding to the first type of target keywords and scenes corresponding to the second type of target keywords; the scene is used for representing evaluation dimensions corresponding to the target keywords;

6. The method of claim 5, wherein after determining the target reply information corresponding to the target evaluation information according to the target keyword, the method further comprises:

7. The method of claim 5, wherein after determining the target reply information corresponding to the target evaluation information according to the target keyword, the method further comprises:

determining the third target reply information according to the first target reply information and the second target reply information; and the third target reply information is obtained by splicing the first target reply information and the second target reply information according to a preset rule.

8. The method of claim 3, wherein the predetermined keyword lexicon further comprises a mapping relationship between each keyword and the scene;

the determining the scene corresponding to the target keyword includes:

9. The method of claim 1, wherein after receiving the target evaluation information, the method further comprises:

recommending general reply information according to an evaluation result corresponding to the target evaluation information; the general reply information corresponds to the evaluation result corresponding to each target evaluation information.

10. An evaluation reply method, characterized in that the method comprises:

receiving target evaluation information;

responding to preset operation, and acquiring target reply information; the target reply information is determined by target keywords in the target evaluation information; the target keyword is determined according to a preset keyword lexicon and the target evaluation information; the preset keyword lexicon comprises a plurality of keywords.

11. An electronic device, comprising: a processor and a memory;

the processor is connected with the memory;

the memory for storing executable program code;

the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory for performing the method of any one of claims 1-10.

12. A computer storage medium, characterized in that it stores a plurality of instructions adapted to be loaded by a processor and to perform the method steps according to any of claims 1-10.